{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/text-retrieval","name":"Text Retrieval","slug":"text-retrieval","description_markdown":"Text Retrieval is the task of finding the most text result (such as an answer, paragraph, or passage) given a query (which could be a question, keywords, or any relevant text)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":671,"papers_with_code":335,"benchmarks":16,"benchmark_tables_in_archive":16,"benchmark_tables_shown":16,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":37,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/text-retrieval-on-mteb","slug":"text-retrieval-on-mteb","dataset":"MTEB","dataset_url":"/dataset/mteb","rows_in_archive":30,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"SGPT-5.8B-msmarco","paper_title":"MTEB: Massive Text Embedding Benchmark","paper_url":"/paper/mteb-massive-text-embedding-benchmark","paper_date":"2022-10-13","arxiv_id":"2210.07316","code_links":[{"title":"embeddings-benchmark/mteb","url":"https://github.com/embeddings-benchmark/mteb"},{"title":"lyon-nlp/mteb-french","url":"https://github.com/lyon-nlp/mteb-french"},{"title":"climsocana/tecb-de","url":"https://github.com/climsocana/tecb-de"},{"title":"wadoodabdul/clinical_ner_benchmark","url":"https://github.com/wadoodabdul/clinical_ner_benchmark"},{"title":"basf/chemteb","url":"https://github.com/basf/chemteb"}],"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mteb-massive-text-embedding-benchmark#ran","syntology_url":"https://syntology.ai/paper/2210.07316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07316"}},"official":{"repos":["embeddings-benchmark/mteb"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/text-retrieval-on-20-newsgroups","slug":"text-retrieval-on-20-newsgroups","dataset":"20 Newsgroups","dataset_url":"/dataset/20-newsgroups","rows_in_archive":3,"metrics":["Precision@100"],"first_row_in_archive_order":{"model":"B-VAE","paper_title":"A Binary Variational Autoencoder for Hashing","paper_url":"/paper/a-binary-variational-autoencoder-for-hashing","paper_date":"2019-10-22","arxiv_id":null,"code_links":[{"title":"fmenat/DiscreteVAE","url":"https://github.com/fmenat/DiscreteVAE"}],"syntology":null}},{"leaderboard":"/sota/text-retrieval-on-image-chat","slug":"text-retrieval-on-image-chat","dataset":"Image-Chat","dataset_url":"/dataset/image-chat","rows_in_archive":3,"metrics":["R@1","R@5","Sum(R@1,5)"],"first_row_in_archive_order":{"model":"PaCE","paper_title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","paper_url":"/paper/pace-unified-multi-modal-dialogue-pre","paper_date":"2023-05-24","arxiv_id":"2305.14839","code_links":[{"title":"AlibabaResearch/DAMO-ConvAI","url":"https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace"}],"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/text-retrieval-on-reuters-21578","slug":"text-retrieval-on-reuters-21578","dataset":"Reuters-21578","dataset_url":"/dataset/reuters-21578","rows_in_archive":3,"metrics":["Precision@100"],"first_row_in_archive_order":{"model":"VDSH","paper_title":"Variational Deep Semantic Hashing for Text Documents","paper_url":"/paper/variational-deep-semantic-hashing-for-text","paper_date":"2017-08-11","arxiv_id":"1708.03436","code_links":[{"title":"unsuthee/VariationalDeepSemanticHashing","url":"https://github.com/unsuthee/VariationalDeepSemanticHashing"},{"title":"J-zin/SNUH","url":"https://github.com/J-zin/SNUH"},{"title":"MindSpore-scientific/code-9","url":"https://github.com/MindSpore-scientific/code-9/tree/main/SNUH"}],"syntology":null}},{"leaderboard":"/sota/text-retrieval-on-climate-fever","slug":"text-retrieval-on-climate-fever","dataset":"CLIMATE-FEVER","dataset_url":"/dataset/climate-fever","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-dbpedia","slug":"text-retrieval-on-dbpedia","dataset":"DBpedia","dataset_url":"/dataset/dbpedia","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-fever","slug":"text-retrieval-on-fever","dataset":"FEVER","dataset_url":"/dataset/fever","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-hotpotqa","slug":"text-retrieval-on-hotpotqa","dataset":"HotpotQA","dataset_url":"/dataset/hotpotqa","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-ms-marco","slug":"text-retrieval-on-ms-marco","dataset":"MS MARCO","dataset_url":"/dataset/ms-marco","rows_in_archive":1,"metrics":["NDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-natural-questions","slug":"text-retrieval-on-natural-questions","dataset":"Natural Questions","dataset_url":"/dataset/natural-questions","rows_in_archive":1,"metrics":["NDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-nfcorpus","slug":"text-retrieval-on-nfcorpus","dataset":"NFCorpus","dataset_url":"/dataset/nfcorpus","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-quora-question-pairs","slug":"text-retrieval-on-quora-question-pairs","dataset":"Quora Question Pairs","dataset_url":"/dataset/quora-question-pairs","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-rsicd","slug":"text-retrieval-on-rsicd","dataset":"RSICD","dataset_url":"/dataset/rsicd","rows_in_archive":1,"metrics":["Recall@1"],"first_row_in_archive_order":{"model":"GeoRSCLIP-FT","paper_title":"RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing","paper_url":"/paper/rs5m-a-large-scale-vision-language-dataset","paper_date":"2023-06-20","arxiv_id":"2306.11300","code_links":[{"title":"om-ai-lab/rs5m","url":"https://github.com/om-ai-lab/rs5m"}],"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rs5m-a-large-scale-vision-language-dataset#ran","syntology_url":"https://syntology.ai/paper/2306.11300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11300"}},"official":{"repos":["om-ai-lab/rs5m"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/text-retrieval-on-scidocs","slug":"text-retrieval-on-scidocs","dataset":"SciDocs","dataset_url":"/dataset/scidocs","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-scifact","slug":"text-retrieval-on-scifact","dataset":"SciFact","dataset_url":"/dataset/scifact","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/text-retrieval-on-trec-covid","slug":"text-retrieval-on-trec-covid","dataset":"TREC-COVID","dataset_url":"/dataset/trec-covid","rows_in_archive":1,"metrics":["nDCG@10"],"first_row_in_archive_order":{"model":"Lucene (BM25S)","paper_title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","paper_url":"/paper/bm25s-orders-of-magnitude-faster-lexical","paper_date":"2024-07-04","arxiv_id":"2407.03618","code_links":[{"title":"xhluca/bm25s","url":"https://github.com/xhluca/bm25s"},{"title":"xhluca/bm25-benchmarks","url":"https://github.com/xhluca/bm25-benchmarks"},{"title":"conda-forge/bm25s-feedstock","url":"https://github.com/conda-forge/bm25s-feedstock"}],"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}}],"datasets":[{"url":"/dataset/natural-questions","name":"Natural Questions","full_name":"","num_papers_in_archive":1404},{"url":"/dataset/ms-marco","name":"MS MARCO","full_name":"Microsoft Machine Reading Comprehension Dataset","num_papers_in_archive":1036},{"url":"/dataset/hotpotqa","name":"HotpotQA","full_name":"","num_papers_in_archive":933},{"url":"/dataset/dbpedia","name":"DBpedia","full_name":"DBpedia","num_papers_in_archive":597},{"url":"/dataset/fever","name":"FEVER","full_name":"Fact Extraction and VERification","num_papers_in_archive":498},{"url":"/dataset/mteb","name":"MTEB","full_name":"Massive Text Embedding Benchmark","num_papers_in_archive":155},{"url":"/dataset/scifact","name":"SciFact","full_name":"","num_papers_in_archive":116},{"url":"/dataset/trec-covid","name":"TREC-COVID","full_name":"","num_papers_in_archive":73},{"url":"/dataset/rsicd","name":"RSICD","full_name":"Remote Sensing Image Captioning Dataset","num_papers_in_archive":70},{"url":"/dataset/reuters-21578","name":"Reuters-21578","full_name":"","num_papers_in_archive":66},{"url":"/dataset/scidocs","name":"SciDocs","full_name":"SciDocs","num_papers_in_archive":57},{"url":"/dataset/quora-question-pairs","name":"Quora Question Pairs","full_name":"","num_papers_in_archive":55},{"url":"/dataset/climate-fever","name":"CLIMATE-FEVER","full_name":"","num_papers_in_archive":38},{"url":"/dataset/image-chat","name":"Image-Chat","full_name":"","num_papers_in_archive":31},{"url":"/dataset/20-newsgroups","name":"20 Newsgroups","full_name":"","num_papers_in_archive":27},{"url":"/dataset/rsvgd","name":"DIOR-RSVG","full_name":"","num_papers_in_archive":25},{"url":"/dataset/tripclick","name":"TripClick","full_name":"","num_papers_in_archive":16},{"url":"/dataset/condensed-movies","name":"Condensed Movies","full_name":"","num_papers_in_archive":15},{"url":"/dataset/vidore","name":"Vidore","full_name":"Visual Document Retrieval Benchmark","num_papers_in_archive":13},{"url":"/dataset/peerqa","name":"PeerQA","full_name":"","num_papers_in_archive":12},{"url":"/dataset/covid-19-twitter-chatter-dataset","name":"COVID-19 Twitter Chatter Dataset","full_name":"","num_papers_in_archive":10},{"url":"/dataset/bsard","name":"BSARD","full_name":"Belgian Statutory Article Retrieval Dataset","num_papers_in_archive":6},{"url":"/dataset/nfcorpus","name":"NFCorpus","full_name":"","num_papers_in_archive":5},{"url":"/dataset/lleqa","name":"LLeQA","full_name":"Long-form Legal Question Answering","num_papers_in_archive":3},{"url":"/dataset/latamxix","name":"LatamXIX","full_name":"19th Century Latin American Spanish Newspaper Corpus with LLM OCR Correction","num_papers_in_archive":2},{"url":"/dataset/maps-kb","name":"MAPS-KB","full_name":"","num_papers_in_archive":2},{"url":"/dataset/acr-appropriateness-criteria-corpus","name":"ACR Appropriateness Criteria Corpus","full_name":"","num_papers_in_archive":1},{"url":"/dataset/claim-matching-robustness","name":"Claim Matching Robustness","full_name":"","num_papers_in_archive":1},{"url":"/dataset/compmix-ir","name":"CompMix-IR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cure","name":"CURE","full_name":"A dataset for Clinical Understanding & Retrieval Evaluation","num_papers_in_archive":1},{"url":"/dataset/dapfam","name":"DAPFAM","full_name":"A Domain‑Aware Patent Retrieval Dataset Aggregated at the Family Level","num_papers_in_archive":1},{"url":"/dataset/dialogcc","name":"DialogCC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/multi-eup","name":"Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval","full_name":"","num_papers_in_archive":1},{"url":"/dataset/polynewsparallel","name":"PolyNewsParallel","full_name":"","num_papers_in_archive":1},{"url":"/dataset/procis","name":"ProCIS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/spanish-corpus-xix","name":"Spanish Corpus XIX","full_name":"19th Century Spanish Corpus","num_papers_in_archive":1},{"url":"/dataset/french-legal-cases","name":"french-legal-cases","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/retrieval","name":"Retrieval"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":7,"rows_per_page":100,"shown":100,"of":671,"of_with_code":335,"tagged_in_all":671,"counts":{"archive_papers_tagged":671,"with_a_code_link":335,"where_syntology_ran_a_sample":117,"not_listed_spam_title":0,"listed":671,"listed_where_code_ran":117,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":97,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":97,"listed_every_run_a_failure_of_syntologys_instrument":20,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/blip-bootstrapping-language-image-pre","slug":"blip-bootstrapping-language-image-pre","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","date":"2022-01-28","arxiv_id":"2201.12086","repositories_listed":9,"syntology":null},{"url":"/paper/knowledge-guided-text-retrieval-and-reading","slug":"knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","date":"2019-11-10","arxiv_id":"1911.03868","repositories_listed":7,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/knowledge-guided-text-retrieval-and-reading#ran","syntology_url":"https://syntology.ai/paper/1911.03868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03868"}},"official":null}},{"url":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}},"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/languagebind-extending-video-language","slug":"languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","repositories_listed":6,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/languagebind-extending-video-language#ran","syntology_url":"https://syntology.ai/paper/2310.01852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01852"}},"official":{"repos":["pku-yuangroup/languagebind"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/flexivit-one-model-for-all-patch-sizes","slug":"flexivit-one-model-for-all-patch-sizes","title":"FlexiViT: