{"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":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":{"name":"Zero-Shot Video Retrieval","url":"/task/zero-shot-video-retrieval","note":null},"dataset":{"name":"MSR-VTT","url":"/dataset/msr-vtt"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Zero-shot video retrieval is the task of retrieving relevant videos based on a query (usually in text form) without any prior training on specific examples of those videos. Unlike traditional retrieval methods that rely on supervised learning with annotated datasets, zero-shot retrieval leverages pre-trained models, typically based on large-scale vision-language learning, to understand semantic relationships between textual descriptions and video content.\r\n\r\nThis approach enables retrieval of unseen video concepts by generalizing knowledge from diverse training data, making it highly useful for domains with limited labeled data, such as broadcast media, surveillance, and historical archives.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["text-to-video R@1","text-to-video R@5","text-to-video R@10","text-to-video Median Rank","text-to-video Mean Rank","video-to-text R@1","video-to-text R@5","video-to-text R@10","video-to-text Median Rank"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"text-to-video R@1":null,"text-to-video R@5":null,"text-to-video R@10":null,"text-to-video Median Rank":null,"text-to-video Mean Rank":null,"video-to-text R@1":null,"video-to-text R@5":null,"video-to-text R@10":null,"video-to-text Median Rank":null}},"counts":{"rows":41,"rows_with_code":35,"rows_with_paper_page":41,"rows_dated":41,"rows_using_additional_data":16},"rows":[{"rank_in_archive_order":1,"model":"InternVideo2-6B","metrics":{"text-to-video R@1":"55.9","text-to-video R@10":"85.1","text-to-video R@5":"78.3","video-to-text R@1":"53.7","video-to-text R@10":"84.1","video-to-text R@5":"77.5"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"GRAM","metrics":{"text-to-video R@1":"54.8","text-to-video R@10":"83.9","video-to-text R@1":"52.9","video-to-text R@10":"82.9"},"uses_additional_data":true,"paper_date":"2024-12-16","paper":"/paper/gramian-multimodal-representation-learning","paper_url":"https://arxiv.org/abs/2412.11959v1","paper_title":"Gramian Multimodal Representation Learning and Alignment","code":"https://github.com/ispamm/GRAM","n_code_links":2,"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"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":1,"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"}}}},{"rank_in_archive_order":3,"model":"InternVideo2-1B","metrics":{"text-to-video R@1":"51.9","text-to-video R@10":"82.5","text-to-video R@5":"75.3","video-to-text R@1":"50.9","video-to-text R@10":"81.8","video-to-text R@5":"73.4"},"uses_additional_data":true,"paper_date":"2024-03-22","paper":"/paper/internvideo2-scaling-video-foundation-models","paper_url":"https://arxiv.org/abs/2403.15377v4","paper_title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"VAST, HowToCaption-finetuned","metrics":{"text-to-video Median Rank":"1","text-to-video R@1":"50","text-to-video R@10":"81.4","text-to-video R@5":"73.2"},"uses_additional_data":false,"paper_date":"2023-10-07","paper":"/paper/howtocaption-prompting-llms-to-transform","paper_url":"https://arxiv.org/abs/2310.04900v2","paper_title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","code":"https://github.com/ninatu/howtocaption","n_code_links":1,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"rank_in_archive_order":5,"model":"FluxViT-B","metrics":{"text-to-video R@1":"49.9","text-to-video R@10":"79.6","text-to-video R@5":"71.0","video-to-text R@1":"49.4","video-to-text R@10":"82.4","video-to-text R@5":"73.9"},"uses_additional_data":true,"paper_date":"2025-03-18","paper":"/paper/make-your-training-flexible-towards","paper_url":"https://arxiv.org/abs/2503.14237v1","paper_title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","code":"https://github.com/opengvlab/fluxvit","n_code_links":1,"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":0,"n_samples":17,"n_pointer_only_licence":6,"sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}}}},{"rank_in_archive_order":6,"model":"VAST","metrics":{"text-to-video R@1":"49.3","text-to-video R@10":"73.9","text-to-video