{"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/sample-frames","entry":"sample_frames","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":8,"n_papers_ran":4,"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":7,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":3,"unverified":3},"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":"2607.03612","paper":"/paper/arxiv-2607-03612","title":"SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"jndeng/SAF3R","path":"saf3r/profile_models.py","file_url":"https://github.com/jndeng/SAF3R/blob/HEAD/saf3r/profile_models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eec68b77b0f0e53d","mcp_get_code":{"code_sha256":"eec68b77b0f0e53d"}},{"arxiv_id":"2511.00405","paper":"/paper/arxiv-2511-00405","title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"XMUDeepLIT/UME-R1","path":"src/data-download/llavahound_cp_download.py","file_url":"https://github.com/XMUDeepLIT/UME-R1/blob/HEAD/src/data-download/llavahound_cp_download.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":"726f29532082b33f","mcp_get_code":{"code_sha256":"726f29532082b33f"}},{"arxiv_id":"2410.05363","paper":"/paper/towards-world-simulator-crafting-physical","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/phygenbench","path":"PhyGenEval/single/vqascore.py","file_url":"https://github.com/opengvlab/phygenbench/blob/HEAD/PhyGenEval/single/vqascore.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f7dcf1d5ccde53d1","mcp_get_code":{"code_sha256":"f7dcf1d5ccde53d1"}},{"arxiv_id":"2409.16597","paper":"/paper/eventhallusion-diagnosing-event","title":"EventHallusion: Diagnosing Event Hallucinations in Video LLMs","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevetich/eventhallusion","path":"run_gpt4o.py","file_url":"https://github.com/stevetich/eventhallusion/blob/HEAD/run_gpt4o.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"057ae0e01af34e68","mcp_get_code":{"code_sha256":"057ae0e01af34e68"}},{"arxiv_id":"2406.11794","paper":"/paper/datacomp-lm-in-search-of-the-next-generation","title":"DataComp-LM: In search of the next generation of training sets for language models","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jieyuz2/taskmeanything","path":"tma/models/qa_model/videoqa_model.py","file_url":"https://github.com/jieyuz2/taskmeanything/blob/HEAD/tma/models/qa_model/videoqa_model.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":"beeff498aac20ff0","mcp_get_code":{"code_sha256":"beeff498aac20ff0"}},{"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":"data_loader/TextVR_dataset.py","file_url":"https://github.com/callsys/textvr/blob/HEAD/data_loader/TextVR_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"222cf68c3c788bd7","mcp_get_code":{"code_sha256":"222cf68c3c788bd7"}},{"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":"base/base_dataset.py","file_url":"https://github.com/callsys/textvr/blob/HEAD/base/base_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4dadb89db8c00cc2","mcp_get_code":{"code_sha256":"4dadb89db8c00cc2"}},{"arxiv_id":"2305.02519","paper":"/paper/anetqa-a-large-scale-benchmark-for-fine","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","date":"2023-05-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MILVLG/anetqa-code","path":"clipbert/sample_imgs_clipbert.py","file_url":"https://github.com/MILVLG/anetqa-code/blob/HEAD/clipbert/sample_imgs_clipbert.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":"4dadb89db8c00cc2","mcp_get_code":{"code_sha256":"4dadb89db8c00cc2"}},{"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":"base/base_dataset.py","file_url":"https://github.com/m-bain/frozen-in-time/blob/HEAD/base/base_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4dadb89db8c00cc2","mcp_get_code":{"code_sha256":"4dadb89db8c00cc2"}}]}