One Model for All Patch Sizes","date":"2022-12-15","arxiv_id":"2212.08013","repositories_listed":6,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flexivit-one-model-for-all-patch-sizes#ran","syntology_url":"https://syntology.ai/paper/2212.08013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08013"}},"official":{"repos":["google-research/big_vision"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/align-before-fuse-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.07651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07651"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/language-agnostic-bert-sentence-embedding","slug":"language-agnostic-bert-sentence-embedding","title":"Language-agnostic BERT Sentence Embedding","date":"2020-07-03","arxiv_id":"2007.01852","repositories_listed":6,"syntology":null},{"url":"/paper/stacked-cross-attention-for-image-text","slug":"stacked-cross-attention-for-image-text","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","arxiv_id":"1803.08024","repositories_listed":6,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stacked-cross-attention-for-image-text#ran","syntology_url":"https://syntology.ai/paper/1803.08024","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08024"}},"official":{"repos":["kuanghuei/SCAN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/mteb-massive-text-embedding-benchmark","slug":"mteb-massive-text-embedding-benchmark","title":"MTEB: Massive Text Embedding Benchmark","date":"2022-10-13","arxiv_id":"2210.07316","repositories_listed":5,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mteb-massive-text-embedding-benchmark#ran","syntology_url":"https://syntology.ai/paper/2210.07316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07316"}},"official":{"repos":["embeddings-benchmark/mteb"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/clip4clip-an-empirical-study-of-clip-for-end","slug":"clip4clip-an-empirical-study-of-clip-for-end","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","date":"2021-04-18","arxiv_id":"2104.08860","repositories_listed":5,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clip4clip-an-empirical-study-of-clip-for-end#ran","syntology_url":"https://syntology.ai/paper/2104.08860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08860"}},"official":{"repos":["ArrowLuo/CLIP4Clip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/frozen-in-time-a-joint-video-and-image","slug":"frozen-in-time-a-joint-video-and-image","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","date":"2021-04-01","arxiv_id":"2104.00650","repositories_listed":5,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/frozen-in-time-a-joint-video-and-image#ran","syntology_url":"https://syntology.ai/paper/2104.00650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00650"}},"official":{"repos":["m-bain/frozen-in-time"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","repositories_listed":5,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}},"official":null}},{"url":"/paper/approximate-nearest-neighbor-negative","slug":"approximate-nearest-neighbor-negative","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","date":"2020-07-01","arxiv_id":"2007.00808","repositories_listed":5,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/approximate-nearest-neighbor-negative#ran","syntology_url":"https://syntology.ai/paper/2007.00808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.00808"}},"official":{"repos":["microsoft/ANCE"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-a-text-video-embedding-from","slug":"learning-a-text-video-embedding-from","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","date":"2018-04-07","arxiv_id":"1804.02516","repositories_listed":5,"syntology":null},{"url":"/paper/efficiently-teaching-an-effective-dense","slug":"efficiently-teaching-an-effective-dense","title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling","date":"2021-04-14","arxiv_id":"2104.06967","repositories_listed":4,"syntology":null},{"url":"/paper/fine-grained-video-text-retrieval-with","slug":"fine-grained-video-text-retrieval-with","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","date":"2020-03-01","arxiv_id":"2003.00392","repositories_listed":4,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-grained-video-text-retrieval-with#ran","syntology_url":"https://syntology.ai/paper/2003.00392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00392"}},"official":null}},{"url":"/paper/bm25s-orders-of-magnitude-faster-lexical","slug":"bm25s-orders-of-magnitude-faster-lexical","title":"BM25S: Orders of magnitude faster lexical search via eager sparse scoring","date":"2024-07-04","arxiv_id":"2407.03618","repositories_listed":3,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/bm25s-orders-of-magnitude-faster-lexical#ran","syntology_url":"https://syntology.ai/paper/2407.03618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03618"}},"official":{"repos":["xhluca/bm25s"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/retsim-resilient-and-efficient-text","slug":"retsim-resilient-and-efficient-text","title":"RETSim: Resilient and Efficient Text