From a6f4d6a893aa48aac340fcceb97b0dda7d84b491 Mon Sep 17 00:00:00 2001 From: Jimmy Lin Date: Mon, 27 May 2024 19:54:06 -0400 Subject: [PATCH] Repackage prebuilt indexes for MS MARCO V1 LTR + Mr.TyDi (Lucene) (#1895) Adopts new, consistent schema for naming --- docs/2cr/mrtydi.html | 44 ++-- docs/2cr/msmarco-v2-passage.html | 90 ++++---- docs/prebuilt-indexes.md | 58 +++--- .../sparse/test_lucenesearcher_check_irst.py | 1 - ...cenesearcher_check_ltr_msmarco_document.py | 2 +- ...ucenesearcher_check_ltr_msmarco_passage.py | 2 +- pyserini/2cr/mrtydi.yaml | 22 +- pyserini/prebuilt_index_info.py | 193 +++++++++--------- ...tydi-v1.1-arabic.20220108.6fcb89.README.md | 13 -- ...tydi-v1.1-arabic.20220928.b5ecc5.README.md | 17 -- ...ydi-v1.1-bengali.20220108.6fcb89.README.md | 13 -- ...ydi-v1.1-bengali.20220928.b5ecc5.README.md | 17 -- ...ydi-v1.1-english.20220108.6fcb89.README.md | 13 -- ...ydi-v1.1-english.20220928.b5ecc5.README.md | 17 -- ...ydi-v1.1-finnish.20220108.6fcb89.README.md | 13 -- ...ydi-v1.1-finnish.20220928.b5ecc5.README.md | 17 -- ...-v1.1-indonesian.20220108.6fcb89.README.md | 13 -- ...-v1.1-indonesian.20220928.b5ecc5.README.md | 17 -- ...di-v1.1-japanese.20220108.6fcb89.README.md | 13 -- ...di-v1.1-japanese.20220928.b5ecc5.README.md | 17 -- ...tydi-v1.1-korean.20220108.6fcb89.README.md | 13 -- ...tydi-v1.1-korean.20220928.b5ecc5.README.md | 17 -- ...ydi-v1.1-russian.20220108.6fcb89.README.md | 13 -- ...ydi-v1.1-russian.20220928.b5ecc5.README.md | 17 -- ...ydi-v1.1-swahili.20220108.6fcb89.README.md | 16 -- ...ydi-v1.1-swahili.20220928.b5ecc5.README.md | 17 -- ...tydi-v1.1-telugu.20220108.6fcb89.README.md | 16 -- ...tydi-v1.1-telugu.20220928.b5ecc5.README.md | 17 -- ...mrtydi-v1.1-thai.20220108.6fcb89.README.md | 13 -- ...mrtydi-v1.1-thai.20220928.b5ecc5.README.md | 17 -- ...rted.mrtydi-v1.1.20220928.b5ecc5.README.md | 160 +++++++++++++++ ...segmented.ltr.20211031.33e4151.README.txt} | 0 ...1-passage.ltr.20210519.e25e33f.README.txt} | 0 pyserini/search/lucene/ltr/__main__.py | 62 +++--- pyserini/search/lucene/ltr/_search_msmarco.py | 5 +- tests/test_prebuilt_index.py | 4 +- 36 files changed, 399 insertions(+), 580 deletions(-) delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220928.b5ecc5.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220108.6fcb89.README.md delete mode 100644 pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220928.b5ecc5.README.md create mode 100644 pyserini/resources/index-metadata/lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md rename pyserini/resources/index-metadata/{index-msmarco-doc-per-passage-ltr-readme.txt => lucene-inverted.msmarco-v1-doc-segmented.ltr.20211031.33e4151.README.txt} (100%) rename pyserini/resources/index-metadata/{index-msmarco-passage-ltr-20210519-e25e33f-readme.txt => lucene-inverted.msmarco-v1-passage.ltr.20210519.e25e33f.README.txt} (100%) diff --git a/docs/2cr/mrtydi.html b/docs/2cr/mrtydi.html index 0d16bf504..507b6f946 100644 --- a/docs/2cr/mrtydi.html +++ b/docs/2cr/mrtydi.html @@ -235,7 +235,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ar \ --topics mrtydi-v1.1-arabic-test \ - --index mrtydi-v1.1-arabic \ + --index mrtydi-v1.1-ar \ --output run.mrtydi.bm25.ar.test.txt --bm25 --hits 100 Evaluation commands: @@ -255,7 +255,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language bn \ --topics mrtydi-v1.1-bengali-test \ - --index mrtydi-v1.1-bengali \ + --index mrtydi-v1.1-bn \ --output run.mrtydi.bm25.bn.test.txt --bm25 --hits 100 Evaluation commands: @@ -275,7 +275,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language en \ --topics mrtydi-v1.1-english-test \ - --index mrtydi-v1.1-english \ + --index mrtydi-v1.1-en \ --output run.mrtydi.bm25.en.test.txt --bm25 --hits 100 Evaluation commands: @@ -295,7 +295,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language fi \ --topics mrtydi-v1.1-finnish-test \ - --index mrtydi-v1.1-finnish \ + --index mrtydi-v1.1-fi \ --output run.mrtydi.bm25.fi.test.txt --bm25 --hits 100 Evaluation commands: @@ -315,7 +315,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language id \ --topics mrtydi-v1.1-indonesian-test \ - --index mrtydi-v1.1-indonesian \ + --index mrtydi-v1.1-id \ --output run.mrtydi.bm25.id.test.txt --bm25 --hits 100 Evaluation commands: @@ -335,7 +335,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ja \ --topics mrtydi-v1.1-japanese-test \ - --index mrtydi-v1.1-japanese \ + --index mrtydi-v1.1-ja \ --output run.mrtydi.bm25.ja.test.txt --bm25 --hits 100 Evaluation commands: @@ -355,7 +355,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ko \ --topics mrtydi-v1.1-korean-test \ - --index mrtydi-v1.1-korean \ + --index mrtydi-v1.1-ko \ --output run.mrtydi.bm25.ko.test.txt --bm25 --hits 100 Evaluation commands: @@ -375,7 +375,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ru \ --topics mrtydi-v1.1-russian-test \ - --index mrtydi-v1.1-russian \ + --index mrtydi-v1.1-ru \ --output run.mrtydi.bm25.ru.test.txt --bm25 --hits 100 Evaluation commands: @@ -395,7 +395,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language sw \ --topics mrtydi-v1.1-swahili-test \ - --index mrtydi-v1.1-swahili \ + --index mrtydi-v1.1-sw \ --output run.mrtydi.bm25.sw.test.txt --bm25 --hits 100 Evaluation commands: @@ -415,7 +415,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language te \ --topics mrtydi-v1.1-telugu-test \ - --index mrtydi-v1.1-telugu \ + --index mrtydi-v1.1-te \ --output run.mrtydi.bm25.te.test.txt --bm25 --hits 100 Evaluation commands: @@ -435,7 +435,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language th \ --topics mrtydi-v1.1-thai-test \ - --index mrtydi-v1.1-thai \ + --index mrtydi-v1.1-th \ --output run.mrtydi.bm25.th.test.txt --bm25 --hits 100 Evaluation commands: @@ -1740,7 +1740,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ar \ --topics mrtydi-v1.1-arabic-test \ - --index mrtydi-v1.1-arabic \ + --index mrtydi-v1.1-ar \ --output run.mrtydi.bm25.ar.test.txt --bm25 --hits 100 Evaluation commands: @@ -1760,7 +1760,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language bn \ --topics mrtydi-v1.1-bengali-test \ - --index mrtydi-v1.1-bengali \ + --index mrtydi-v1.1-bn \ --output run.mrtydi.bm25.bn.test.txt --bm25 --hits 100 Evaluation commands: @@ -1780,7 +1780,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language en \ --topics mrtydi-v1.1-english-test \ - --index mrtydi-v1.1-english \ + --index mrtydi-v1.1-en \ --output run.mrtydi.bm25.en.test.txt --bm25 --hits 100 Evaluation commands: @@ -1800,7 +1800,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language fi \ --topics mrtydi-v1.1-finnish-test \ - --index mrtydi-v1.1-finnish \ + --index mrtydi-v1.1-fi \ --output run.mrtydi.bm25.fi.test.txt --bm25 --hits 100 Evaluation commands: @@ -1820,7 +1820,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language id \ --topics mrtydi-v1.1-indonesian-test \ - --index mrtydi-v1.1-indonesian \ + --index mrtydi-v1.1-id \ --output run.mrtydi.bm25.id.test.txt --bm25 --hits 100 Evaluation commands: @@ -1840,7 +1840,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ja \ --topics mrtydi-v1.1-japanese-test \ - --index mrtydi-v1.1-japanese \ + --index mrtydi-v1.1-ja \ --output run.mrtydi.bm25.ja.test.txt --bm25 --hits 100 Evaluation commands: @@ -1860,7 +1860,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ko \ --topics mrtydi-v1.1-korean-test \ - --index mrtydi-v1.1-korean \ + --index mrtydi-v1.1-ko \ --output run.mrtydi.bm25.ko.test.txt --bm25 --hits 100 Evaluation commands: @@ -1880,7 +1880,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language ru \ --topics mrtydi-v1.1-russian-test \ - --index mrtydi-v1.1-russian \ + --index mrtydi-v1.1-ru \ --output run.mrtydi.bm25.ru.test.txt --bm25 --hits 100 Evaluation commands: @@ -1900,7 +1900,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language sw \ --topics mrtydi-v1.1-swahili-test \ - --index mrtydi-v1.1-swahili \ + --index mrtydi-v1.1-sw \ --output run.mrtydi.bm25.sw.test.txt --bm25 --hits 100 Evaluation commands: @@ -1920,7 +1920,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language te \ --topics mrtydi-v1.1-telugu-test \ - --index mrtydi-v1.1-telugu \ + --index mrtydi-v1.1-te \ --output run.mrtydi.bm25.te.test.txt --bm25 --hits 100 Evaluation commands: @@ -1940,7 +1940,7 @@

