{"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/extract-frames","entry":"extract_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":21,"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":20,"n_samples_ran":9,"n_samples_fingerprinted":2,"n_places":22,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":7,"unverified":11},"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":"2608.25158","paper":"/paper/arxiv-2608-25158","title":"FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"fuzzingbrain/FuzzingBrain-Bench","path":"fbbench/grading/signature.py","file_url":"https://github.com/fuzzingbrain/FuzzingBrain-Bench/blob/HEAD/fbbench/grading/signature.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c33b6a9ed87e0d6","mcp_get_code":{"code_sha256":"6c33b6a9ed87e0d6"}},{"arxiv_id":"2606.19184","paper":"/paper/arxiv-2606-19184","title":"When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"mapooon/SelfBlendedImages","path":"src/inference/preprocess.py","file_url":"https://github.com/mapooon/SelfBlendedImages/blob/HEAD/src/inference/preprocess.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3532e63049e34e2b","mcp_get_code":{"code_sha256":"3532e63049e34e2b"}},{"arxiv_id":"2602.07063","paper":"/paper/arxiv-2602-07063","title":"Video-based Music Generation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"serkansulun/emsync","path":"evaluation/alignment_utils.py","file_url":"https://github.com/serkansulun/emsync/blob/HEAD/evaluation/alignment_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"20906b6ed112a728","mcp_get_code":{"code_sha256":"20906b6ed112a728"}},{"arxiv_id":"2505.20292","paper":"/paper/opens2v-nexus-a-detailed-benchmark-and","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PKU-YuanGroup/OpenS2V-Nexus","path":"eval/get_naturalscore.py","file_url":"https://github.com/PKU-YuanGroup/OpenS2V-Nexus/blob/HEAD/eval/get_naturalscore.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":"7e425139d10d0ffa","mcp_get_code":{"code_sha256":"7e425139d10d0ffa"}},{"arxiv_id":"2505.03318","paper":"/paper/unified-multimodal-chain-of-thought-reward","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","date":"2025-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"codegoat24/unifiedreward","path":"UnifiedReward-Flex/flex_pair_rank_video_generation.py","file_url":"https://github.com/codegoat24/unifiedreward/blob/HEAD/UnifiedReward-Flex/flex_pair_rank_video_generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"37e4da1b39bbdfca","mcp_get_code":{"code_sha256":"37e4da1b39bbdfca"}},{"arxiv_id":"2504.13736","paper":"/paper/limitnet-progressive-content-aware-image","title":"LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networks","date":"2025-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ds-kiel/LimitNet","path":"process_video_frames.py","file_url":"https://github.com/ds-kiel/LimitNet/blob/HEAD/process_video_frames.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88fde3803da6f96e","mcp_get_code":{"code_sha256":"88fde3803da6f96e"}},{"arxiv_id":"2504.02259","paper":"/paper/re-thinking-temporal-search-for-long-form","title":"Re-thinking Temporal Search for Long-Form Video Understanding","date":"2025-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"longvideohaystack/tstar","path":"LVHaystackBench/val_qa_results.py","file_url":"https://github.com/longvideohaystack/tstar/blob/HEAD/LVHaystackBench/val_qa_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ffff1df97b161c31","mcp_get_code":{"code_sha256":"ffff1df97b161c31"}},{"arxiv_id":"2412.15206","paper":"/paper/autotrust-benchmarking-trustworthiness-in","title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving","date":"2024-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taco-group/autotrust","path":"Dolphins/inference.py","file_url":"https://github.com/taco-group/autotrust/blob/HEAD/Dolphins/inference.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":"e67e2f749d91037b","mcp_get_code":{"code_sha256":"e67e2f749d91037b"}},{"arxiv_id":"2412.09401","paper":"/paper/slam3r-real-time-dense-scene-reconstruction","title":"SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-vcl-3dv/slam3r","path":"slam3r/app/app_offline.py","file_url":"https://github.com/pku-vcl-3dv/slam3r/blob/HEAD/slam3r/app/app_offline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3f193cdd34292571","mcp_get_code":{"code_sha256":"3f193cdd34292571"}},{"arxiv_id":"2408.07009","paper":"/paper/imagen-3","title":"Imagen 3","date":"2024-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linzhiqiu/t2i_metrics","path":"t2v_metrics/models/vqascore_models/gemini_model.py","file_url":"https://github.com/linzhiqiu/t2i_metrics/blob/HEAD/t2v_metrics/models/vqascore_models/gemini_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":"46c6c4b62cdd0bdb","mcp_get_code":{"code_sha256":"46c6c4b62cdd0bdb"}},{"arxiv_id":"2408.07009","paper":"/paper/imagen-3","title":"Imagen 3","date":"2024-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"linzhiqiu/t2i_metrics","path":"t2v_metrics/models/vqascore_models/gpt4v_model.py","file_url":"https://github.com/linzhiqiu/t2i_metrics/blob/HEAD/t2v_metrics/models/vqascore_models/gpt4v_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0037c0a0dea955f5","mcp_get_code":{"code_sha256":"0037c0a0dea955f5"}},{"arxiv_id":"2407.05551","paper":"/paper/read-watch-and-scream-sound-generation-from","title":"Read, Watch and Scream! Sound Generation from Text and Video","date":"2024-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/rewas","path":"evaluation/av_align_score.py","file_url":"https://github.com/naver-ai/rewas/blob/HEAD/evaluation/av_align_score.