{"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/parse-with-config","entry":"parse_with_config","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":12,"n_papers_ran":3,"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":4,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2507.06072","paper":"/paper/mcam-multimodal-causal-analysis-model-for-ego","title":"MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding","date":"2025-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SixCorePeach/MCAM","path":"configs/config.py","file_url":"https://github.com/SixCorePeach/MCAM/blob/HEAD/configs/config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e81145412a40e36","mcp_get_code":{"code_sha256":"3e81145412a40e36"}},{"arxiv_id":"2412.11959","paper":"/paper/gramian-multimodal-representation-learning","title":"Gramian Multimodal Representation Learning and Alignment","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ispamm/GRAM","path":"utils/args.py","file_url":"https://github.com/ispamm/GRAM/blob/HEAD/utils/args.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15b65a6a6e8fd954","mcp_get_code":{"code_sha256":"15b65a6a6e8fd954"}},{"arxiv_id":"2409.19865","paper":"/paper/tokenbinder-text-video-retrieval-with-one-to","title":"TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bingqingzhang/TokenBinder","path":"src/configs/config.py","file_url":"https://github.com/bingqingzhang/TokenBinder/blob/HEAD/src/configs/config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e81145412a40e36","mcp_get_code":{"code_sha256":"3e81145412a40e36"}},{"arxiv_id":"2404.10241","paper":"/paper/vision-and-language-navigation-via-causal","title":"Vision-and-Language Navigation via Causal Learning","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crystalsixone/vln-goat","path":"pretrain_src/parser.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/pretrain_src/parser.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":"f46bad6811c75514","mcp_get_code":{"code_sha256":"f46bad6811c75514"}},{"arxiv_id":"2307.12907","paper":"/paper/gridmm-grid-memory-map-for-vision-and","title":"GridMM: Grid Memory Map for Vision-and-Language Navigation","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MrZihan/GridMM","path":"pretrain_src/parser.py","file_url":"https://github.com/MrZihan/GridMM/blob/HEAD/pretrain_src/parser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f46bad6811c75514","mcp_get_code":{"code_sha256":"f46bad6811c75514"}},{"arxiv_id":"2305.18500","paper":"/paper/vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TXH-mercury/VAST","path":"utils/args.py","file_url":"https://github.com/TXH-mercury/VAST/blob/HEAD/utils/args.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15b65a6a6e8fd954","mcp_get_code":{"code_sha256":"15b65a6a6e8fd954"}},{"arxiv_id":"2303.15616","paper":"/paper/fine-grained-audible-video-description","title":"Fine-grained Audible Video Description","date":"2023-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenNLPLab/FAVDBench","path":"AVLFormer/src/configs/config.py","file_url":"https://github.com/OpenNLPLab/FAVDBench/blob/HEAD/AVLFormer/src/configs/config.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":"9bf9ef86f23d7a76","mcp_get_code":{"code_sha256":"9bf9ef86f23d7a76"}},{"arxiv_id":"2303.04995","paper":"/paper/text-visual-prompting-for-efficient-2d","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","date":"2023-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intel/TVP","path":"src/configs/config.py","file_url":"https://github.com/intel/TVP/blob/HEAD/src/configs/config.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":"3e81145412a40e36","mcp_get_code":{"code_sha256":"3e81145412a40e36"}},{"arxiv_id":"2206.03428","paper":"/paper/revealing-single-frame-bias-for-video-and","title":"Revealing Single Frame Bias for Video-and-Language Learning","date":"2022-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jayleicn/ClipBERT","path":"src/configs/config.py","file_url":"https://github.com/jayleicn/ClipBERT/blob/HEAD/src/configs/config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e81145412a40e36","mcp_get_code":{"code_sha256":"3e81145412a40e36"}},{"arxiv_id":"2112.05375","paper":"/paper/rethinking-the-two-stage-framework-for","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","date":"2021-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kellyiss/situformer","path":"util/misc.py","file_url":"https://github.com/kellyiss/situformer/blob/HEAD/util/misc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f46bad6811c75514","mcp_get_code":{"code_sha256":"f46bad6811c75514"}},{"arxiv_id":"Lin_SwinBERT_End-to-End_Transformers_With_Sparse_Attention_for_Video_Captioning_CVPR_2022_paper","paper":null,"title":"arXiv:Lin_SwinBERT_End-to-End_Transformers_With_Sparse_Attention_for_Video_Captioning_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"microsoft/SwinBERT","path":"src/configs/config.py","file_url":"https://github.com/microsoft/SwinBERT/blob/HEAD/src/configs/config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e81145412a40e36","mcp_get_code":{"code_sha256":"3e81145412a40e36"}},{"arxiv_id":"Li_Align_and_Prompt_Video-and-Language_Pre-Training_With_Entity_Prompts_CVPR_2022_paper","paper":null,"title":"arXiv:Li_Align_and_Prompt_Video-and-Language_Pre-Training_With_Entity_Prompts_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"salesforce/ALPRO","path":"src/configs/config.py","file_url":"https://github.com/salesforce/ALPRO/blob/HEAD/src/configs/config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"3e81145412a40e36","mcp_get_code":{"code_sha256":"3e81145412a40e36"}}]}