{"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/attn","entry":"attn","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+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":9,"n_papers_ran":8,"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":5,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":10,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":2,"ran":0,"unverified":1},"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/video_transformer.py","file_url":"https://github.com/xuboshen/EgoNCEpp/blob/HEAD/EgoVLP/model/video_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"544c604bc4f58d28","mcp_get_code":{"code_sha256":"544c604bc4f58d28"}},{"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/video_transformer.py","file_url":"https://github.com/facebookresearch/EgoVLPv2/blob/HEAD/EgoVLPv2/model/video_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"544c604bc4f58d28","mcp_get_code":{"code_sha256":"544c604bc4f58d28"}},{"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/video_transformer.py","file_url":"https://github.com/callsys/textvr/blob/HEAD/model/video_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"544c604bc4f58d28","mcp_get_code":{"code_sha256":"544c604bc4f58d28"}},{"arxiv_id":"2212.04501","paper":"/paper/learning-video-representations-from-large","title":"Learning Video Representations from Large Language Models","date":"2022-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/lavila","path":"lavila/models/timesformer.py","file_url":"https://github.com/facebookresearch/lavila/blob/HEAD/lavila/models/timesformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"544c604bc4f58d28","mcp_get_code":{"code_sha256":"544c604bc4f58d28"}},{"arxiv_id":"2210.10820","paper":"/paper/vtc-improving-video-text-retrieval-with-user","title":"VTC: Improving Video-Text Retrieval with User Comments","date":"2022-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"unitaryai/VTC","path":"model/timesformer_clip.py","file_url":"https://github.com/unitaryai/VTC/blob/HEAD/model/timesformer_clip.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"544c604bc4f58d28","mcp_get_code":{"code_sha256":"544c604bc4f58d28"}},{"arxiv_id":"2201.04850","paper":"/paper/bridgeformer-bridging-video-text-retrieval","title":"Bridging Video-text Retrieval with Multiple Choice Questions","date":"2022-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/bridgeformer/bridge_former_training_block.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/bridgeformer/bridge_former_training_block.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"19f4493dcaecc931","mcp_get_code":{"code_sha256":"19f4493dcaecc931"}},{"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/video_transformer.py","file_url":"https://github.com/m-bain/frozen-in-time/blob/HEAD/model/video_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"544c604bc4f58d28","mcp_get_code":{"code_sha256":"544c604bc4f58d28"}},{"arxiv_id":"2102.05095","paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/TimeSformer-pytorch","path":"timesformer_pytorch/timesformer_pytorch.py","file_url":"https://github.com/lucidrains/TimeSformer-pytorch/blob/HEAD/timesformer_pytorch/timesformer_pytorch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d2b139fbe3e2fe5","mcp_get_code":{"code_sha256":"5d2b139fbe3e2fe5"}},{"arxiv_id":"2102.05095","paper":"/paper/is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"halixness/generative_timesformer_pytorch","path":"timesformer_pytorch/timesformer_pytorch.py","file_url":"https://github.com/halixness/generative_timesformer_pytorch/blob/HEAD/timesformer_pytorch/timesformer_pytorch.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c9b2023a8e7f543b","mcp_get_code":{"code_sha256":"c9b2023a8e7f543b"}},{"arxiv_id":"1805.11462","paper":"/paper/opennmt-neural-machine-translation-toolkit","title":"OpenNMT: Neural Machine Translation Toolkit","date":"2018-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deep-spin/OpenNMT-entmax","path":"eval2table.py","file_url":"https://github.com/deep-spin/OpenNMT-entmax/blob/HEAD/eval2table.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ba6eb69db2dce38","mcp_get_code":{"code_sha256":"1ba6eb69db2dce38"}}]}