tweak docs.

castorini · Nov 29, 2024 · 5a12c63 · 5a12c63
1 parent 494bbc6
commit 5a12c63
Show file tree

Hide file tree

Showing 8 changed files with 48 additions and 48 deletions.
diff --git a/...ressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.parquet.flat.cached.md b/...ressions/regressions-msmarco-v1-passage.bge-base-en-v1.5.parquet.flat.cached.md
@@ -33,15 +33,15 @@ Download the corpus and unpack into `collections/`:
 
 ```bash
 wget https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-bge-base-en-v1.5.parquet.tar -P collections/
-tar xvf collections/msmarco-passage-bge-base-en-v1.5.tar -C collections/
+tar xvf collections/msmarco-passage-bge-base-en-v1.5.parquet.tar -C collections/
 ```
 
-To confirm, `msmarco-passage-bge-base-en-v1.5.tar` is 39 GB and has MD5 checksum `b235e19ec492c18a18057b30b8b23fd4`.
+To confirm, `msmarco-passage-bge-base-en-v1.5.parquet.tar` is 39 GB and has MD5 checksum `b235e19ec492c18a18057b30b8b23fd4`.
 With the corpus downloaded, the following command will perform the remaining steps below:
 
 ```bash
 python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.bge-base-en-v1.5.parquet.flat.cached \
-  --corpus-path collections/msmarco-passage-bge-base-en-v1.5
+  --corpus-path collections/msmarco-passage-bge-base-en-v1.5.parquet
 ```
 
 ## Indexing
@@ -52,13 +52,13 @@ Sample indexing command, building flat indexes:
 bin/run.sh io.anserini.index.IndexFlatDenseVectors \
   -threads 16 \
   -collection ParquetDenseVectorCollection \
-  -input /path/to/msmarco-passage-bge-base-en-v1.5 \
+  -input /path/to/msmarco-passage-bge-base-en-v1.5.parquet \
   -generator ParquetDenseVectorDocumentGenerator \
   -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \
-  >& logs/log.msmarco-passage-bge-base-en-v1.5 &
+  >& logs/log.msmarco-passage-bge-base-en-v1.5.parquet &
 ```
 
-The path `/path/to/msmarco-passage-bge-base-en-v1.5/` should point to the corpus downloaded above.
+The path `/path/to/msmarco-passage-bge-base-en-v1.5.parquet/` should point to the corpus downloaded above.
 Upon completion, we should have an index with 8,841,823 documents.
 
 ## Retrieval
@@ -73,17 +73,17 @@ bin/run.sh io.anserini.search.SearchFlatDenseVectors \
   -index indexes/lucene-flat.msmarco-v1-passage.bge-base-en-v1.5/ \
   -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.gz \
   -topicReader JsonIntVector \
-  -output runs/run.msmarco-passage-bge-base-en-v1.5.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt \
+  -output runs/run.msmarco-passage-bge-base-en-v1.5.parquet.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt \
   -hits 1000 -threads 16 &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```bash
-bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
-bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
-bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
-bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
+bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.parquet.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
+bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.parquet.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
+bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.parquet.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
+bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-bge-base-en-v1.5.parquet.bge-flat-cached.topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.txt
 ```
 
 ## Effectiveness

diff --git a/...regressions-msmarco-v1-passage.cohere-embed-english-v3.0.parquet.flat.cached.md b/...regressions-msmarco-v1-passage.cohere-embed-english-v3.0.parquet.flat.cached.md
@@ -31,15 +31,15 @@ Download the corpus and unpack into `collections/`:
 
 ```bash
 wget https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-cohere-embed-english-v3.0.parquet.tar -P collections/
-tar xvf collections/msmarco-passage-cohere-embed-english-v3.0.tar -C collections/
+tar xvf collections/msmarco-passage-cohere-embed-english-v3.0.parquet.tar -C collections/
 ```
 
-To confirm, `msmarco-passage-cohere-embed-english-v3.0.tar` is 16 GB and has MD5 checksum `40c5caf33476746e93ceeb75174b8d64`.
+To confirm, `msmarco-passage-cohere-embed-english-v3.0.parquet.tar` is 16 GB and has MD5 checksum `40c5caf33476746e93ceeb75174b8d64`.
 With the corpus downloaded, the following command will perform the remaining steps below:
 
 ```bash
 python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.cohere-embed-english-v3.0.parquet.flat.cached \
-  --corpus-path collections/msmarco-passage-cohere-embed-english-v3.0
+  --corpus-path collections/msmarco-passage-cohere-embed-english-v3.0.parquet
 ```
 
