{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/v2t-metrics","entry":"v2t_metrics","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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)"},"n_papers":8,"n_papers_ran":2,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":6,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":4},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2405.17719","paper":"/paper/egonce-do-egocentric-video-language-models","title":"EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions?","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuboshen/EgoNCEpp","path":"EgoVLP/model/metric.py","file_url":"https://github.com/xuboshen/EgoNCEpp/blob/HEAD/EgoVLP/model/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"52a134b570ef6e0c","mcp_get_code":{"code_sha256":"52a134b570ef6e0c"}},{"arxiv_id":"2311.18259","paper":"/paper/ego-exo4d-understanding-skilled-human","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","date":"2023-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/EgoVLPv2","path":"EgoVLPv2/model/metric.py","file_url":"https://github.com/facebookresearch/EgoVLPv2/blob/HEAD/EgoVLPv2/model/metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"843a44c72eb4765d","mcp_get_code":{"code_sha256":"843a44c72eb4765d"}},{"arxiv_id":"2305.03347","paper":"/paper/a-large-cross-modal-video-retrieval-dataset","title":"A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension","date":"2023-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"callsys/textvr","path":"model/metric.py","file_url":"https://github.com/callsys/textvr/blob/HEAD/model/metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"000e15329b7114d0","mcp_get_code":{"code_sha256":"000e15329b7114d0"}},{"arxiv_id":"2105.02192","paper":"/paper/audio-retrieval-with-natural-language-queries","title":"Audio Retrieval with Natural Language Queries","date":"2021-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oncescuandreea/audio-retrieval","path":"model/metric.py","file_url":"https://github.com/oncescuandreea/audio-retrieval/blob/HEAD/model/metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"382b08bd2c7acdef","mcp_get_code":{"code_sha256":"382b08bd2c7acdef"}},{"arxiv_id":"2104.08271","paper":"/paper/teachtext-crossmodal-generalized-distillation","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"albanie/collaborative-experts","path":"model/metric.py","file_url":"https://github.com/albanie/collaborative-experts/blob/HEAD/model/metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0ce3d614411abce7","mcp_get_code":{"code_sha256":"0ce3d614411abce7"}},{"arxiv_id":"2104.00650","paper":"/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","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"m-bain/frozen-in-time","path":"model/metric.py","file_url":"https://github.com/m-bain/frozen-in-time/blob/HEAD/model/metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"000e15329b7114d0","mcp_get_code":{"code_sha256":"000e15329b7114d0"}},{"arxiv_id":"2007.10639","paper":"/paper/multi-modal-transformer-for-video-retrieval","title":"Multi-modal Transformer for Video Retrieval","date":"2020-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gabeur/mmt","path":"model/metric.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/model/metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"79bc20d6b4080f0b","mcp_get_code":{"code_sha256":"79bc20d6b4080f0b"}},{"arxiv_id":"1907.13487","paper":"/paper/use-what-you-have-video-retrieval-using","title":"Use What You Have: Video Retrieval Using Representations From Collaborative Experts","date":"2019-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caijincen712/CE","path":"model/metric.py","file_url":"https://github.com/caijincen712/CE/blob/HEAD/model/metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0ce3d614411abce7","mcp_get_code":{"code_sha256":"0ce3d614411abce7"}}]}