R@5":"68.3"},"uses_additional_data":true,"paper_date":"2023-05-29","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_url":"https://arxiv.org/abs/2305.18500v2","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","code":"https://github.com/TXH-mercury/VALOR","n_code_links":2,"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_samples":42,"n_pointer_only_licence":8,"sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}}}},{"rank_in_archive_order":7,"model":"mPLUG-2","metrics":{"text-to-video R@1":"47.1","text-to-video R@10":"79.0","text-to-video R@5":"69.7"},"uses_additional_data":false,"paper_date":"2023-02-01","paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","paper_url":"https://arxiv.org/abs/2302.00402v1","paper_title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","code":"https://github.com/modelscope/modelscope","n_code_links":4,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_samples":19,"n_pointer_only_licence":2,"sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"rank_in_archive_order":8,"model":"FluxViT-S","metrics":{"text-to-video R@1":"45.0","text-to-video R@10":"75.8","text-to-video R@5":"67.5","video-to-text R@1":"44.9","video-to-text R@10":"76.5","video-to-text R@5":"68.2"},"uses_additional_data":true,"paper_date":"2025-03-18","paper":"/paper/make-your-training-flexible-towards","paper_url":"https://arxiv.org/abs/2503.14237v1","paper_title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","code":"https://github.com/opengvlab/fluxvit","n_code_links":1,"official":{"repos":["opengvlab/fluxvit"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":0,"n_samples":17,"n_pointer_only_licence":6,"sample_list":"/paper/make-your-training-flexible-towards#ran","syntology_url":"https://syntology.ai/paper/2503.14237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14237"}}}},{"rank_in_archive_order":9,"model":"LanguageBind(ViT-H/14)","metrics":{"text-to-video Median Rank":"2","text-to-video R@1":"44.8","text-to-video R@10":"78.7","text-to-video R@5":"70.0","video-to-text Median Rank":"2.","video-to-text R@1":"40.9","video-to-text R@10":"75.7","video-to-text R@5":"66.4"},"uses_additional_data":true,"paper_date":"2023-10-03","paper":"/paper/languagebind-extending-video-language","paper_url":"https://arxiv.org/abs/2310.01852v7","paper_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","code":"https://github.com/PKU-YuanGroup/Video-LLaVA","n_code_links":6,"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"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":10,"model":"LanguageBind(ViT-L/14)","metrics":{"text-to-video Median Rank":"2.0","text-to-video R@1":"42.8","text-to-video R@10":"76.0","text-to-video R@5":"67.5","video-to-text Median Rank":"3.0","video-to-text R@1":"38.3","video-to-text R@10":"77.8","video-to-text R@5":"65.8"},"uses_additional_data":true,"paper_date":"2023-10-03","paper":"/paper/languagebind-extending-video-language","paper_url":"https://arxiv.org/abs/2310.01852v7","paper_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","code":"https://github.com/PKU-YuanGroup/Video-LLaVA","n_code_links":6,"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"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":11,"model":"UMT-L (ViT-L/16)","metrics":{"text-to-video R@1":"42.6","text-to-video R@10":"73.1","text-to-video R@5":"64.4","video-to-text R@1":"38.6","video-to-text R@10":"69.6","video-to-text R@5":"59.8"},"uses_additional_data":true,"paper_date":"2023-03-28","paper":"/paper/unmasked-teacher-towards-training-efficient","paper_url":"https://arxiv.org/abs/2303.16058v2","paper_title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","code":"https://github.com/opengvlab/unmasked_teacher","n_code_links":1,"official":{"repos":["opengvlab/unmasked_teacher"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":3,"sample_list":"/paper/unmasked-teacher-towards-training-efficient#ran","syntology_url":"https://syntology.ai/paper/2303.16058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16058"}}}},{"rank_in_archive_order":12,"model":"vid-TLDR (UMT-L)","metrics":{"text-to-video R@1":"42.1","text-to-video R@10":"72.4","text-to-video R@5":"63.9","video-to-text R@1":"37.7","video-to-text R@10":"69.4","video-to-text R@5":"59.8"},"uses_additional_data":true,"paper_date":"2024-03-20","paper":"/paper/vid-tldr-training-free-token-merging-for","paper_url":"https://arxiv.org/abs/2403.13347v2","paper_title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","code":"https://github.com/mlvlab/vid-tldr","n_code_links":1,"official":{"repos":["mlvlab/vid-tldr"],"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/vid-tldr-training-free-token-merging-for#ran","syntology_url":"https://syntology.ai/paper/2403.13347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13347"}}}},{"rank_in_archive_order":13,"model":"BT-Adapter","metrics":{"text-to-video