Mr.TyDi

--threads 16 --batch-size 128 \ --language th \ --topics mrtydi-v1.1-thai-test \ - --index mrtydi-v1.1-thai \ + --index mrtydi-v1.1-th \ --output run.mrtydi.bm25.th.test.txt --bm25 --hits 100 Evaluation commands: diff --git a/docs/2cr/msmarco-v2-passage.html b/docs/2cr/msmarco-v2-passage.html index d335ea256..fc5781d47 100644 --- a/docs/2cr/msmarco-v2-passage.html +++ b/docs/2cr/msmarco-v2-passage.html @@ -875,7 +875,7 @@

MS MARCO V2 Passage

python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5 \
+  --index msmarco-v2-passage.d2q-t5 \
   --topics dl21 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-default.dl21.txt \
   --bm25
@@ -896,7 +896,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5 \
+  --index msmarco-v2-passage.d2q-t5 \
   --topics dl22 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-default.dl22.txt \
   --bm25
@@ -917,7 +917,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5 \
+  --index msmarco-v2-passage.d2q-t5 \
   --topics dl23 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-default.dl23.txt \
   --bm25
@@ -938,7 +938,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5 \
+  --index msmarco-v2-passage.d2q-t5 \
   --topics msmarco-v2-passage-dev \
   --output run.msmarco-v2-passage.bm25-d2q-t5-default.dev.txt \
   --bm25
@@ -958,7 +958,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5 \
+  --index msmarco-v2-passage.d2q-t5 \
   --topics msmarco-v2-passage-dev2 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-default.dev2.txt \
   --bm25
@@ -1033,7 +1033,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5 \
+  --index msmarco-v2-passage-augmented.d2q-t5 \
   --topics dl21 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-augmented-default.dl21.txt \
   --bm25
@@ -1054,7 +1054,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5 \
+  --index msmarco-v2-passage-augmented.d2q-t5 \
   --topics dl22 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-augmented-default.dl22.txt \
   --bm25
@@ -1075,7 +1075,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5 \
+  --index msmarco-v2-passage-augmented.d2q-t5 \
   --topics dl23 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-augmented-default.dl23.txt \
   --bm25
@@ -1096,7 +1096,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5 \
+  --index msmarco-v2-passage-augmented.d2q-t5 \
   --topics msmarco-v2-passage-dev \
   --output run.msmarco-v2-passage.bm25-d2q-t5-augmented-default.dev.txt \
   --bm25
@@ -1116,7 +1116,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5 \
+  --index msmarco-v2-passage-augmented.d2q-t5 \
   --topics msmarco-v2-passage-dev2 \
   --output run.msmarco-v2-passage.bm25-d2q-t5-augmented-default.dev2.txt \
   --bm25
@@ -1191,7 +1191,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5-docvectors \
+  --index msmarco-v2-passage.d2q-t5-docvectors \
   --topics dl21 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-default.dl21.txt \
   --bm25 --rm3
@@ -1212,7 +1212,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5-docvectors \
+  --index msmarco-v2-passage.d2q-t5-docvectors \
   --topics dl22 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-default.dl22.txt \
   --bm25 --rm3
@@ -1233,7 +1233,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5-docvectors \
+  --index msmarco-v2-passage.d2q-t5-docvectors \
   --topics dl23 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-default.dl23.txt \
   --bm25 --rm3
@@ -1254,7 +1254,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5-docvectors \
+  --index msmarco-v2-passage.d2q-t5-docvectors \
   --topics msmarco-v2-passage-dev \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-default.dev.txt \
   --bm25 --rm3
@@ -1274,7 +1274,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-d2q-t5-docvectors \
+  --index msmarco-v2-passage.d2q-t5-docvectors \
   --topics msmarco-v2-passage-dev2 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-default.dev2.txt \
   --bm25 --rm3
@@ -1349,7 +1349,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5-docvectors \
+  --index msmarco-v2-passage-augmented.d2q-t5-docvectors \
   --topics dl21 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-augmented-default.dl21.txt \
   --bm25 --rm3
@@ -1370,7 +1370,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5-docvectors \
+  --index msmarco-v2-passage-augmented.d2q-t5-docvectors \
   --topics dl22 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-augmented-default.dl22.txt \
   --bm25 --rm3
@@ -1391,7 +1391,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5-docvectors \
+  --index msmarco-v2-passage-augmented.d2q-t5-docvectors \
   --topics dl23 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-augmented-default.dl23.txt \
   --bm25 --rm3
@@ -1412,7 +1412,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5-docvectors \
+  --index msmarco-v2-passage-augmented.d2q-t5-docvectors \
   --topics msmarco-v2-passage-dev \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-augmented-default.dev.txt \
   --bm25 --rm3
@@ -1432,7 +1432,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-augmented-d2q-t5-docvectors \
+  --index msmarco-v2-passage-augmented.d2q-t5-docvectors \
   --topics msmarco-v2-passage-dev2 \
   --output run.msmarco-v2-passage.bm25-rm3-d2q-t5-augmented-default.dev2.txt \
   --bm25 --rm3
@@ -1508,7 +1508,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics dl21-unicoil-noexp \
   --output run.msmarco-v2-passage.unicoil-noexp.dl21.txt \
   --hits 1000 --impact
@@ -1529,7 +1529,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics dl22-unicoil-noexp \
   --output run.msmarco-v2-passage.unicoil-noexp.dl22.txt \
   --hits 1000 --impact
@@ -1550,7 +1550,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics dl23-unicoil-noexp \
   --output run.msmarco-v2-passage.unicoil-noexp.dl23.txt \
   --hits 1000 --impact
@@ -1571,7 +1571,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics msmarco-v2-passage-dev-unicoil-noexp \
   --output run.msmarco-v2-passage.unicoil-noexp.dev.txt \
   --hits 1000 --impact
@@ -1591,7 +1591,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics msmarco-v2-passage-dev2-unicoil-noexp \
   --output run.msmarco-v2-passage.unicoil-noexp.dev2.txt \
   --hits 1000 --impact
@@ -1666,7 +1666,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics dl21-unicoil \
   --output run.msmarco-v2-passage.unicoil.dl21.txt \
   --hits 1000 --impact
@@ -1687,7 +1687,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics dl22-unicoil \
   --output run.msmarco-v2-passage.unicoil.dl22.txt \
   --hits 1000 --impact
@@ -1708,7 +1708,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics dl23-unicoil \
   --output run.msmarco-v2-passage.unicoil.dl23.txt \
   --hits 1000 --impact
@@ -1729,7 +1729,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics msmarco-v2-passage-dev-unicoil \
   --output run.msmarco-v2-passage.unicoil.dev.txt \
   --hits 1000 --impact
@@ -1749,7 +1749,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics msmarco-v2-passage-dev2-unicoil \
   --output run.msmarco-v2-passage.unicoil.dev2.txt \
   --hits 1000 --impact
@@ -1825,7 +1825,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics dl21 \
   --encoder castorini/unicoil-noexp-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-noexp-otf.dl21.txt \
@@ -1847,7 +1847,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics dl22 \
   --encoder castorini/unicoil-noexp-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-noexp-otf.dl22.txt \
@@ -1869,7 +1869,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics dl23 \
   --encoder castorini/unicoil-noexp-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-noexp-otf.dl23.txt \
@@ -1891,7 +1891,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics msmarco-v2-passage-dev \
   --encoder castorini/unicoil-noexp-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-noexp-otf.dev.txt \
@@ -1912,7 +1912,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-noexp-0shot \
+  --index msmarco-v2-passage.unicoil-noexp-0shot \
   --topics msmarco-v2-passage-dev2 \
   --encoder castorini/unicoil-noexp-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-noexp-otf.dev2.txt \
@@ -1988,7 +1988,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics dl21 \
   --encoder castorini/unicoil-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-otf.dl21.txt \
@@ -2010,7 +2010,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics dl22 \
   --encoder castorini/unicoil-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-otf.dl22.txt \
@@ -2032,7 +2032,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics dl23 \
   --encoder castorini/unicoil-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-otf.dl23.txt \
@@ -2054,7 +2054,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics msmarco-v2-passage-dev \
   --encoder castorini/unicoil-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-otf.dev.txt \
@@ -2075,7 +2075,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-unicoil-0shot \
+  --index msmarco-v2-passage.unicoil-0shot \
   --topics msmarco-v2-passage-dev2 \
   --encoder castorini/unicoil-msmarco-passage \
   --output run.msmarco-v2-passage.unicoil-otf.dev2.txt \
@@ -2151,7 +2151,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-slimr-pp-norefine-0shot \
+  --index msmarco-v2-passage.slimr-pp \
   --topics dl21 \
   --encoder castorini/slimr-pp-msmarco-passage \
   --output run.msmarco-v2-passage.slimr-pp.dl21.txt \
@@ -2173,7 +2173,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-slimr-pp-norefine-0shot \
+  --index msmarco-v2-passage.slimr-pp \
   --topics dl22 \
   --encoder castorini/slimr-pp-msmarco-passage \
   --output run.msmarco-v2-passage.slimr-pp.dl22.txt \
@@ -2195,7 +2195,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-slimr-pp-norefine-0shot \
+  --index msmarco-v2-passage.slimr-pp \
   --topics dl23 \
   --encoder castorini/slimr-pp-msmarco-passage \
   --output run.msmarco-v2-passage.slimr-pp.dl23.txt \
@@ -2217,7 +2217,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-slimr-pp-norefine-0shot \
+  --index msmarco-v2-passage.slimr-pp \
   --topics msmarco-v2-passage-dev \
   --encoder castorini/slimr-pp-msmarco-passage \
   --output run.msmarco-v2-passage.slimr-pp.dev.txt \
@@ -2238,7 +2238,7 @@ 
MS MARCO V2 Passage