Similarity","date":"2023-11-28","arxiv_id":"2311.17264","repositories_listed":3,"syntology":null},{"url":"/paper/x-clip-end-to-end-multi-grained-contrastive","slug":"x-clip-end-to-end-multi-grained-contrastive","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","date":"2022-07-15","arxiv_id":"2207.07285","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/x-clip-end-to-end-multi-grained-contrastive#ran","syntology_url":"https://syntology.ai/paper/2207.07285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07285"}},"official":{"repos":["xuguohai/X-CLIP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","repositories_listed":3,"syntology":null},{"url":"/paper/beir-a-heterogenous-benchmark-for-zero-shot","slug":"beir-a-heterogenous-benchmark-for-zero-shot","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","date":"2021-04-17","arxiv_id":"2104.08663","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/beir-a-heterogenous-benchmark-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2104.08663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08663"}},"official":{"repos":["UKPLab/beir"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/seeing-out-of-the-box-end-to-end-pre-training","slug":"seeing-out-of-the-box-end-to-end-pre-training","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","date":"2021-04-07","arxiv_id":"2104.03135","repositories_listed":3,"syntology":null},{"url":"/paper/wit-wikipedia-based-image-text-dataset-for","slug":"wit-wikipedia-based-image-text-dataset-for","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","date":"2021-03-02","arxiv_id":"2103.01913","repositories_listed":3,"syntology":null},{"url":"/paper/engaging-image-chat-modeling-personality-in","slug":"engaging-image-chat-modeling-personality-in","title":"Image Chat: Engaging Grounded Conversations","date":"2018-11-02","arxiv_id":"1811.00945","repositories_listed":3,"syntology":null},{"url":"/paper/single-shot-scene-text-retrieval","slug":"single-shot-scene-text-retrieval","title":"Single Shot Scene Text Retrieval","date":"2018-08-27","arxiv_id":"1808.09044","repositories_listed":3,"syntology":null},{"url":"/paper/variational-deep-semantic-hashing-for-text","slug":"variational-deep-semantic-hashing-for-text","title":"Variational Deep Semantic Hashing for Text Documents","date":"2017-08-11","arxiv_id":"1708.03436","repositories_listed":3,"syntology":null},{"url":"/paper/m2d2-exploring-general-purpose-audio-language","slug":"m2d2-exploring-general-purpose-audio-language","title":"M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP","date":"2025-03-28","arxiv_id":"2503.22104","repositories_listed":2,"syntology":null},{"url":"/paper/biomedica-an-open-biomedical-image-caption","slug":"biomedica-an-open-biomedical-image-caption","title":"BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature","date":"2025-01-13","arxiv_id":"2501.07171","repositories_listed":2,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/biomedica-an-open-biomedical-image-caption#ran","syntology_url":"https://syntology.ai/paper/2501.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07171"}},"official":{"repos":["ale9806/open_clip_with_biomedica","minwoosun/biomedica-etl"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/gramian-multimodal-representation-learning","slug":"gramian-multimodal-representation-learning","title":"Gramian Multimodal Representation Learning and Alignment","date":"2024-12-16","arxiv_id":"2412.11959","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/gramian-multimodal-representation-learning#ran","syntology_url":"https://syntology.ai/paper/2412.11959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11959"}},"official":{"repos":["ispamm/GRAM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/rwkv-clip-a-robust-vision-language","slug":"rwkv-clip-a-robust-vision-language","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","date":"2024-06-11","arxiv_id":"2406.06973","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/rwkv-clip-a-robust-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.06973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06973"}},"official":{"repos":["deepglint/rwkv-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/m3d-advancing-3d-medical-image-analysis-with","slug":"m3d-advancing-3d-medical-image-analysis-with","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","date":"2024-03-31","arxiv_id":"2404.00578","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3d-advancing-3d-medical-image-analysis-with#ran","syntology_url":"https://syntology.ai/paper/2404.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00578"}},"official":{"repos":["baai-dcai/m3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/data-efficient-multimodal-fusion-on-a-single","slug":"data-efficient-multimodal-fusion-on-a-single","title":"Data-Efficient Multimodal Fusion on a Single GPU","date":"2023-12-15","arxiv_id":"2312.10144","repositories_listed":2,"syntology":null},{"url":"/paper/rgnet-a-unified-retrieval-and-grounding","slug":"rgnet-a-unified-retrieval-and-grounding","title":"RGNet: A Unified Clip Retrieval and Grounding Network for Long Videos","date":"2023-12-11","arxiv_id":"2312.06729","repositories_listed":2,"syntology":null},{"url":"/paper/frozen-transformers-in-language-models-are","slug":"frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","arxiv_id":"2310.12973","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":4,"n_honours":3,"n_violates":1,"n_no_contract":3,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/frozen-transformers-in-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.12973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12973"}},"official":{"repos":["ziqipang/lm4visualencoding"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-llama-for-multi-stage-text","slug":"fine-tuning-llama-for-multi-stage-text","title":"Fine-Tuning LLaMA for Multi-Stage Text Retrieval","date":"2023-10-12","arxiv_id":"2310.08319","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fine-tuning-llama-for-multi-stage-text#ran","syntology_url":"https://syntology.ai/paper/2310.08319","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08319"}},"official":null}},{"url":"/paper/esa-external-space-attention-aggregation-for","slug":"esa-external-space-attention-aggregation-for","title":"ESA: External Space Attention Aggregation for Image-Text Retrieval","date":"2023-10-10","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/multimodal-dataset-distillation-for-image","slug":"multimodal-dataset-distillation-for-image","title":"Vision-Language Dataset Distillation","date":"2023-08-15","arxiv_id":"2308.07545","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multimodal-dataset-distillation-for-image#ran","syntology_url":"https://syntology.ai/paper/2308.07545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07545"}},"official":{"repos":["princetonvisualai/multimodal_dataset_distillation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-rank-in-generative-retrieval","slug":"learning-to-rank-in-generative-retrieval","title":"Learning to Rank in Generative Retrieval","date":"2023-06-27","arxiv_id":"2306.15222","repositories_listed":2,"syntology":null},{"url":"/paper/contrasting-intra-modal-and-ranking-cross","slug":"contrasting-intra-modal-and-ranking-cross","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","date":"2023-06-15","arxiv_id":"2306.08832","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrasting-intra-modal-and-ranking-cross#ran","syntology_url":"https://syntology.ai/paper/2306.08832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08832"}},"official":{"repos":["lezhang7/Enhance-FineGrained","magiccircuit/enhance-finegrained"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/h2ogpt-democratizing-large-language-models","slug":"h2ogpt-democratizing-large-language-models","title":"h2oGPT: Democratizing Large Language Models","date":"2023-06-13","arxiv_id":"2306.08161","repositories_listed":2,"syntology":null},{"url":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/region-aware-pretraining-for-open-vocabulary","slug":"region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","arxiv_id":"2305.07011","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/region-aware-pretraining-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2305.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07011"}},"official":{"repos":["mcahny/rovit","google-research/google-research"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperbolic-image-text-representations","slug":"hyperbolic-image-text-representations","title":"Hyperbolic Image-Text Representations","date":"2023-04-18","arxiv_id":"2304.09172","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hyperbolic-image-text-representations#ran","syntology_url":"https://syntology.ai/paper/2304.09172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09172"}},"official":{"repos":["facebookresearch/meru"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["found_in_text","listed"]}}},{"url":"/paper/atomic-an-image-text-retrieval-test","slug":"atomic-an-image-text-retrieval-test","title":"AToMiC: An Image/Text Retrieval Test Collection to Support Multimedia Content Creation","date":"2023-04-04","arxiv_id":"2304.01961","repositories_listed":2,"syntology":null},{"url":"/paper/pmc-clip-contrastive-language-image-pre","slug":"pmc-clip-contrastive-language-image-pre","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","date":"2023-03-13","arxiv_id":"2303.07240","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pmc-clip-contrastive-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2303.07240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07240"}},"official":{"repos":["WeixiongLin/PMC-CLIP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/uniadapter-unified-parameter-efficient","slug":"uniadapter-unified-parameter-efficient","title":"UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling","date":"2023-02-13","arxiv_id":"2302.06605","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uniadapter-unified-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2302.06605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06605"}},"official":{"repos":["rerv/uniadapter","uniadapter/uniadapter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/upop-unified-and-progressive-pruning-for","slug":"upop-unified-and-progressive-pruning-for","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","date":"2023-01-31","arxiv_id":"2301.13741","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/upop-unified-and-progressive-pruning-for#ran","syntology_url":"https://syntology.ai/paper/2301.13741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.13741"}},"official":{"repos":["sdc17/upop"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/hada-a-graph-based-amalgamation-framework-in","slug":"hada-a-graph-based-amalgamation-framework-in","title":"HADA: A Graph-based Amalgamation Framework in Image-text Retrieval","date":"2023-01-11","arxiv_id":"2301.04742","repositories_listed":2,"syntology":null},{"url":"/paper/pre-trained-language-models-can-be-fully-zero","slug":"pre-trained-language-models-can-be-fully-zero","title":"Pre-trained Language Models Can be Fully Zero-Shot Learners","date":"2022-12-14","arxiv_id":"2212.06950","repositories_listed":2,"syntology":null},{"url":"/paper/dense-text-retrieval-based-on-pretrained","slug":"dense-text-retrieval-based-on-pretrained","title":"Dense Text Retrieval based on Pretrained Language Models: A Survey","date":"2022-11-27","arxiv_id":"2211.14876","repositories_listed":2,"syntology":null},{"url":"/paper/dissecting-deep-metric-learning-losses-for","slug":"dissecting-deep-metric-learning-losses-for","title":"Dissecting Deep Metric Learning Losses for Image-Text Retrieval","date":"2022-10-21","arxiv_id":"2210.13188","repositories_listed":2,"syntology":null},{"url":"/paper/parameter-efficient-prompt-tuning-makes","slug":"parameter-efficient-prompt-tuning-makes","title":"Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers","date":"2022-07-14","arxiv_id":"2207.07087","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/parameter-efficient-prompt-tuning-makes#ran","syntology_url":"https://syntology.ai/paper/2207.07087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07087"}},"official":{"repos":["thudm/p-tuning-v2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/egocentric-video-language-pretraining","slug":"egocentric-video-language-pretraining","title":"Egocentric