R@1":"40.9","text-to-video R@10":"73.5","text-to-video R@5":"64.7"},"uses_additional_data":false,"paper_date":"2023-09-27","paper":"/paper/one-for-all-video-conversation-is-feasible","paper_url":"https://arxiv.org/abs/2309.15785v2","paper_title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","code":"https://github.com/farewellthree/BT-Adapter","n_code_links":1,"official":{"repos":["farewellthree/BT-Adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":2,"sample_list":"/paper/one-for-all-video-conversation-is-feasible#ran","syntology_url":"https://syntology.ai/paper/2309.15785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15785"}}}},{"rank_in_archive_order":14,"model":"InternVideo","metrics":{"text-to-video R@1":"40.7","video-to-text R@1":"39.6"},"uses_additional_data":true,"paper_date":"2022-12-06","paper":"/paper/internvideo-general-video-foundation-models","paper_url":"https://arxiv.org/abs/2212.03191v2","paper_title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","code":"https://github.com/opengvlab/internvideo","n_code_links":2,"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}}}},{"rank_in_archive_order":15,"model":"Florence","metrics":{"text-to-video R@1":"37.6","text-to-video R@10":"72.6","text-to-video R@5":"63.8"},"uses_additional_data":false,"paper_date":"2021-11-22","paper":"/paper/florence-a-new-foundation-model-for-computer","paper_url":"https://arxiv.org/abs/2111.11432v1","paper_title":"Florence: A New Foundation Model for Computer Vision","code":"https://github.com/microsoft/unicl","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"HowToCaption","metrics":{"text-to-video Median Rank":"3","text-to-video R@1":"37.6","text-to-video R@10":"73.3","text-to-video R@5":"62"},"uses_additional_data":false,"paper_date":"2023-10-07","paper":"/paper/howtocaption-prompting-llms-to-transform","paper_url":"https://arxiv.org/abs/2310.04900v2","paper_title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","code":"https://github.com/ninatu/howtocaption","n_code_links":1,"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5,"sample_list":"/paper/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}}}},{"rank_in_archive_order":17,"model":"ImageBind","metrics":{"text-to-video R@1":"36.8","text-to-video R@10":"70.0","text-to-video R@5":"61.8"},"uses_additional_data":false,"paper_date":"2023-05-09","paper":"/paper/imagebind-one-embedding-space-to-bind-them","paper_url":"https://arxiv.org/abs/2305.05665v2","paper_title":"ImageBind: One Embedding Space To Bind Them All","code":"https://github.com/facebookresearch/imagebind","n_code_links":3,"official":{"repos":["facebookresearch/imagebind"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":10,"n_ran_no_instrument_failure":15,"n_unverified":7,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":24,"n_constructed":14,"n_ran_checked":21,"n_instrument":3,"n_unverified":10,"n_samples":34,"n_pointer_only_licence":32,"sample_list":"/paper/imagebind-one-embedding-space-to-bind-them#ran","syntology_url":"https://syntology.ai/paper/2305.05665","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05665"}}}},{"rank_in_archive_order":18,"model":"OmniVL","metrics":{"text-to-video R@1":"34.6","text-to-video R@10":"66.6","text-to-video R@5":"58.4"},"uses_additional_data":true,"paper_date":"2022-09-15","paper":"/paper/omnivl-one-foundation-model-for-image","paper_url":"https://arxiv.org/abs/2209.07526v2","paper_title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"HiTeA-17M","metrics":{"text-to-video R@1":"34.4","text-to-video R@10":"69.9","text-to-video R@5":"60.0"},"uses_additional_data":false,"paper_date":"2022-12-30","paper":"/paper/hitea-hierarchical-temporal-aware-video","paper_url":"https://arxiv.org/abs/2212.14546v1","paper_title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"Singularity-17M","metrics":{"text-to-video R@1":"34.0","text-to-video R@10":"66.7","text-to-video R@5":"56.7"},"uses_additional_data":true,"paper_date":"2022-06-07","paper":"/paper/revealing-single-frame-bias-for-video-and","paper_url":"https://arxiv.org/abs/2206.03428v1","paper_title":"Revealing Single Frame Bias for Video-and-Language Learning","code":"https://github.com/jayleicn/ClipBERT","n_code_links":2,"official":{"repos":["jayleicn/singularity"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":2,"sample_list":"/paper/revealing-single-frame-bias-for-video-and#ran","syntology_url":"https://syntology.ai/paper/2206.