   

 
python -m pyserini.search.lucene \
   --threads 16 --batch-size 128 \
-  --index msmarco-v2-passage-slimr-pp-norefine-0shot \
+  --index msmarco-v2-passage.slimr-pp \
   --topics msmarco-v2-passage-dev2 \
   --encoder castorini/slimr-pp-msmarco-passage \
   --output run.msmarco-v2-passage.slimr-pp.dev2.txt \
diff --git a/docs/prebuilt-indexes.md b/docs/prebuilt-indexes.md
index 3b564e7c3..8096ecebe 100644
--- a/docs/prebuilt-indexes.md
+++ b/docs/prebuilt-indexes.md
@@ -110,15 +110,13 @@ Detailed configuration information for the pre-built indexes are stored in [`pys
 [readme]
 
Lucene index (+docvectors) of the MS MARCO V1 passage corpus with doc2query-T5 expansions.
 

-
msmarco-passage-ltr
-[readme]
-
Lucene index of the MS MARCO passage corpus with four extra preprocessed fields for LTR. (Lucene 8)
+
msmarco-v1-passage.ltr
+[readme]
+
Lucene index of the MS MARCO V1 passage corpus with four extra preprocessed fields for LTR. (Lucene 8)
 

-
msmarco-doc-per-passage-ltr
-
Lucene index of the MS MARCO document per-passage corpus with four extra preprocessed fields for LTR. (Lucene 8)
-

-
msmarco-document-segment-ltr
-
Lucene index of the MS MARCO document segmented corpus with four extra preprocessed fields for LTR. (Lucene 8)
+
msmarco-v1-doc-segmented.ltr
+[readme]
+
Lucene index of the MS MARCO V1 segmented document corpus with four extra preprocessed fields for LTR. (Lucene 8)
 

 
msmarco-v2-doc
 [readme]
@@ -436,48 +434,48 @@ Detailed configuration information for the pre-built indexes are stored in [`pys
 
 
 

-
mrtydi-v1.1-arabic
-[readme]
+
mrtydi-v1.1-ar
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Arabic).
 

-
mrtydi-v1.1-bengali
-[readme]
+
mrtydi-v1.1-bn
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Bengali).
 

-
mrtydi-v1.1-english
-[readme]
+
mrtydi-v1.1-en
+[readme]
 
Lucene index for Mr.TyDi v1.1 (English).
 

-
mrtydi-v1.1-finnish
-[readme]
+
mrtydi-v1.1-fi
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Finnish).
 

-
mrtydi-v1.1-indonesian
-[readme]
+
mrtydi-v1.1-id
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Indonesian).
 

-
mrtydi-v1.1-japanese
-[readme]
+
mrtydi-v1.1-ja
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Japanese).
 

-
mrtydi-v1.1-korean
-[readme]
+
mrtydi-v1.1-ko
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Korean).
 

-
mrtydi-v1.1-russian
-[readme]
+
mrtydi-v1.1-ru
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Russian).
 

-
mrtydi-v1.1-swahili
-[readme]
+
mrtydi-v1.1-sw
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Swahili).
 

-
mrtydi-v1.1-telugu
-[readme]
+
mrtydi-v1.1-te
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Telugu).
 

-
mrtydi-v1.1-thai
-[readme]
+
mrtydi-v1.1-th
+[readme]
 
Lucene index for Mr.TyDi v1.1 (Thai).
 

 

diff --git a/integrations/sparse/test_lucenesearcher_check_irst.py b/integrations/sparse/test_lucenesearcher_check_irst.py
index fe2a1181f..cd2d9bdd0 100644
--- a/integrations/sparse/test_lucenesearcher_check_irst.py
+++ b/integrations/sparse/test_lucenesearcher_check_irst.py
@@ -102,7 +102,6 @@ def test_max_aggregation_dl19(self):
         self.assertEqual(stderr, '')
         self.assertEqual(map_score, 0.3286)
         self.assertEqual(ndcg_score, 0.5371)
-        
 
     def test_max_aggregation_dl20_passage(self):
         # dl20 passage max
diff --git a/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_document.py b/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_document.py
index d1cf09dca..73da5b4af 100644
--- a/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_document.py
+++ b/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_document.py
@@ -44,7 +44,7 @@ def test_reranking(self):
                     --topic tools/topics-and-qrels/topics.msmarco-doc.dev.txt \
                     --model ltr_test/msmarco-passage-ltr-mrr-v1/   \
                     --qrel tools/topics-and-qrels/qrels.msmarco-doc.dev.txt \
-                    --index msmarco-doc-per-passage-ltr --ibm-model ltr_test/ibm_model/ \
+                    --index msmarco-v1-doc-segmented.ltr --ibm-model ltr_test/ibm_model/ \
                     --granularity document --output ltr_test/{outp} --max-passage --hits 10000')
 