 ## Indexing
@@ -50,13 +50,13 @@ Sample indexing command, building flat indexes:
 bin/run.sh io.anserini.index.IndexFlatDenseVectors \
   -threads 16 \
   -collection ParquetDenseVectorCollection \
-  -input /path/to/msmarco-passage-cohere-embed-english-v3.0 \
+  -input /path/to/msmarco-passage-cohere-embed-english-v3.0.parquet \
   -generator ParquetDenseVectorDocumentGenerator \
   -index indexes/lucene-flat.msmarco-v1-passage.cohere-embed-english-v3.0/ \
-  >& logs/log.msmarco-passage-cohere-embed-english-v3.0 &
+  >& logs/log.msmarco-passage-cohere-embed-english-v3.0.parquet &
 ```
 
-The path `/path/to/msmarco-passage-cohere-embed-english-v3.0/` should point to the corpus downloaded above.
+The path `/path/to/msmarco-passage-cohere-embed-english-v3.0.parquet/` should point to the corpus downloaded above.
 Upon completion, we should have an index with 8,841,823 documents.
 
 ## Retrieval
@@ -71,17 +71,17 @@ bin/run.sh io.anserini.search.SearchFlatDenseVectors \
   -index indexes/lucene-flat.msmarco-v1-passage.cohere-embed-english-v3.0/ \
   -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.gz \
   -topicReader JsonIntVector \
-  -output runs/run.msmarco-passage-cohere-embed-english-v3.0.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt \
+  -output runs/run.msmarco-passage-cohere-embed-english-v3.0.parquet.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt \
   -hits 1000 -threads 16 &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```bash
-bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
-bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
-bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
-bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
+bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.parquet.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
+bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.parquet.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
+bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.parquet.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
+bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cohere-embed-english-v3.0.parquet.cohere-embed-english-v3.0-flat-cached.topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.txt
 ```
 
 ## Effectiveness

diff --git a/...egressions/regressions-msmarco-v1-passage.cos-dpr-distil.parquet.flat.cached.md b/...egressions/regressions-msmarco-v1-passage.cos-dpr-distil.parquet.flat.cached.md
@@ -33,15 +33,15 @@ Download the corpus and unpack into `collections/`:
 
 ```bash
 wget https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-cos-dpr-distil.parquet.tar -P collections/
-tar xvf collections/msmarco-passage-cos-dpr-distil.tar -C collections/
+tar xvf collections/msmarco-passage-cos-dpr-distil.parquet.tar -C collections/
 ```
 
-To confirm, `msmarco-passage-cos-dpr-distil.tar` is 38 GB and has MD5 checksum `c8a204fbc3ccda581aa375936af43a97`.
+To confirm, `msmarco-passage-cos-dpr-distil.parquet.tar` is 38 GB and has MD5 checksum `c8a204fbc3ccda581aa375936af43a97`.
 With the corpus downloaded, the following command will perform the remaining steps below:
 
 ```bash
 python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.cos-dpr-distil.parquet.flat.cached \
-  --corpus-path collections/msmarco-passage-cos-dpr-distil
+  --corpus-path collections/msmarco-passage-cos-dpr-distil.parquet
 ```
 
 ## Indexing
@@ -52,13 +52,13 @@ Sample indexing command, building flat indexes:
 bin/run.sh io.anserini.index.IndexFlatDenseVectors \
   -threads 16 \
   -collection ParquetDenseVectorCollection \
-  -input /path/to/msmarco-passage-cos-dpr-distil \
+  -input /path/to/msmarco-passage-cos-dpr-distil.parquet \
   -generator ParquetDenseVectorDocumentGenerator \
   -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \
-  >& logs/log.msmarco-passage-cos-dpr-distil &
+  >& logs/log.msmarco-passage-cos-dpr-distil.parquet &
 ```
 
-The path `/path/to/msmarco-passage-cos-dpr-distil/` should point to the corpus downloaded above.
+The path `/path/to/msmarco-passage-cos-dpr-distil.parquet/` should point to the corpus downloaded above.
 Upon completion, we should have an index with 8,841,823 documents.
 
 ## Retrieval
@@ -73,17 +73,17 @@ bin/run.sh io.anserini.search.SearchFlatDenseVectors \
   -index indexes/lucene-flat.msmarco-v1-passage.cos-dpr-distil/ \
   -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.gz \
   -topicReader JsonIntVector \
-  -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt \
+  -output runs/run.msmarco-passage-cos-dpr-distil.parquet.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt \
   -hits 1000 -threads 16 &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```bash
-bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
-bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
-bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
-bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
+bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.parquet.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
+bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.parquet.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
+bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.parquet.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
+bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-cos-dpr-distil.parquet.cos-dpr-distil-flat-cached.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt
 ```
 
 ## Effectiveness

diff --git a/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.parquet.flat.cached.md b/docs/regressions/regressions-msmarco-v1-passage.openai-ada2.parquet.flat.cached.md
@@ -33,15 +33,15 @@ Download the corpus and unpack into `collections/`:
 
 ```bash
 wget https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-openai-ada2.parquet.tar -P collections/
-tar xvf collections/msmarco-passage-openai-ada2.tar -C collections/
+tar xvf collections/msmarco-passage-openai-ada2.parquet.tar -C collections/
 ```
 
