{"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/resized-crop","entry":"resized_crop","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":5,"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":3,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2502.13363","paper":"/paper/pretrained-image-text-models-are-secretly","title":"Pretrained Image-Text Models are Secretly Video Captioners","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chunhuizng/mllm-video-captioner","path":"lavis/processors/functional_video.py","file_url":"https://github.com/chunhuizng/mllm-video-captioner/blob/HEAD/lavis/processors/functional_video.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":false,"code_sha256_prefix":"d0e65b9f687e2f97","mcp_get_code":{"code_sha256":"d0e65b9f687e2f97"}},{"arxiv_id":"2411.12951","paper":"/paper/on-the-consistency-of-video-large-language","title":"On the Consistency of Video Large Language Models in Temporal Comprehension","date":"2024-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minjoong507/consistency-of-video-llm","path":"timechat/processors/functional_video.py","file_url":"https://github.com/minjoong507/consistency-of-video-llm/blob/HEAD/timechat/processors/functional_video.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d0e65b9f687e2f97","mcp_get_code":{"code_sha256":"d0e65b9f687e2f97"}},{"arxiv_id":"2402.16050","paper":"/paper/lstp-language-guided-spatial-temporal-prompt","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigai-nlco/VideoTGB","path":"src/gadgets/functional_video.py","file_url":"https://github.com/bigai-nlco/VideoTGB/blob/HEAD/src/gadgets/functional_video.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0e65b9f687e2f97","mcp_get_code":{"code_sha256":"d0e65b9f687e2f97"}},{"arxiv_id":"2310.04900","paper":"/paper/howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ninatu/howtocaption","path":"howtocaption/data_loader/utils.py","file_url":"https://github.com/ninatu/howtocaption/blob/HEAD/howtocaption/data_loader/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2663cef69f96fe01","mcp_get_code":{"code_sha256":"2663cef69f96fe01"}},{"arxiv_id":"2308.06112","paper":"/paper/lip2vec-efficient-and-robust-visual-speech","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","date":"2023-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YasserdahouML/Lip2Vec","path":"datasets/functional_video.py","file_url":"https://github.com/YasserdahouML/Lip2Vec/blob/HEAD/datasets/functional_video.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b0239305ba36c73f","mcp_get_code":{"code_sha256":"b0239305ba36c73f"}}]}