         result = subprocess.check_output(f'python tools/scripts/msmarco/msmarco_doc_eval.py --judgments tools/topics-and-qrels/qrels.msmarco-doc.dev.txt --run ltr_test/{outp}', shell=True).decode(sys.stdout.encoding)
diff --git a/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_passage.py b/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_passage.py
index acb333aa1..def199306 100644
--- a/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_passage.py
+++ b/integrations/sparse/test_lucenesearcher_check_ltr_msmarco_passage.py
@@ -45,7 +45,7 @@ def test_reranking(self):
                     --model ltr_test/msmarco-passage-ltr-mrr-v1 \
                     --topic tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \
                     --qrel tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt \
-                    --index msmarco-passage-ltr --ibm-model ltr_test/ibm_model/ \
+                    --index msmarco-v1-passage.ltr --ibm-model ltr_test/ibm_model/ \
                     --output-format tsv --output ltr_test/{outp}')
         result = subprocess.check_output(f'python tools/scripts/msmarco/msmarco_passage_eval.py tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt ltr_test/{outp}', shell=True).decode(sys.stdout.encoding)
         a,b = result.find('#####################\nMRR @10:'), result.find('\nQueriesRanked: 6980\n#####################\n')
diff --git a/pyserini/2cr/mrtydi.yaml b/pyserini/2cr/mrtydi.yaml
index 174d81cd3..5ca1c7e7c 100644
--- a/pyserini/2cr/mrtydi.yaml
+++ b/pyserini/2cr/mrtydi.yaml
@@ -714,7 +714,7 @@ conditions:
   # BM25
   - name: bm25.ar
     eval_key: mrtydi-v1.1-arabic
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ar --topics mrtydi-v1.1-arabic-${split} --index mrtydi-v1.1-arabic --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ar --topics mrtydi-v1.1-arabic-${split} --index mrtydi-v1.1-ar --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -730,7 +730,7 @@ conditions:
             R@100: 0.7928
   - name: bm25.bn
     eval_key: mrtydi-v1.1-bengali
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language bn --topics mrtydi-v1.1-bengali-${split} --index mrtydi-v1.1-bengali --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language bn --topics mrtydi-v1.1-bengali-${split} --index mrtydi-v1.1-bn --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -746,7 +746,7 @@ conditions:
           - R@100: 0.8694
   - name: bm25.en
     eval_key: mrtydi-v1.1-english
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language en --topics mrtydi-v1.1-english-${split} --index mrtydi-v1.1-english --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language en --topics mrtydi-v1.1-english-${split} --index mrtydi-v1.1-en --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -762,7 +762,7 @@ conditions:
           - R@100: 0.5365
   - name: bm25.fi
     eval_key: mrtydi-v1.1-finnish
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language fi --topics mrtydi-v1.1-finnish-${split} --index mrtydi-v1.1-finnish --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language fi --topics mrtydi-v1.1-finnish-${split} --index mrtydi-v1.1-fi --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -778,7 +778,7 @@ conditions:
           - R@100: 0.7196
   - name: bm25.id
     eval_key: mrtydi-v1.1-indonesian
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language id --topics mrtydi-v1.1-indonesian-${split} --index mrtydi-v1.1-indonesian --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language id --topics mrtydi-v1.1-indonesian-${split} --index mrtydi-v1.1-id --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -794,7 +794,7 @@ conditions:
           - R@100: 0.8426
   - name: bm25.ja
     eval_key: mrtydi-v1.1-japanese
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ja --topics mrtydi-v1.1-japanese-${split} --index mrtydi-v1.1-japanese --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ja --topics mrtydi-v1.1-japanese-${split} --index mrtydi-v1.1-ja --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -810,7 +810,7 @@ conditions:
           - R@100: 0.6431
   - name: bm25.ko
     eval_key: mrtydi-v1.1-korean
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ko --topics mrtydi-v1.1-korean-${split} --index mrtydi-v1.1-korean --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ko --topics mrtydi-v1.1-korean-${split} --index mrtydi-v1.1-ko --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -826,7 +826,7 @@ conditions:
           - R@100: 0.6188
   - name: bm25.ru
     eval_key: mrtydi-v1.1-russian
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ru --topics mrtydi-v1.1-russian-${split} --index mrtydi-v1.1-russian --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language ru --topics mrtydi-v1.1-russian-${split} --index mrtydi-v1.1-ru --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -842,7 +842,7 @@ conditions:
           - R@100: 0.6541
   - name: bm25.sw
     eval_key: mrtydi-v1.1-swahili
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language sw --topics mrtydi-v1.1-swahili-${split} --index mrtydi-v1.1-swahili --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language sw --topics mrtydi-v1.1-swahili-${split} --index mrtydi-v1.1-sw --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -858,7 +858,7 @@ conditions:
           - R@100: 0.7642
   - name: bm25.te
     eval_key: mrtydi-v1.1-telugu
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language te --topics mrtydi-v1.1-telugu-${split} --index mrtydi-v1.1-telugu --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language te --topics mrtydi-v1.1-telugu-${split} --index mrtydi-v1.1-te --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
@@ -874,7 +874,7 @@ conditions:
           - R@100: 0.8971
   - name: bm25.th
     eval_key: mrtydi-v1.1-thai
-    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language th --topics mrtydi-v1.1-thai-${split} --index mrtydi-v1.1-thai --output $output --bm25 --hits 100
+    command: python -m pyserini.search.lucene --threads ${sparse_threads} --batch-size ${sparse_batch_size} --language th --topics mrtydi-v1.1-thai-${split} --index mrtydi-v1.1-th --output $output --bm25 --hits 100
     splits:
       - split: train
         scores:
diff --git a/pyserini/prebuilt_index_info.py b/pyserini/prebuilt_index_info.py
index 1c429b23f..a30875e9c 100644
--- a/pyserini/prebuilt_index_info.py
+++ b/pyserini/prebuilt_index_info.py
@@ -238,48 +238,34 @@
     },
 
     # MS MARCO V1 indexes for LTR experiments.
-    "msmarco-passage-ltr": {
-        "description": "Lucene index of the MS MARCO passage corpus with four extra preprocessed fields for LTR. (Lucene 8)",
-        "filename": "index-msmarco-passage-ltr-20210519-e25e33f.tar.gz",
-        "readme": "index-msmarco-passage-ltr-20210519-e25e33f-readme.txt",
+    "msmarco-v1-passage.ltr": {
+        "description": "Lucene index of the MS MARCO V1 passage corpus with four extra preprocessed fields for LTR. (Lucene 8)",
+        "filename": "lucene-inverted.msmarco-v1-passage.ltr.20210519.e25e33f.tar.gz",
+        "readme": "lucene-inverted.msmarco-v1-passage.ltr.20210519.e25e33f.README.txt",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/index-msmarco-passage-ltr-20210519-e25e33f.tar.gz",
-            "https://vault.cs.uwaterloo.ca/s/8qFCaCtwabRfYQD/download"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.msmarco-v1-passage.ltr.20210519.e25e33f.tar.gz"
         ],
-        "md5": "a5de642c268ac1ed5892c069bdc29ae3",
-        "size compressed (bytes)": 14073966046,
+        "md5": "5da425ca44d2e3e5c38a7f564f13ad23",
+        "size compressed (bytes)": 14073966165,
         "total_terms": 352316036,
         "documents": 8841823,
         "unique_terms": 2660824,
         "downloaded": False
     },
-    "msmarco-doc-per-passage-ltr": {
-        "description": "Lucene index of the MS MARCO document per-passage corpus with four extra preprocessed fields for LTR. (Lucene 8)",
-        "filename": "index-msmarco-doc-per-passage-ltr-20211031-33e4151.tar.gz",
+    "msmarco-v1-doc-segmented.ltr": {
+        "description": "Lucene index of the MS MARCO V1 segmented document corpus with four extra preprocessed fields for LTR. (Lucene 8)",
+        "filename": "lucene-inverted.msmarco-v1-doc-segmented.ltr.20211031.33e4151.tar.gz",
+        "readme": "lucene-inverted.msmarco-v1-doc-segmented.ltr.20211031.33e4151.README.txt",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/index-msmarco-doc-per-passage-ltr-20211031-33e4151.tar.gz",
-            "https://vault.cs.uwaterloo.ca/s/kNdXMWXEsTt3fT8/download"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.msmarco-v1-doc-segmented.ltr.20211031.33e4151.tar.gz",
         ],
-        "md5": "bd60e89041b4ebbabc4bf0cfac608a87",
-        "size compressed (bytes)": 45835520960,
+        "md5": "86f108d8441b6845f8caf1208dd7ac7a",
+        "size compressed (bytes)": 45835523273,
         "total_terms": 1232004740,
         "documents": 20545628,
         "unique_terms": 10123678,
         "downloaded": False
     },
-    "msmarco-document-segment-ltr": {
-        "description": "Lucene index of the MS MARCO document segmented corpus with four extra preprocessed fields for LTR. (Lucene 8)",
-        "filename": "lucene-index.msmarco-doc-segmented.ibm.tar.gz",
-        "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.msmarco-doc-segmented.ibm.tar.gz"
-        ],
-        "md5": "13064bdaf8e8a79222634d67ecd3ddb5",
-        "size compressed (bytes)": 98984853515,
-        "total_terms": 3197500226,
-        "documents": 20532330,
-        "unique_terms": -1,
-        "downloaded": False
-    },
 