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03428"}}}},{"rank_in_archive_order":21,"model":"CLIP4Clip","metrics":{"text-to-video Mean Rank":"34.0","text-to-video Median Rank":"4","text-to-video R@1":"32.0","text-to-video R@10":"66.9","text-to-video R@5":"57.0"},"uses_additional_data":false,"paper_date":"2021-04-18","paper":"/paper/clip4clip-an-empirical-study-of-clip-for-end","paper_url":"https://arxiv.org/abs/2104.08860v2","paper_title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","code":"https://github.com/towhee-io/towhee","n_code_links":5,"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"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":22,"model":"Yatai Ji et. al.","metrics":{"text-to-video R@1":"30.9","text-to-video R@10":"65.0","text-to-video R@5":"54.4"},"uses_additional_data":false,"paper_date":"2022-11-24","paper":"/paper/seeing-what-you-miss-vision-language-pre","paper_url":"https://arxiv.org/abs/2211.13437v2","paper_title":"Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning","code":"https://github.com/iigroup/scl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"HiTeA-5M","metrics":{"text-to-video R@1":"29.9","text-to-video R@10":"62.9","text-to-video R@5":"54.2"},"uses_additional_data":false,"paper_date":"2022-12-30","paper":"/paper/hitea-hierarchical-temporal-aware-video","paper_url":"https://arxiv.org/abs/2212.14546v1","paper_title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"Singularity-5M","metrics":{"text-to-video R@1":"28.4","text-to-video R@10":"59.5","text-to-video R@5":"50.2"},"uses_additional_data":true,"paper_date":"2022-06-07","paper":"/paper/revealing-single-frame-bias-for-video-and","paper_url":"https://arxiv.org/abs/2206.03428v1","paper_title":"Revealing Single Frame Bias for Video-and-Language Learning","code":"https://github.com/jayleicn/ClipBERT","n_code_links":2,"official":{"repos":["jayleicn/singularity"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":2,"sample_list":"/paper/revealing-single-frame-bias-for-video-and#ran","syntology_url":"https://syntology.ai/paper/2206.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.03428"}}}},{"rank_in_archive_order":25,"model":"Clover","metrics":{"text-to-video Median Rank":"6","text-to-video R@1":"26.4","text-to-video R@10":"60","text-to-video R@5":"49.5"},"uses_additional_data":false,"paper_date":"2022-07-16","paper":"/paper/clover-towards-a-unified-video-language","paper_url":"https://arxiv.org/abs/2207.07885v3","paper_title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","code":"https://github.com/leeyn-43/clover","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"MILES","metrics":{"text-to-video Median Rank":"7","text-to-video R@1":"26.1","text-to-video R@10":"56.9","text-to-video R@5":"47.2"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/miles-visual-bert-pre-training-with-injected","paper_url":"https://arxiv.org/abs/2204.12408v1","paper_title":"MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval","code":"https://github.com/tencentarc/mcq","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"Y. Ge et. al.","metrics":{"text-to-video Median Rank":"7.0","text-to-video R@1":"26.0","text-to-video R@10":"56.4","text-to-video R@5":"46.4"},"uses_additional_data":false,"paper_date":"2022-01-13","paper":"/paper/bridgeformer-bridging-video-text-retrieval","paper_url":"https://arxiv.org/abs/2201.04850v2","paper_title":"Bridging Video-text Retrieval with Multiple Choice Questions","code":"https://github.com/towhee-io/towhee","n_code_links":2,"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"]},"syntology":{"n_ran":13,"n_constructed":8,"n_ran_checked":9,"n_instrument":4,"n_unverified":11,"n_samples":24,"n_pointer_only_licence":6,"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"}}}},{"rank_in_archive_order":28,"model":"VIOLET","metrics":{"text-to-video R@1":"25.9","text-to-video R@10":"59.7","text-to-video R@5":"49.5"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/violet-end-to-end-video-language-transformers","paper_url":"https://arxiv.org/abs/2111.12681v2","paper_title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","code":"https://github.com/tsujuifu/pytorch_violet","n_code_links":1,"official":{"repos":["tsujuifu/pytorch_violet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/violet-end-to-end-video-language-transformers#ran","syntology_url":"https://syntology.ai/paper/2111.12681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12681"}}}},{"rank_in_archive_order":29,"model":"FROZEN","metrics":{"text-to-video