Video-Language Pretraining","date":"2022-06-03","arxiv_id":"2206.01670","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/egocentric-video-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2206.01670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01670"}},"official":{"repos":["showlab/egovlp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mugen-a-playground-for-video-audio-text","slug":"mugen-a-playground-for-video-audio-text","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","date":"2022-04-17","arxiv_id":"2204.08058","repositories_listed":2,"syntology":null},{"url":"/paper/dall-eval-probing-the-reasoning-skills-and","slug":"dall-eval-probing-the-reasoning-skills-and","title":"DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models","date":"2022-02-08","arxiv_id":"2202.04053","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dall-eval-probing-the-reasoning-skills-and#ran","syntology_url":"https://syntology.ai/paper/2202.04053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04053"}},"official":{"repos":["j-min/dalleval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bridgeformer-bridging-video-text-retrieval","slug":"bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","arxiv_id":"2201.04850","repositories_listed":2,"syntology":{"n":24,"n_ran":13,"n_constructed":8,"n_ran_checked":9,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":6,"phrase":"13 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/bridgeformer-bridging-video-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2201.04850","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.04850"}},"official":{"repos":["tencentarc/mcq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","repositories_listed":2,"syntology":null},{"url":"/paper/improving-video-text-retrieval-by-multi","slug":"improving-video-text-retrieval-by-multi","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","date":"2021-09-09","arxiv_id":"2109.04290","repositories_listed":2,"syntology":null},{"url":"/paper/lightningdot-pre-training-visual-semantic","slug":"lightningdot-pre-training-visual-semantic","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","date":"2021-03-16","arxiv_id":"2103.08784","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lightningdot-pre-training-visual-semantic#ran","syntology_url":"https://syntology.ai/paper/2103.08784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.08784"}},"official":{"repos":["intersun/LightningDOT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/exploring-classic-and-neural-lexical","slug":"exploring-classic-and-neural-lexical","title":"Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits","date":"2021-02-12","arxiv_id":"2102.06815","repositories_listed":2,"syntology":null},{"url":"/paper/gloria-a-multimodal-global-local","slug":"gloria-a-multimodal-global-local","title":"GLoRIA: A Multimodal Global-Local Representation Learning Framework for Label-Efficient Medical Image Recognition","date":"2021-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-adversarial-training-for-vision","slug":"large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":12,"n_constructed":5,"n_ran_checked":9,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/large-scale-adversarial-training-for-vision#ran","syntology_url":"https://syntology.ai/paper/2006.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06195"}},"official":{"repos":["zhegan27/LXMERT-AdvTrain","zhegan27/VILLA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/the-neuro-symbolic-concept-learner-1","slug":"the-neuro-symbolic-concept-learner-1","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","date":"2019-04-26","arxiv_id":"1904.12584","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-neuro-symbolic-concept-learner-1#ran","syntology_url":"https://syntology.ai/paper/1904.12584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12584"}},"official":{"repos":["vacancy/NSCL-PyTorch-Release"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tree-based-text-retrieval-via-hierarchical","slug":"tree-based-text-retrieval-via-hierarchical","title":"Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese Regulations","date":"2025-06-16","arxiv_id":"2506.13607","repositories_listed":1,"syntology":null},{"url":"/paper/glap-general-contrastive-audio-text","slug":"glap-general-contrastive-audio-text","title":"GLAP: General contrastive audio-text pretraining across domains and languages","date":"2025-06-12","arxiv_id":"2506.11350","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/glap-general-contrastive-audio-text#ran","syntology_url":"https://syntology.ai/paper/2506.11350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.11350"}},"official":{"repos":["xiaomi-research/dasheng-glap"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mstar-box-free-multi-query-scene-text","slug":"mstar-box-free-multi-query-scene-text","title":"MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling","date":"2025-06-12","arxiv_id":"2506.10609","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mstar-box-free-multi-query-scene-text#ran","syntology_url":"https://syntology.ai/paper/2506.10609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.10609"}},"official":{"repos":["yingift/mstar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tablerag-a-retrieval-augmented-generation","slug":"tablerag-a-retrieval-augmented-generation","title":"TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoning","date":"2025-06-12","arxiv_id":"2506.10380","repositories_listed":1,"syntology":null},{"url":"/paper/adding-simple-structure-at-inference-improves","slug":"adding-simple-structure-at-inference-improves","title":"Adding simple structure at inference improves Vision-Language