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"49a15be06f03b885","mcp_get_code":{"code_sha256":"49a15be06f03b885"}},{"arxiv_id":"2402.11473","paper":"/paper/poisoned-forgery-face-towards-backdoor","title":"Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JWLiang007/PFF","path":"src/inference/preprocess.py","file_url":"https://github.com/JWLiang007/PFF/blob/HEAD/src/inference/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73f6f4be641ec794","mcp_get_code":{"code_sha256":"73f6f4be641ec794"}},{"arxiv_id":"2312.00438","paper":"/paper/dolphins-multimodal-language-model-for","title":"Dolphins: Multimodal Language Model for Driving","date":"2023-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"safolab-wisc/dolphins","path":"inference.py","file_url":"https://github.com/safolab-wisc/dolphins/blob/HEAD/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e67e2f749d91037b","mcp_get_code":{"code_sha256":"e67e2f749d91037b"}},{"arxiv_id":"2311.16093","paper":"/paper/have-we-built-machines-that-think-like-people","title":"Visual cognition in multimodal large language models","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lsbuschoff/multimodal","path":"eval/helpers.py","file_url":"https://github.com/lsbuschoff/multimodal/blob/HEAD/eval/helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4aeb5b30f23fc371","mcp_get_code":{"code_sha256":"4aeb5b30f23fc371"}},{"arxiv_id":"2311.04219","paper":"/paper/otterhd-a-high-resolution-multi-modality","title":"OtterHD: A High-Resolution Multi-modality Model","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luodian/otter","path":"pipeline/demos/interactive/otter_video.py","file_url":"https://github.com/luodian/otter/blob/HEAD/pipeline/demos/interactive/otter_video.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"029892ebb4321050","mcp_get_code":{"code_sha256":"029892ebb4321050"}},{"arxiv_id":"2309.16429","paper":"/paper/diverse-and-aligned-audio-to-video-generation","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guyyariv/TempoTokens","path":"av_align.py","file_url":"https://github.com/guyyariv/TempoTokens/blob/HEAD/av_align.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"20906b6ed112a728","mcp_get_code":{"code_sha256":"20906b6ed112a728"}},{"arxiv_id":"2306.09077","paper":"/paper/estimating-generic-3d-room-structures-from-2d-1","title":"Estimating Generic 3D Room Structures from 2D Annotations","date":"2023-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/cad-estate","path":"src/cad_estate/download_and_extract_frames.py","file_url":"https://github.com/google-research/cad-estate/blob/HEAD/src/cad_estate/download_and_extract_frames.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":"c49a409b1a2325dd","mcp_get_code":{"code_sha256":"c49a409b1a2325dd"}},{"arxiv_id":"2008.12603","paper":"/paper/a-realistic-fish-habitat-dataset-to-evaluate","title":"A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis","date":"2020-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alzayats/DeepFish","path":"scripts/predict_simple.py","file_url":"https://github.com/alzayats/DeepFish/blob/HEAD/scripts/predict_simple.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc0dbea81e13ab8f","mcp_get_code":{"code_sha256":"bc0dbea81e13ab8f"}},{"arxiv_id":"1911.00232","paper":"/paper/multi-moments-in-time-learning-and","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","date":"2019-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"metalbubble/moments_models","path":"utils.py","file_url":"https://github.com/metalbubble/moments_models/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":false,"code_sha256_prefix":"cec5115b0d865d23","mcp_get_code":{"code_sha256":"cec5115b0d865d23"}},{"arxiv_id":"1712.00080","paper":"/paper/super-slomo-high-quality-estimation-of","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","date":"2017-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"avinashpaliwal/Super-SloMo","path":"video_to_slomo.py","file_url":"https://github.com/avinashpaliwal/Super-SloMo/blob/HEAD/video_to_slomo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f220725a8c1b4e18","mcp_get_code":{"code_sha256":"f220725a8c1b4e18"}},{"arxiv_id":"1711.08496","paper":"/paper/temporal-relational-reasoning-in-videos","title":"Temporal Relational Reasoning in Videos","date":"2017-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhoubolei/TRN-pytorch","path":"test_video.py","file_url":"https://github.com/zhoubolei/TRN-pytorch/blob/HEAD/test_video.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c89e8de7543d2de8","mcp_get_code":{"code_sha256":"c89e8de7543d2de8"}}]}