     # MS MARCO V2 document corpus, three indexes with different amounts of information (and sizes).
     "msmarco-v2-doc": {
@@ -1404,155 +1390,155 @@
 }
 
 TF_INDEX_INFO_MRTYDI = {
-    "mrtydi-v1.1-arabic": {
+    "mrtydi-v1.1-ar": {
         "description": "Lucene index for Mr.TyDi v1.1 (Arabic).",
-        "filename": "lucene-index.mrtydi-v1.1-arabic.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-arabic.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-ar.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-arabic.20220928.b5ecc5.tar.gz",
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-ar.20220928.b5ecc5.tar.gz",
         ],
-        "md5": "efff40a2548f759eb8b0e47e0622685b",
-        "size compressed (bytes)": 1420441600,
+        "md5": "eae9ed3430eeb685328c92be886197d3",
+        "size compressed (bytes)": 1166813697,
         "total_terms": 92529032,
         "documents": 2106586,
         "unique_terms": 1284748,
         "downloaded": False
     },
-    "mrtydi-v1.1-bengali": {
+    "mrtydi-v1.1-bn": {
         "description": "Lucene index for Mr.TyDi v1.1 (Bengali).",
-        "filename": "lucene-index.mrtydi-v1.1-bengali.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-bengali.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-bn.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-bengali.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-bn.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "6ed844c8f17b2f041fba7c5676d3fb42",
-        "size compressed (bytes)": 294942720,
+        "md5": "4fdb127c48c311851875d884ccf9d3e7",
+        "size compressed (bytes)": 240163624,
         "total_terms": 15236599,
         "documents": 304059,
         "unique_terms": 520699,
         "downloaded": False
     },
-    "mrtydi-v1.1-english": {
+    "mrtydi-v1.1-en": {
         "description": "Lucene index for Mr.TyDi v1.1 (English).",
-        "filename": "lucene-index.mrtydi-v1.1-english.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-english.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-en.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-english.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-en.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "e6b0a2531d958c3d1a65634dc315b0ab",
-        "size compressed (bytes)": 20566118400,
+        "md5": "98eb2e28b120c9fac2aa43fa370d0d27",
+        "size compressed (bytes)": 16732696856,
         "total_terms": 1507060932,
         "documents": 32907100,
         "unique_terms": -1,
         "downloaded": False
     },
-    "mrtydi-v1.1-finnish": {
+    "mrtydi-v1.1-fi": {
         "description": "Lucene index for Mr.TyDi v1.1 (Finnish).",
-        "filename": "lucene-index.mrtydi-v1.1-finnish.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-finnish.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-fi.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-finnish.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-fi.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "0f464c022447eed5431157f0b2feb0b3",
-        "size compressed (bytes)": 1116272640,
+        "md5": "c5546562c77bd28bb1ab68ca24c5b37a",
+        "size compressed (bytes)": 906509667,
         "total_terms": 69416543,
         "documents": 1908757,
         "unique_terms": 1715076,
         "downloaded": False
     },
-    "mrtydi-v1.1-indonesian": {
+    "mrtydi-v1.1-id": {
         "description": "Lucene index for Mr.TyDi v1.1 (Indonesian).",
-        "filename": "lucene-index.mrtydi-v1.1-indonesian.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-indonesian.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-id.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-indonesian.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-id.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "345d43a2443786a3394a93a6f7ef77b7",
-        "size compressed (bytes)": 698388480,
+        "md5": "551b282737fd885b1904ea365768c066",
+        "size compressed (bytes)": 562187620,
         "total_terms": 52493134,
         "documents": 1469399,
         "unique_terms": 942552,
         "downloaded": False
     },
-    "mrtydi-v1.1-japanese": {
+    "mrtydi-v1.1-ja": {
         "description": "Lucene index for Mr.TyDi v1.1 (Japanese).",
-        "filename": "lucene-index.mrtydi-v1.1-japanese.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-japanese.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-ja.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-japanese.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-ja.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "5f0802c1257c325a3e25c58523dba841",
-        "size compressed (bytes)": 4333844480,
+        "md5": "6f5062b65c69ce37c8a4e76d08e6d5c4",
+        "size compressed (bytes)": 3637126847,
         "total_terms": 300761975,
         "documents": 7000027,
         "unique_terms": 1588879,
         "downloaded": False
     },
-    "mrtydi-v1.1-korean": {
+    "mrtydi-v1.1-ko": {
         "description": "Lucene index for Mr.TyDi v1.1 (Korean).",
-        "filename": "lucene-index.mrtydi-v1.1-korean.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-korean.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-ko.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-korean.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-ko.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "4277f406b138c46edf7c17e4248f3b2e",
-        "size compressed (bytes)": 1349109760,
+        "md5": "a52bfe4be87fd3178ca231b007e7af38",
+        "size compressed (bytes)": 1137658449,
         "total_terms": 122217295,
         "documents": 1496126,
         "unique_terms": 1517179,
         "downloaded": False
     },
-    "mrtydi-v1.1-russian": {
+    "mrtydi-v1.1-ru": {
         "description": "Lucene index for Mr.TyDi v1.1 (Russian).",
-        "filename": "lucene-index.mrtydi-v1.1-russian.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-russian.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-ru.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-russian.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-ru.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "d5837fee29c60c7a3a24cfd598056038",
-        "size compressed (bytes)": 6864660480,
+        "md5": "dc1d75d31595252e3a6b665b522adf3b",
+        "size compressed (bytes)": 5642484260,
         "total_terms": 346329117,
         "documents": 9597504,
         "unique_terms": 3034240,
         "downloaded": False
     },
-    "mrtydi-v1.1-swahili": {
+    "mrtydi-v1.1-sw": {
         "description": "Lucene index for Mr.TyDi v1.1 (Swahili).",
-        "filename": "lucene-index.mrtydi-v1.1-swahili.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-swahili.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-sw.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-swahili.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-sw.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "bebff76ec6dfe76c904604f8ed1bcd3e",
-        "size compressed (bytes)": 59607040,
+        "md5": "4514e4a3f35279408a2e0aea3051dce0",
+        "size compressed (bytes)": 47557469,
         "total_terms": 4937051,
         "documents": 136689,
         "unique_terms": 385711,
         "downloaded": False
     },
-    "mrtydi-v1.1-telugu": {
+    "mrtydi-v1.1-te": {
         "description": "Lucene index for Mr.TyDi v1.1 (Telugu).",
-        "filename": "lucene-index.mrtydi-v1.1-telugu.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-telugu.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-te.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-telugu.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-te.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "89f8b280cacbdc27e90bb1ea40029c21",
-        "size compressed (bytes)": 519157760,
+        "md5": "4bd62ef02febb49a487e765c023507de",
+        "size compressed (bytes)": 413881826,
         "total_terms": 26812052,
         "documents": 548224,
         "unique_terms": 1157217,
         "downloaded": False
     },
-    "mrtydi-v1.1-thai": {
+    "mrtydi-v1.1-th": {
         "description": "Lucene index for Mr.TyDi v1.1 (Thai).",
-        "filename": "lucene-index.mrtydi-v1.1-thai.20220928.b5ecc5.tar.gz",
-        "readme": "lucene-index.mrtydi-v1.1-thai.20220928.b5ecc5.README.md",
+        "filename": "lucene-inverted.mrtydi-v1.1-th.20220928.b5ecc5.tar.gz",
+        "readme": "lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md",
         "urls": [
-            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene-index.mrtydi-v1.1-thai.20220928.b5ecc5.tar.gz"
+            "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.mrtydi-v1.1-th.20220928.b5ecc5.tar.gz"
         ],
-        "md5": "047152fc6bc1b5c5d945f38b23de971e",
-        "size compressed (bytes)": 546201600,
+        "md5": "d040c15b460d488571eb959192335771",
+        "size compressed (bytes)": 450209352,
         "total_terms": 31550936,
         "documents": 568855,
         "unique_terms": 663628,
@@ -1560,6 +1546,20 @@
     }
 }
 
