{"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":3,"n_unverified":10,"n_pointer_only":0}}},{"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_unverified":1,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":0,"n_unverified":7,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}},{"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":10,"n_unverified":12,"n_pointer_only":0}}}],"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":335,"tagged_in_all":671,"items":[{"url":"/paper/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","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":4,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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":7,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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":1,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/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":3,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/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","title":"Stacked Cross Attention for Image-Text Matching","date":"2018-03-21","arxiv_id":"1803.08024","repositories_listed":6,"syntology":{"n":16,"n_ran":7,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/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":3,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":3}},{"url":"/paper/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":3,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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_unverified":2,"n_pointer_only":9}},{"url":"/paper/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":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/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","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","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":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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":10,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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","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":0,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/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":2,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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_unverified":7,"n_pointer_only":0}}],"syntology_records":18,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}