Median Rank":"7.0","text-to-video R@1":"24.7","text-to-video R@10":"57.2","text-to-video R@5":"46.9"},"uses_additional_data":false,"paper_date":"2021-04-01","paper":"/paper/frozen-in-time-a-joint-video-and-image","paper_url":"https://arxiv.org/abs/2104.00650v2","paper_title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","code":"https://github.com/towhee-io/towhee","n_code_links":5,"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"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":3,"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"}}}},{"rank_in_archive_order":30,"model":"ALPRO","metrics":{"text-to-video Median Rank":"8","text-to-video R@1":"24.1","text-to-video R@10":"55.4","text-to-video R@5":"44.7"},"uses_additional_data":false,"paper_date":"2021-12-17","paper":"/paper/align-and-prompt-video-and-language-pre","paper_url":"https://arxiv.org/abs/2112.09583v2","paper_title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","code":"https://github.com/salesforce/alpro","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"OA-Trans","metrics":{"text-to-video Median Rank":"8.0","text-to-video R@1":"23.4","text-to-video R@10":"55.6","text-to-video R@5":"47.5"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/object-aware-video-language-pre-training-for","paper_url":"https://arxiv.org/abs/2112.00656v6","paper_title":"Object-aware Video-language Pre-training for Retrieval","code":"https://github.com/FingerRec/OA-Transformer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"LaT","metrics":{"text-to-video Median Rank":"8","text-to-video R@1":"23.4","text-to-video R@10":"53.3","text-to-video R@5":"44.1","video-to-text Median Rank":"12","video-to-text R@1":"17.2","video-to-text R@10":"47.9","video-to-text R@5":"36.2"},"uses_additional_data":false,"paper_date":"2022-07-11","paper":"/paper/lat-latent-translation-with-cycle-consistency","paper_url":"https://arxiv.org/abs/2207.04858v2","paper_title":"LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"A. Nagrani et. al.","metrics":{"text-to-video R@1":"19.4","text-to-video R@10":"50.3","text-to-video R@5":"39.5"},"uses_additional_data":true,"paper_date":"2022-04-01","paper":"/paper/learning-audio-video-modalities-from-image","paper_url":"https://arxiv.org/abs/2204.00679v1","paper_title":"Learning Audio-Video Modalities from Image Captions","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"HD-VILA","metrics":{"text-to-video Median Rank":"15","text-to-video R@1":"14.6","text-to-video R@10":"44.1","text-to-video R@5":"34.4"},"uses_additional_data":false,"paper_date":"2021-11-19","paper":"/paper/advancing-high-resolution-video-language","paper_url":"https://arxiv.org/abs/2111.10337v2","paper_title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","code":"https://github.com/microsoft/xpretrain","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"Norton","metrics":{"text-to-video R@1":"10.7","text-to-video R@5":"24.1"},"uses_additional_data":false,"paper_date":"2024-01-30","paper":"/paper/multi-granularity-correspondence-learning-1","paper_url":"https://arxiv.org/abs/2401.16702v1","paper_title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","code":"https://github.com/XLearning-SCU/2024-ICLR-Norton","n_code_links":1,"official":null,"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/multi-granularity-correspondence-learning-1#ran","syntology_url":"https://syntology.ai/paper/2401.16702","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16702"}}}},{"rank_in_archive_order":36,"model":"VideoCLIP","metrics":{"text-to-video R@1":"10.4","text-to-video R@10":"30.0","text-to-video R@5":"22.2"},"uses_additional_data":false,"paper_date":"2021-09-28","paper":"/paper/videoclip-contrastive-pre-training-for-zero","paper_url":"https://arxiv.org/abs/2109.14084v2","paper_title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","code":"https://github.com/facebookresearch/fairseq","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"MIL-NCE","metrics":{"text-to-video Mean Rank":"29.5","text-to-video R@1":"9.9","text-to-video R@10":"32.4","text-to-video R@5":"24.0"},"uses_additional_data":false,"paper_date":"2019-12-13","paper":"/paper/end-to-end-learning-of-visual-representations","paper_url":"https://arxiv.org/abs/1912.06430v4","paper_title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","code":"https://github.com/antoine77340/MIL-NCE_HowTo100M","n_code_links":4,"official":{"repos":["antoine77340/MIL-NCE_HowTo100M"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":2,"sample_list":"/paper/end-to-end-learning-of-visual-representations#ran","syntology_url":"https://syntology.ai/paper/1912.06430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.06430"}}}},{"rank_in_archive_order":38,"model":"TACo","metrics":{"text-to-video