Compositionality","date":"2025-06-11","arxiv_id":"2506.09691","repositories_listed":1,"syntology":null},{"url":"/paper/discovla-discrepancy-reduction-in-vision-1","slug":"discovla-discrepancy-reduction-in-vision-1","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","date":"2025-06-10","arxiv_id":"2506.08887","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/discovla-discrepancy-reduction-in-vision-1#ran","syntology_url":"https://syntology.ai/paper/2506.08887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08887"}},"official":{"repos":["lunarshen/dsicovla"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-medical-vision-language-alignment","slug":"efficient-medical-vision-language-alignment","title":"Efficient Medical Vision-Language Alignment Through Adapting Masked Vision Models","date":"2025-06-10","arxiv_id":"2506.08990","repositories_listed":1,"syntology":null},{"url":"/paper/flagevalmm-a-flexible-framework-for","slug":"flagevalmm-a-flexible-framework-for","title":"FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation","date":"2025-06-10","arxiv_id":"2506.09081","repositories_listed":1,"syntology":null},{"url":"/paper/attacking-attention-of-foundation-models","slug":"attacking-attention-of-foundation-models","title":"Attacking Attention of Foundation Models Disrupts Downstream Tasks","date":"2025-06-03","arxiv_id":"2506.05394","repositories_listed":1,"syntology":null},{"url":"/paper/eru-kg-efficient-reference-aligned","slug":"eru-kg-efficient-reference-aligned","title":"ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation","date":"2025-05-30","arxiv_id":"2505.24219","repositories_listed":1,"syntology":null},{"url":"/paper/one-trajectory-one-token-grounded-video","slug":"one-trajectory-one-token-grounded-video","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","date":"2025-05-29","arxiv_id":"2505.23617","repositories_listed":1,"syntology":null},{"url":"/paper/lovr-a-benchmark-for-long-video-retrieval-in","slug":"lovr-a-benchmark-for-long-video-retrieval-in","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","date":"2025-05-20","arxiv_id":"2505.13928","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11180","slug":"2505-11180","title":"mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs","date":"2025-05-16","arxiv_id":"2505.11180","repositories_listed":1,"syntology":null},{"url":"/paper/reproducibility-replicability-and-insights","slug":"reproducibility-replicability-and-insights","title":"Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction","date":"2025-05-12","arxiv_id":"2505.07730","repositories_listed":1,"syntology":null},{"url":"/paper/a-vision-language-foundation-model-for-leaf","slug":"a-vision-language-foundation-model-for-leaf","title":"A Vision-Language Foundation Model for Leaf Disease Identification","date":"2025-05-11","arxiv_id":"2505.07019","repositories_listed":1,"syntology":null},{"url":"/paper/fg-clip-fine-grained-visual-and-textual","slug":"fg-clip-fine-grained-visual-and-textual","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","date":"2025-05-08","arxiv_id":"2505.05071","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fg-clip-fine-grained-visual-and-textual#ran","syntology_url":"https://syntology.ai/paper/2505.05071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05071"}},"official":{"repos":["360cvgroup/fg-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/med3dvlm-an-efficient-vision-language-model","slug":"med3dvlm-an-efficient-vision-language-model","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","date":"2025-03-25","arxiv_id":"2503.20047","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/med3dvlm-an-efficient-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.20047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20047"}},"official":{"repos":["mirthai/med3dvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-the-gap-benchmarking-spatial-reasoning","slug":"mind-the-gap-benchmarking-spatial-reasoning","title":"Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models","date":"2025-03-25","arxiv_id":"2503.19707","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mind-the-gap-benchmarking-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19707"}},"official":{"repos":["stogiannidis/srbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/goal-global-local-object-alignment-learning","slug":"goal-global-local-object-alignment-learning","title":"GOAL: Global-local Object Alignment Learning","date":"2025-03-22","arxiv_id":"2503.17782","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/goal-global-local-object-alignment-learning#ran","syntology_url":"https://syntology.ai/paper/2503.17782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17782"}},"official":{"repos":["perceptualai-lab/goal"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/atri-mitigating-multilingual-audio-text","slug":"atri-mitigating-multilingual-audio-text","title":"ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors","date":"2025-02-20","arxiv_id":"2502.14627","repositories_listed":1,"syntology":null},{"url":"/paper/siglip-2-multilingual-vision-language","slug":"siglip-2-multilingual-vision-language","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","date":"2025-02-20","arxiv_id":"2502.14786","repositories_listed":1,"syntology":null},{"url":"/paper/peerqa-a-scientific-question-answering","slug":"peerqa-a-scientific-question-answering","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","date":"2025-02-19","arxiv_id":"2502.13668","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/peerqa-a-scientific-question-answering#ran","syntology_url":"https://syntology.ai/paper/2502.13668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13668"}},"official":{"repos":["ukplab/peerqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-working-memory-query-guided-segment","slug":"temporal-working-memory-query-guided-segment","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","date":"2025-02-09","arxiv_id":"2502.06020","repositories_listed":1,"syntology":null},{"url":"/paper/cross-the-gap-exposing-the-intra-modal","slug":"cross-the-gap-exposing-the-intra-modal","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","date":"2025-02-06","arxiv_id":"2502.04263","repositories_listed":1,"syntology":null},{"url":"/paper/expertized-caption-auto-enhancement-for-video","slug":"expertized-caption-auto-enhancement-for-video","title":"Expertized