{"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/evaluate-exact-match-accuracy","entry":"evaluate_exact_match_accuracy","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":7,"n_papers_ran":7,"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":3,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":6,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"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":"2509.19003","paper":"/paper/arxiv-2509-19003","title":"Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"baaivision/CoS","path":"eval/vqa/score_with_prm.py","file_url":"https://github.com/baaivision/CoS/blob/HEAD/eval/vqa/score_with_prm.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e159a001bd4cbfaa","mcp_get_code":{"code_sha256":"e159a001bd4cbfaa"}},{"arxiv_id":"2412.05185","paper":"/paper/linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"e159a001bd4cbfaa","mcp_get_code":{"code_sha256":"e159a001bd4cbfaa"}},{"arxiv_id":"2412.03324","paper":"/paper/a-stitch-in-time-saves-nine-small-vlm-is-a","title":"A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"e159a001bd4cbfaa","mcp_get_code":{"code_sha256":"e159a001bd4cbfaa"}},{"arxiv_id":"2410.16261","paper":"/paper/mini-internvl-a-flexible-transfer-pocket","title":"Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"e159a001bd4cbfaa","mcp_get_code":{"code_sha256":"e159a001bd4cbfaa"}},{"arxiv_id":"2407.01976","paper":"/paper/a-bounding-box-is-worth-one-token","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","date":"2024-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"laytextllm/laytextllm","path":"eval/utils.py","file_url":"https://github.com/laytextllm/laytextllm/blob/HEAD/eval/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15713876351e02ec","mcp_get_code":{"code_sha256":"15713876351e02ec"}},{"arxiv_id":"2406.15334","paper":"/paper/multimodal-task-vectors-enable-many-shot","title":"Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning","date":"2024-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brandon3964/multimodal-task-vector","path":"eval_mm/evaluate_vqa.py","file_url":"https://github.com/brandon3964/multimodal-task-vector/blob/HEAD/eval_mm/evaluate_vqa.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e159a001bd4cbfaa","mcp_get_code":{"code_sha256":"e159a001bd4cbfaa"}},{"arxiv_id":"2405.11985","paper":"/paper/mtvqa-benchmarking-multilingual-text-centric","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bytedance/MTVQA","path":"scripts/acc.py","file_url":"https://github.com/bytedance/MTVQA/blob/HEAD/scripts/acc.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"152082cc5f135e87","mcp_get_code":{"code_sha256":"152082cc5f135e87"}}]}