+TF_INDEX_INFO_MRTYDI_ALIASES = {
+    "mrtydi-v1.1-arabic": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-ar"],
+    "mrtydi-v1.1-bengali": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-bn"],
+    "mrtydi-v1.1-english": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-en"],
+    "mrtydi-v1.1-finnish": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-fi"],
+    "mrtydi-v1.1-indonesian": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-id"],
+    "mrtydi-v1.1-japanese": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-ja"],
+    "mrtydi-v1.1-korean": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-ko"],
+    "mrtydi-v1.1-russian": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-ru"],
+    "mrtydi-v1.1-swahili": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-sw"],
+    "mrtydi-v1.1-telugu": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-te"],
+    "mrtydi-v1.1-thai": TF_INDEX_INFO_MRTYDI["mrtydi-v1.1-th"]
+}
+
 TF_INDEX_INFO_MIRACL = {
     "miracl-v1.0-ar": {
         "description": "Lucene index for MIRACL v1.0 (Arabic).",
@@ -2498,6 +2498,7 @@
                  **TF_INDEX_INFO_MSMARCO_ALIASES,
                  **TF_INDEX_INFO_BEIR,
                  **TF_INDEX_INFO_MRTYDI,
+                 **TF_INDEX_INFO_MRTYDI_ALIASES,
                  **TF_INDEX_INFO_MIRACL,
                  **TF_INDEX_INFO_CIRAL,
                  **TF_INDEX_INFO_OTHER,
@@ -2790,7 +2791,9 @@
 
 IMPACT_INDEX_INFO_MSMARCO_ALIASES = {
     # To preserve working commands in published papers: integrations/papers/test_sigir2022.py testcase test_Trotman_etal
-    "msmarco-passage-unicoil-d2q": IMPACT_INDEX_INFO_MSMARCO["msmarco-v1-passage.unicoil"]
+    "msmarco-passage-unicoil-d2q": IMPACT_INDEX_INFO_MSMARCO["msmarco-v1-passage.unicoil"],
+    # To preserve working commands in published papers: integrations/papers/test_sigir2022.py testcase test_Ma_etal_section4_1b
+    "msmarco-v2-passage-unicoil-0shot": IMPACT_INDEX_INFO_MSMARCO["msmarco-v2-passage.unicoil-0shot"]
 }
 
