{"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/chat-mt","entry":"chat_mt","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":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":2,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2510.11190","paper":"/paper/arxiv-2510-11190","title":"FlexAC : Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"ylhz/FlexAC","path":"vlmeval/inference_mt.py","file_url":"https://github.com/ylhz/FlexAC/blob/HEAD/vlmeval/inference_mt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c96f86fc774ee85d","mcp_get_code":{"code_sha256":"c96f86fc774ee85d"}},{"arxiv_id":"2507.06167","paper":"/paper/skywork-r1v3-technical-report","title":"Skywork-R1V3 Technical Report","date":"2025-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seephys/seephys-project","path":"vlmeval/inference_mt.py","file_url":"https://github.com/seephys/seephys-project/blob/HEAD/vlmeval/inference_mt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c96f86fc774ee85d","mcp_get_code":{"code_sha256":"c96f86fc774ee85d"}},{"arxiv_id":"2507.01949","paper":"/paper/kwai-keye-vl-technical-report","title":"Kwai Keye-VL Technical Report","date":"2025-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kwai-keye/keye","path":"evaluation/KC-MMBench/vlmeval/inference_mt.py","file_url":"https://github.com/kwai-keye/keye/blob/HEAD/evaluation/KC-MMBench/vlmeval/inference_mt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c96f86fc774ee85d","mcp_get_code":{"code_sha256":"c96f86fc774ee85d"}},{"arxiv_id":"2505.17163","paper":"/paper/ocr-reasoning-benchmark-unveiling-the-true","title":"OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning","date":"2025-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SCUT-DLVCLab/OCR-Reasoning","path":"vlmeval/inference_mt.py","file_url":"https://github.com/SCUT-DLVCLab/OCR-Reasoning/blob/HEAD/vlmeval/inference_mt.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":"c96f86fc774ee85d","mcp_get_code":{"code_sha256":"c96f86fc774ee85d"}},{"arxiv_id":"2505.15929","paper":"/paper/phyx-does-your-model-have-the-wits-for","title":"PhyX: Does Your Model Have the \"Wits\" for Physical Reasoning?","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NastyMarcus/PhyX","path":"vlmeval/inference_mt.py","file_url":"https://github.com/NastyMarcus/PhyX/blob/HEAD/vlmeval/inference_mt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c96f86fc774ee85d","mcp_get_code":{"code_sha256":"c96f86fc774ee85d"}},{"arxiv_id":"2504.10465","paper":"/paper/pixel-sail-single-transformer-for-pixel","title":"Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding","date":"2025-04-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"magic-research/Sa2VA","path":"sa2va_eval/vlmeval/inference_mt.py","file_url":"https://github.com/magic-research/Sa2VA/blob/HEAD/sa2va_eval/vlmeval/inference_mt.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":"d39e00e95c8c76b0","mcp_get_code":{"code_sha256":"d39e00e95c8c76b0"}},{"arxiv_id":"2408.15556","paper":"/paper/divide-conquer-and-combine-a-training-free","title":"Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DreamMr/HR-Bench","path":"hrbench/vlmeval/inference_mt.py","file_url":"https://github.com/DreamMr/HR-Bench/blob/HEAD/hrbench/vlmeval/inference_mt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d39e00e95c8c76b0","mcp_get_code":{"code_sha256":"d39e00e95c8c76b0"}}]}