R@1":"9.8","text-to-video R@10":"33.4","text-to-video R@5":"25.0"},"uses_additional_data":false,"paper_date":"2021-08-23","paper":"/paper/taco-token-aware-cascade-contrastive-learning","paper_url":"https://arxiv.org/abs/2108.09980v1","paper_title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"SSML","metrics":{"text-to-video R@1":"8.0","text-to-video R@10":"29.3","text-to-video R@5":"21.3"},"uses_additional_data":false,"paper_date":"2020-03-06","paper":"/paper/noise-estimation-using-density-estimation-for","paper_url":"https://arxiv.org/abs/2003.03186v3","paper_title":"Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning","code":"https://github.com/elad-amrani/ssml","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"MMT","metrics":{"text-to-video Mean Rank":"148.1","text-to-video Median Rank":"66","text-to-video R@5":"14.4"},"uses_additional_data":true,"paper_date":"2020-07-21","paper":"/paper/multi-modal-transformer-for-video-retrieval","paper_url":"https://arxiv.org/abs/2007.10639v1","paper_title":"Multi-modal Transformer for Video Retrieval","code":"https://github.com/gabeur/mmt","n_code_links":1,"official":null,"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/multi-modal-transformer-for-video-retrieval#ran","syntology_url":"https://syntology.ai/paper/2007.10639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10639"}}}},{"rank_in_archive_order":41,"model":"VATT-MBS","metrics":{"text-to-video Median Rank":"49","text-to-video R@10":"29.7"},"uses_additional_data":false,"paper_date":"2021-04-22","paper":"/paper/vatt-transformers-for-multimodal-self","paper_url":"https://arxiv.org/abs/2104.11178v3","paper_title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","code":"https://github.com/google-research/google-research/tree/master/vatt","n_code_links":5,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":5,"n_constructed":4,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/vatt-transformers-for-multimodal-self#ran","syntology_url":"https://syntology.ai/paper/2104.11178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11178"}}}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 6 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,590 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 1 proposed a result, which gave no cell that passed the extractor's own checks; none await a verdict and none were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":41,"metric_columns":9,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1590,"candidates":6,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":1,"no_cell_passed_checks":1,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 1 newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"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","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":1,"shown_on_page":1,"no_cell_split":{"no_cell_passed_checks_in_ledger":1,"rows_refused_by_rule":1,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2509.24734","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","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)"},"rows_with_graph_line":24,"rows_with_any_sample_ran":23,"rows_with_a_run_with_no_instrument_failure":20,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":22,"rows_whose_official_repository_has_a_sample_that_ran":16,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":13,"rows_community_repositories_only":4,"rows_runs_from_other_or_unrecorded_repositories":0,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology 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","distinct_papers_with_graph_line":20,"distinct_papers_with_any_sample_ran":19,"distinct_papers_with_a_run_with_no_instrument_failure":16,"samples_over_distinct_papers":{"n_ran":186,"n_constructed":32,"n_ran_checked":134,"n_instrument":52,"n_unverified":52,"n_samples":238,"n_pointer_only_licence":88,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":228,"n_constructed":32,"n_ran_checked":171,"n_instrument":57,"n_unverified":58,"n_samples":286,"n_pointer_only_licence":104,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"4195b9e0ee3a385060471e2718c8d4b822a427684cdcc6a5058872f0dff635f5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}