 IMPACT_INDEX_INFO_BEIR = {
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220108.6fcb89.README.md
deleted file mode 100644
index 0b3e01f26..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-arabic
-
-Lucene index for Mr.TyDi v1.1 (Arabic).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-arabic/ \
-  -index indexes/lucene-index.mrtydi-v1.1-arabic.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language ar
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220928.b5ecc5.README.md
deleted file mode 100644
index 451c03a78..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-arabic.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-arabic
-
-Lucene index for Mr.TyDi v1.1 (Arabic).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=arabic
-abbr=ar
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220108.6fcb89.README.md
deleted file mode 100644
index 8d6565e9d..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-bengali
-
-Lucene index for Mr.TyDi v1.1 (Bengali).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-bengali/ \
-  -index indexes/lucene-index.mrtydi-v1.1-bengali.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language bn
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220928.b5ecc5.README.md
deleted file mode 100644
index a7a1e252a..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-bengali.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-bengali
-
-Lucene index for Mr.TyDi v1.1 (Bengali).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=bengali
-abbr=bn
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220108.6fcb89.README.md
deleted file mode 100644
index 8c4f02f19..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-english
-
-Lucene index for Mr.TyDi v1.1 (English).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-english/ \
-  -index indexes/lucene-index.mrtydi-v1.1-english.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language en
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220928.b5ecc5.README.md
deleted file mode 100644
index b664d41a3..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-english.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-english
-
-Lucene index for Mr.TyDi v1.1 (English).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=english
-abbr=en
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220108.6fcb89.README.md
deleted file mode 100644
index 10b161844..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-finnish
-
-Lucene index for Mr.TyDi v1.1 (Finnish).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-finnish/ \
-  -index indexes/lucene-index.mrtydi-v1.1-finnish.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language fi
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220928.b5ecc5.README.md
deleted file mode 100644
index 156c59490..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-finnish.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-finnish
-
-Lucene index for Mr.TyDi v1.1 (Finnish).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=finnish
-abbr=fi
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220108.6fcb89.README.md
deleted file mode 100644
index 13570f274..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-indonesian
-
-Lucene index for Mr.TyDi v1.1 (Indonesian).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-indonesian/ \
-  -index indexes/lucene-index.mrtydi-v1.1-indonesian.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language id
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220928.b5ecc5.README.md
deleted file mode 100644
index 0a8b36fe6..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-indonesian.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-indonesian
-
-Lucene index for Mr.TyDi v1.1 (Indonesian).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=indonesian
-abbr=id
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220108.6fcb89.README.md
deleted file mode 100644
index a78a572a0..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-japanese
-
-Lucene index for Mr.TyDi v1.1 (Japanese).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-japanese/ \
-  -index indexes/lucene-index.mrtydi-v1.1-japanese.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language ja
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220928.b5ecc5.README.md
deleted file mode 100644
index 3fc37ed50..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-japanese.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-japanese
-
-Lucene index for Mr.TyDi v1.1 (Japanese).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=japanese
-abbr=ja
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220108.6fcb89.README.md
deleted file mode 100644
index 3810f6261..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-korean
-
-Lucene index for Mr.TyDi v1.1 (Korean).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-korean/ \
-  -index indexes/lucene-index.mrtydi-v1.1-korean.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language ko
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220928.b5ecc5.README.md
deleted file mode 100644
index ed106fd28..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-korean.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-korean
-
-Lucene index for Mr.TyDi v1.1 (Korean).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=korean
-abbr=ko
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220108.6fcb89.README.md
deleted file mode 100644
index 7df1ccbf9..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-russian
-
-Lucene index for Mr.TyDi v1.1 (Russian).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-russian/ \
-  -index indexes/lucene-index.mrtydi-v1.1-russian.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language ru
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220928.b5ecc5.README.md
deleted file mode 100644
index 3ee7340f3..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-russian.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-russian
-
-Lucene index for Mr.TyDi v1.1 (Russian).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=russian
-abbr=ru
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220108.6fcb89.README.md
deleted file mode 100644
index 5d7fd59cf..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# mrtydi-v1.1-swahili
-
-Lucene index for Mr.TyDi v1.1 (Swahili).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-swahili/ \
-  -index indexes/lucene-index.mrtydi-v1.1-swahili.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -pretokenized
-```
-
-Note that `-language sw` gives identical results (and is more semantically accurate) but since we do not have a language-specific tokenizer here, we just use the whitespace tokenizer, which is what `-pretokenized` uses.
-This index was built based on Anserini regressions at the time; see [Anserini #1727](https://github.com/castorini/anserini/pull/1727).
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220928.b5ecc5.README.md
deleted file mode 100644
index 02e7bb875..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-swahili.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-swahili
-
-Lucene index for Mr.TyDi v1.1 (Swahili).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=swahili
-abbr=sw
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220108.6fcb89.README.md
deleted file mode 100644
index eedd6e194..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# mrtydi-v1.1-telugu
-
-Lucene index for Mr.TyDi v1.1 (Telugu).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-telugu/ \
-  -index indexes/lucene-index.mrtydi-v1.1-telugu.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -pretokenized
-```
-
-Note that `-language te` gives identical results (and is more semantically accurate) but since we do not have a language-specific tokenizer here, we just use the whitespace tokenizer, which is what `-pretokenized` uses.
-This index was built based on Anserini regressions at the time; see [Anserini #1727](https://github.com/castorini/anserini/pull/1727).
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220928.b5ecc5.README.md
deleted file mode 100644
index 2f4bcd9b0..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-telugu.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-telugu
-
-Lucene index for Mr.TyDi v1.1 (Telugu).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=telugu
-abbr=te
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220108.6fcb89.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220108.6fcb89.README.md
deleted file mode 100644
index 296e30f8a..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220108.6fcb89.README.md
+++ /dev/null
@@ -1,13 +0,0 @@
-# mrtydi-v1.1-thai
-
-Lucene index for Mr.TyDi v1.1 (Thai).
-
-This index was generated on 2022/01/08 at Anserini commit [`6fcb89`](https://github.com/castorini/anserini/commit/6fcb896c61e2b8cf2f235def3e95dda5fe4cd2fc) on `orca` with the following command:
-
-```
-target/appassembler/bin/IndexCollection -collection MrTyDiCollection \
-  -generator DefaultLuceneDocumentGenerator -threads 1 \
-  -input /store/collections/mr-tydi-corpus/mrtydi-v1.1-thai/ \
-  -index indexes/lucene-index.mrtydi-v1.1-thai.20220108.6fcb89/ \
-  -storePositions -storeDocvectors -storeRaw -optimize -language th
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220928.b5ecc5.README.md
deleted file mode 100644
index 5a23bafff..000000000
--- a/pyserini/resources/index-metadata/lucene-index.mrtydi-v1.1-thai.20220928.b5ecc5.README.md
+++ /dev/null
@@ -1,17 +0,0 @@
-# mrtydi-v1.1-thai
-
-Lucene index for Mr.TyDi v1.1 (Thai).
-
-This index was generated on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca` with the following command:
-
-```
-lang=thai
-abbr=th
-
-target/appassembler/bin/IndexCollection \
-    -collection MrTyDiCollection \
-    -input MrTyDi/miracl-corpus-v1.0-$lang \
-    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
-    -generator DefaultLuceneDocumentGenerator \
-    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
-```
\ No newline at end of file
diff --git a/pyserini/resources/index-metadata/lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md b/pyserini/resources/index-metadata/lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md
new file mode 100644
index 000000000..3430111f6
--- /dev/null
+++ b/pyserini/resources/index-metadata/lucene-inverted.mrtydi-v1.1.20220928.b5ecc5.README.md
@@ -0,0 +1,160 @@
+# mrtydi-v1.1
+
+The following indexes were built on 2022/09/28 at Anserini commit [`b5ecc5`](https://github.com/castorini/anserini/commit/b5ecc5aff79ddfc82b175f6bd3048f5039f0480f) on `orca`.
+
+At the time each index was built, the full name of the language was used.
+In May 2024, as part of repackaging indexes to adopt a more consistent naming scheme, the indexes were renamed to use standard two-letter language codes (e.g., `mrtydi-v1.1-ar` instead of `mrtydi-v1.1-arabic`).
+
+**mrtydi-v1.1-arabic**: Lucene index for Mr.TyDi v1.1 (Arabic).
+
+```
+lang=arabic
+abbr=ar
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-bengali**: Lucene index for Mr.TyDi v1.1 (Bengali).
+
+```
+lang=bengali
+abbr=bn
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-english**: Lucene index for Mr.TyDi v1.1 (English).
+
+```
+lang=english
+abbr=en
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-finnish**: Lucene index for Mr.TyDi v1.1 (Finnish).
+
+```
+lang=finnish
+abbr=fi
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-indonesian**: Lucene index for Mr.TyDi v1.1 (Indonesian).
+
+```
+lang=indonesian
+abbr=id
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-japanese**: Lucene index for Mr.TyDi v1.1 (Japanese).
+
+```
+lang=japanese
+abbr=ja
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-korean**: Lucene index for Mr.TyDi v1.1 (Korean).
+
+```
+lang=korean
+abbr=ko
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-russian**: Lucene index for Mr.TyDi v1.1 (Russian).
+
+```
+lang=russian
+abbr=ru
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-swahili**: Lucene index for Mr.TyDi v1.1 (Swahili).
+
+```
+lang=swahili
+abbr=sw
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-telugu**: Lucene index for Mr.TyDi v1.1 (Telugu).
+
+```
+lang=telugu
+abbr=te
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
+
+**mrtydi-v1.1-thai**: Lucene index for Mr.TyDi v1.1 (Thai).
+
+```
+lang=thai
+abbr=th
+
+target/appassembler/bin/IndexCollection \
+    -collection MrTyDiCollection \
+    -input MrTyDi/miracl-corpus-v1.0-$lang \
+    -index indexes-miracl/lucene-index.mrtydi-v1.1-$lang \
+    -generator DefaultLuceneDocumentGenerator \
+    -threads 16 -storePositions -storeDocvectors -storeRaw -language $abbr
+```
diff --git a/pyserini/resources/index-metadata/index-msmarco-doc-per-passage-ltr-readme.txt b/pyserini/resources/index-metadata/lucene-inverted.msmarco-v1-doc-segmented.ltr.20211031.33e4151.README.txt
similarity index 100%
rename from pyserini/resources/index-metadata/index-msmarco-doc-per-passage-ltr-readme.txt
rename to pyserini/resources/index-metadata/lucene-inverted.msmarco-v1-doc-segmented.ltr.20211031.33e4151.README.txt
diff --git a/pyserini/resources/index-metadata/index-msmarco-passage-ltr-20210519-e25e33f-readme.txt b/pyserini/resources/index-metadata/lucene-inverted.msmarco-v1-passage.ltr.20210519.e25e33f.README.txt
similarity index 100%
rename from pyserini/resources/index-metadata/index-msmarco-passage-ltr-20210519-e25e33f-readme.txt
rename to pyserini/resources/index-metadata/lucene-inverted.msmarco-v1-passage.ltr.20210519.e25e33f.README.txt
diff --git a/pyserini/search/lucene/ltr/__main__.py b/pyserini/search/lucene/ltr/__main__.py
index 1278487c3..4bef7c9eb 100644
--- a/pyserini/search/lucene/ltr/__main__.py
+++ b/pyserini/search/lucene/ltr/__main__.py
@@ -14,19 +14,13 @@
 # limitations under the License.
 #
 
-import sys
-
-# We're going to explicitly use a local installation of Pyserini (as opposed to a pip-installed one).
-# Comment these lines out to use a pip-installed one instead.
-sys.path.insert(0, './')
-
 import argparse
 import numpy as np
 import pandas as pd
+
 from tqdm import tqdm
 from collections import defaultdict
 from transformers import AutoTokenizer
-from pyserini.search.lucene.ltr._search_msmarco import MsmarcoLtrSearcher
 from pyserini.search.lucene.ltr import *
 from pyserini.search.lucene import LuceneSearcher
 from pyserini.analysis import Analyzer, get_lucene_analyzer
@@ -34,36 +28,37 @@
 """
 Running prediction on candidates
 """
+
+
 def dev_data_loader(file, format, topic, rerank, prebuilt, qrel, granularity, top=1000):
     if rerank:
         if format == 'tsv':
-            dev = pd.read_csv(file, sep="\t",
-                            names=['qid', 'pid', 'rank'],
-                            dtype={'qid': 'S','pid': 'S', 'rank':'i',})
+            dev = pd.read_csv(file, sep="\t", names=['qid', 'pid', 'rank'],
+                              dtype={'qid': 'S', 'pid': 'S', 'rank': 'i'})
         elif format == 'trec':
             dev = pd.read_csv(file, sep="\s+",
-                        names=['qid', 'q0', 'pid', 'rank', 'score', 'tag'],
-                        usecols=['qid', 'pid', 'rank'],
-                        dtype={'qid': 'S','pid': 'S', 'rank':'i',})
+                              names=['qid', 'q0', 'pid', 'rank', 'score', 'tag'],
+                              usecols=['qid', 'pid', 'rank'],
+                              dtype={'qid': 'S', 'pid': 'S', 'rank': 'i', })
         else:
             raise Exception('unknown parameters')
         assert dev['qid'].dtype == object
         assert dev['pid'].dtype == object
         assert dev['rank'].dtype == np.int32
-        dev = dev[dev['rank']<=top]
+        dev = dev[dev['rank'] <= top]
     else:
         if prebuilt:
             bm25search = LuceneSearcher.from_prebuilt_index(args.index)
         else:
             bm25search = LuceneSearcher(args.index)
         bm25search.set_bm25(0.82, 0.68)
-        dev_dic = {"qid":[], "pid":[], "rank":[]}
+        dev_dic = {"qid": [], "pid": [], "rank": []}
         for topic in tqdm(queries.keys()):
             query_text = queries[topic]['raw']
             bm25_dev = bm25search.search(query_text, args.hits)
             doc_ids = [bm25_result.docid for bm25_result in bm25_dev]
             qid = [topic for _ in range(len(doc_ids))]
-            rank = [i for i in range(1, len(doc_ids)+1)]
+            rank = [i for i in range(1, len(doc_ids) + 1)]
             dev_dic['qid'].extend(qid)
             dev_dic['pid'].extend(doc_ids)
             dev_dic['rank'].extend(rank)
@@ -74,8 +69,8 @@ def dev_data_loader(file, format, topic, rerank, prebuilt, qrel, granularity, to
     else:
         seperation = " "
     dev_qrel = pd.read_csv(qrel, sep=seperation,
-                            names=["qid", "q0", "pid", "rel"], usecols=['qid', 'pid', 'rel'],
-                            dtype={'qid': 'S','pid': 'S', 'rel':'i'})
+                           names=["qid", "q0", "pid", "rel"], usecols=['qid', 'pid', 'rel'],
+                           dtype={'qid': 'S', 'pid': 'S', 'rel': 'i'})
     dev = dev.merge(dev_qrel, left_on=['qid', 'pid'], right_on=['qid', 'pid'], how='left')
     dev['rel'] = dev['rel'].fillna(0).astype(np.int32)
     dev = dev.sort_values(['qid', 'pid']).set_index(['qid', 'pid'])
@@ -138,11 +133,11 @@ def query_loader(topic):
                 print(analyzed)
         query_toks = query_lemmas.split()
         if len(query_toks) >= 0:
-            query = {"raw" : query,
-                "text": query_lemmas.split(' '),
-                "text_unlemm": query_unlemm.split(' '),
-                "analyzed": analyzed,
-                "text_bert_tok": bert_tokenizer.tokenize(query.lower())}
+            query = {"raw": query,
+                     "text": query_lemmas.split(' '),
+                     "text_unlemm": query_unlemm.split(' '),
+                     "analyzed": analyzed,
+                     "text_bert_tok": bert_tokenizer.tokenize(query.lower())}
             queries[did] = query
 