-To confirm, `msmarco-passage-openai-ada2.tar` is 75 GB and has MD5 checksum `fa3637e9c4150b157270e19ef3a4f779`.
+To confirm, `msmarco-passage-openai-ada2.parquet.tar` is 75 GB and has MD5 checksum `fa3637e9c4150b157270e19ef3a4f779`.
 With the corpus downloaded, the following command will perform the remaining steps below:
 
 ```bash
 python src/main/python/run_regression.py --index --verify --search --regression msmarco-v1-passage.openai-ada2.parquet.flat.cached \
-  --corpus-path collections/msmarco-passage-openai-ada2
+  --corpus-path collections/msmarco-passage-openai-ada2.parquet
 ```
 
 ## Indexing
@@ -52,13 +52,13 @@ Sample indexing command, building flat indexes:
 bin/run.sh io.anserini.index.IndexFlatDenseVectors \
   -threads 16 \
   -collection ParquetDenseVectorCollection \
-  -input /path/to/msmarco-passage-openai-ada2 \
+  -input /path/to/msmarco-passage-openai-ada2.parquet \
   -generator ParquetDenseVectorDocumentGenerator \
   -index indexes/lucene-flat.msmarco-v1-passage.openai-ada2/ \
-  >& logs/log.msmarco-passage-openai-ada2 &
+  >& logs/log.msmarco-passage-openai-ada2.parquet &
 ```
 
-The path `/path/to/msmarco-passage-openai-ada2/` should point to the corpus downloaded above.
+The path `/path/to/msmarco-passage-openai-ada2.parquet/` should point to the corpus downloaded above.
 Upon completion, we should have an index with 8,841,823 documents.
 
 ## Retrieval
@@ -73,17 +73,17 @@ bin/run.sh io.anserini.search.SearchFlatDenseVectors \
   -index indexes/lucene-flat.msmarco-v1-passage.openai-ada2/ \
   -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.openai-ada2.jsonl.gz \
   -topicReader JsonIntVector \
-  -output runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt \
+  -output runs/run.msmarco-passage-openai-ada2.parquet.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt \
   -hits 1000 -threads 16 &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```bash
-bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
-bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
-bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
-bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
+bin/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.parquet.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
+bin/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.parquet.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
+bin/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.parquet.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
+bin/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage-openai-ada2.parquet.openai-ada2-flat-cached.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt
 ```
 
 ## Effectiveness

diff --git a/src/main/resources/regression/msmarco-v1-passage.bge-base-en-v1.5.parquet.flat.cached.yaml b/src/main/resources/regression/msmarco-v1-passage.bge-base-en-v1.5.parquet.flat.cached.yaml
@@ -1,5 +1,5 @@
 ---
-corpus: msmarco-passage-bge-base-en-v1.5
+corpus: msmarco-passage-bge-base-en-v1.5.parquet
 corpus_path: collections/msmarco/msmarco-passage-bge-base-en-v1.5.parquet/
 
 download_url: https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-bge-base-en-v1.5.parquet.tar

diff --git a/...esources/regression/msmarco-v1-passage.cohere-embed-english-v3.0.parquet.flat.cached.yaml b/...esources/regression/msmarco-v1-passage.cohere-embed-english-v3.0.parquet.flat.cached.yaml
@@ -1,5 +1,5 @@
 ---
-corpus: msmarco-passage-cohere-embed-english-v3.0
+corpus: msmarco-passage-cohere-embed-english-v3.0.parquet
 corpus_path: collections/msmarco/msmarco-passage-cohere-embed-english-v3.0.parquet/
 
 download_url: https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-cohere-embed-english-v3.0.parquet.tar

diff --git a/src/main/resources/regression/msmarco-v1-passage.cos-dpr-distil.parquet.flat.cached.yaml b/src/main/resources/regression/msmarco-v1-passage.cos-dpr-distil.parquet.flat.cached.yaml
@@ -1,5 +1,5 @@
 ---
-corpus: msmarco-passage-cos-dpr-distil
+corpus: msmarco-passage-cos-dpr-distil.parquet
 corpus_path: collections/msmarco/msmarco-passage-cos-dpr-distil.parquet/
 
 download_url: https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-cos-dpr-distil.parquet.tar

diff --git a/src/main/resources/regression/msmarco-v1-passage.openai-ada2.parquet.flat.cached.yaml b/src/main/resources/regression/msmarco-v1-passage.openai-ada2.parquet.flat.cached.yaml
@@ -1,5 +1,5 @@
 ---
-corpus: msmarco-passage-openai-ada2
+corpus: msmarco-passage-openai-ada2.parquet
 corpus_path: collections/msmarco/msmarco-passage-openai-ada2.parquet/
 
 download_url: https://rgw.cs.uwaterloo.ca/pyserini/data/msmarco-passage-openai-ada2.parquet.tar