Caption Auto-Enhancement for Video-Text Retrieval","date":"2025-02-05","arxiv_id":"2502.02885","repositories_listed":1,"syntology":null},{"url":"/paper/large-vision-language-models-for-knowledge","slug":"large-vision-language-models-for-knowledge","title":"Large Vision-Language Models for Knowledge-Grounded Data Annotation of Memes","date":"2025-01-23","arxiv_id":"2501.13851","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-graph-retrieval-augmented","slug":"a-survey-of-graph-retrieval-augmented","title":"A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models","date":"2025-01-21","arxiv_id":"2501.13958","repositories_listed":1,"syntology":null},{"url":"/paper/gasliteing-the-retrieval-exploring","slug":"gasliteing-the-retrieval-exploring","title":"GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search","date":"2024-12-30","arxiv_id":"2412.20953","repositories_listed":1,"syntology":null},{"url":"/paper/reversed-in-time-a-novel-temporal-emphasized","slug":"reversed-in-time-a-novel-temporal-emphasized","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","date":"2024-12-26","arxiv_id":"2412.19178","repositories_listed":1,"syntology":null},{"url":"/paper/where-am-i-cross-view-geo-localization-with","slug":"where-am-i-cross-view-geo-localization-with","title":"Where am I? Cross-View Geo-localization with Natural Language Descriptions","date":"2024-12-22","arxiv_id":"2412.17007","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-hypothetical-summary-for-retrieval","slug":"multimodal-hypothetical-summary-for-retrieval","title":"Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering","date":"2024-12-19","arxiv_id":"2412.14880","repositories_listed":1,"syntology":null},{"url":"/paper/i0t-embedding-standardization-method-towards","slug":"i0t-embedding-standardization-method-towards","title":"I0T: Embedding Standardization Method Towards Zero Modality Gap","date":"2024-12-18","arxiv_id":"2412.14384","repositories_listed":1,"syntology":null},{"url":"/paper/clasp-contrastive-language-speech-pretraining","slug":"clasp-contrastive-language-speech-pretraining","title":"CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval","date":"2024-12-17","arxiv_id":"2412.13071","repositories_listed":1,"syntology":null},{"url":"/paper/carel-instruction-guided-reinforcement","slug":"carel-instruction-guided-reinforcement","title":"CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives","date":"2024-11-29","arxiv_id":"2411.19787","repositories_listed":1,"syntology":null},{"url":"/paper/audiosetcaps-an-enriched-audio-caption","slug":"audiosetcaps-an-enriched-audio-caption","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","date":"2024-11-28","arxiv_id":"2411.18953","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/audiosetcaps-an-enriched-audio-caption#ran","syntology_url":"https://syntology.ai/paper/2411.18953","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18953"}},"official":{"repos":["jishengbai/audiosetcaps"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-of-medical-vision-and-language","slug":"a-survey-of-medical-vision-and-language","title":"A Survey of Medical Vision-and-Language Applications and Their Techniques","date":"2024-11-19","arxiv_id":"2411.12195","repositories_listed":1,"syntology":null}],"syntology_records":46,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":10,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/text-retrieval-on-mteb","since_archive":"/sota/text-retrieval-on-mteb#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/text-retrieval-on-fever","since_archive":"/sota/text-retrieval-on-fever#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/text-retrieval-on-hotpotqa","since_archive":"/sota/text-retrieval-on-hotpotqa#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/text-retrieval-on-ms-marco","since_archive":"/sota/text-retrieval-on-ms-marco#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/text-retrieval-on-nfcorpus","since_archive":"/sota/text-retrieval-on-nfcorpus#since-judged","papers_judged":4,"placed":1},{"leaderboard":"/sota/text-retrieval-on-scidocs","since_archive":"/sota/text-retrieval-on-scidocs#since-judged","papers_judged":5,"placed":1},{"leaderboard":"/sota/text-retrieval-on-scifact","since_archive":"/sota/text-retrieval-on-scifact#since-judged","papers_judged":5,"placed":1},{"leaderboard":"/sota/text-retrieval-on-trec-covid","since_archive":"/sota/text-retrieval-on-trec-covid#since-judged","papers_judged":3,"placed":0}]},"papers_where_code_ran":117,"papers_where_code_ran_first_page":"/task/text-retrieval/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":7,"url":"/task/text-retrieval/papers/2","json":"/task/text-retrieval/papers/2.json","rows":100},{"order":"archive","page":3,"of":7,"url":"/task/text-retrieval/papers/3","json":"/task/text-retrieval/papers/3.json","rows":100},{"order":"archive","page":4,"of":7,"url":"/task/text-retrieval/papers/4","json":"/task/text-retrieval/papers/4.json","rows":100},{"order":"archive","page":5,"of":7,"url":"/task/text-retrieval/papers/5","json":"/task/text-retrieval/papers/5.json","rows":100},{"order":"archive","page":6,"of":7,"url":"/task/text-retrieval/papers/6","json":"/task/text-retrieval/papers/6.json","rows":100},{"order":"archive","page":7,"of":7,"url":"/task/text-retrieval/papers/7","json":"/task/text-retrieval/papers/7.json","rows":71},{"order":"ran","page":1,"of":2,"url":"/task/text-retrieval/papers/ran/1","json":"/task/text-retrieval/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/text-retrieval/papers/ran/2","json":"/task/text-retrieval/papers/ran/2.json","rows":17}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"8b6799281d154bd68ed9782ba4eac143597291c5508dd6d66f603ddd2d894054","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}