         if ln % 10000 == 0:
@@ -189,7 +184,7 @@ def eval_recall(dev_qrel, dev_data):
     score_tie_counter = 0
     score_tie_query = set()
 
-    recall_point = [10,20,50,100,200,250,300,333,400,500,1000]
+    recall_point = [10, 20, 50, 100, 200, 250, 300, 333, 400, 500, 1000]
     recall_curve = {k: [] for k in recall_point}
     for qid, group in tqdm(dev_data.groupby('qid')):
         group = group.reset_index()
@@ -230,7 +225,7 @@ def eval_recall(dev_qrel, dev_data):
 def output(file, dev_data, format, maxp):
     score_tie_counter = 0
     score_tie_query = set()
-    output_file = open(file,'w')
+    output_file = open(file, 'w')
     results = defaultdict(dict)
     idx = 0
     for qid, group in tqdm(dev_data.groupby('qid')):
@@ -250,14 +245,13 @@ def output(file, dev_data, format, maxp):
                     results[qid][docid] = t.score
             else:
                 results[qid][t.pid] = t.score
-            
 
     for qid in tqdm(results.keys()):
         rank = 1
         docid_score = results[qid]
-        docid_score = sorted(docid_score.items(),key=lambda kv: kv[1], reverse=True)
+        docid_score = sorted(docid_score.items(), key=lambda kv: kv[1], reverse=True)
         for docid, score in docid_score:
-            if format=='trec':
+            if format == 'trec':
                 output_file.write(f"{qid}\tQ0\t{docid}\t{rank}\t{score}\tltr\n")
             else:
                 output_file.write(f"{qid}\t{docid}\t{rank}\n")
@@ -265,11 +259,12 @@ def output(file, dev_data, format, maxp):
     score_tie = f'score_tie occurs {score_tie_counter} times in {len(score_tie_query)} queries'
     print(score_tie)
 
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Learning to rank reranking')
     parser.add_argument('--input', default='')
     parser.add_argument('--hits', type=int, default=1000)
-    parser.add_argument('--input-format', default = 'trec')
+    parser.add_argument('--input-format', default='trec')
     parser.add_argument('--model', required=True)
     parser.add_argument('--index', required=True)
     parser.add_argument('--output', required=True)
@@ -284,8 +279,9 @@ def output(file, dev_data, format, maxp):
     args = parser.parse_args()
     queries = query_loader(args.topic)
     print("---------------------loading dev----------------------------------------")
-    prebuilt = args.index == 'msmarco-passage-ltr' or args.index == 'msmarco-doc-per-passage-ltr'
-    dev, dev_qrel = dev_data_loader(args.input, args.input_format, args.topic, args.rerank, prebuilt, args.qrel, args.granularity, args.hits)
+    prebuilt = args.index == 'msmarco-v1-passage.ltr' or args.index == 'msmarco-v1-doc-segmented.ltr'
+    dev, dev_qrel = dev_data_loader(args.input, args.input_format, args.topic, args.rerank, prebuilt, args.qrel,
+                                    args.granularity, args.hits)
     searcher = MsmarcoLtrSearcher(args.model, args.ibm_model, args.index, args.granularity, prebuilt, args.topic)
     searcher.add_fe()
     batch_info = searcher.search(dev, queries)
@@ -293,5 +289,5 @@ def output(file, dev_data, format, maxp):
 
     eval_res = eval_mrr(batch_info)
     eval_recall(dev_qrel, batch_info)
-    output(args.output, batch_info,args.output_format, args.max_passage)
-    print('Done!')
\ No newline at end of file
+    output(args.output, batch_info, args.output_format, args.max_passage)
+    print('Done!')
diff --git a/pyserini/search/lucene/ltr/_search_msmarco.py b/pyserini/search/lucene/ltr/_search_msmarco.py
index 7b1bb9504..24f9ea9aa 100644
--- a/pyserini/search/lucene/ltr/_search_msmarco.py
+++ b/pyserini/search/lucene/ltr/_search_msmarco.py
@@ -43,9 +43,9 @@ def __init__(self, model: str, ibm_model:str, index:str, data: str, prebuilt: bo
             self.lucene_searcher = LuceneSearcher.from_prebuilt_index(index)
             index_directory = os.path.join(get_cache_home(), 'indexes')
             if data == 'passage':
-                index_path = os.path.join(index_directory, 'index-msmarco-passage-ltr-20210519-e25e33f.a5de642c268ac1ed5892c069bdc29ae3')
+                index_path = os.path.join(index_directory, 'lucene-inverted.msmarco-v1-passage.ltr.20210519.e25e33f.5da425ca44d2e3e5c38a7f564f13ad23')
             else:
-                index_path = os.path.join(index_directory, 'index-msmarco-doc-per-passage-ltr-20211031-33e4151.bd60e89041b4ebbabc4bf0cfac608a87')
+                index_path = os.path.join(index_directory, 'lucene-inverted.msmarco-v1-doc-segmented.ltr.20211031.33e4151.86f108d8441b6845f8caf1208dd7ac7a')
             self.index_reader = IndexReader.from_prebuilt_index(index)
         else:
             index_path = index
@@ -53,7 +53,6 @@ def __init__(self, model: str, ibm_model:str, index:str, data: str, prebuilt: bo
         self.fe = FeatureExtractor(index_path, max(multiprocessing.cpu_count()//2, 1))
         self.data = data
 
-    
     def add_fe(self):
         #self.fe.add(RunList('collections/msmarco-ltr-passage/run.monot5.run_list.whole.trec','t5'))
         #self.fe.add(RunList('../bert.whole.doc.trec','bert'))
diff --git a/tests/test_prebuilt_index.py b/tests/test_prebuilt_index.py
index 0a14f7c31..f1d0bbee9 100644
--- a/tests/test_prebuilt_index.py
+++ b/tests/test_prebuilt_index.py
@@ -43,8 +43,8 @@ def test_tf_mrtydi(self):
                 for url in TF_INDEX_INFO[key]['urls']:
                     urls.append(url)
 
-        # 11 languages
-        self.assertEqual(cnt, 11)
+        # 11 languages, but two entries for each language from aliases (e.g., arabic and ar)
+        self.assertEqual(cnt, 22)
         self._test_urls(urls)
 
     def test_tf_miracl(self):