{"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-yes-no","entry":"extract_yes_no","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":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":6,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":4},"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":"2609.01224","paper":"/paper/arxiv-2609-01224","title":"S$^2$Prune: Spatially Structured Visual Token Pruning for Multimodal Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"yuanyuanjia71-spec/S2Prune","path":"s2prune/metrics.py","file_url":"https://github.com/yuanyuanjia71-spec/S2Prune/blob/HEAD/s2prune/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d83d989499ab54f2","mcp_get_code":{"code_sha256":"d83d989499ab54f2"}},{"arxiv_id":"2605.10896","paper":"/paper/arxiv-2605-10896","title":"V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"genwro-ai/V4FinBench","path":"src/v4finbench/llama/inference.py","file_url":"https://github.com/genwro-ai/V4FinBench/blob/HEAD/src/v4finbench/llama/inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06b7e6ed36a9edd0","mcp_get_code":{"code_sha256":"06b7e6ed36a9edd0"}},{"arxiv_id":"2412.13871","paper":"/paper/llava-uhd-v2-an-mllm-integrating-high","title":"LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/llava-uhd","path":"VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.py","file_url":"https://github.com/thunlp/llava-uhd/blob/HEAD/VLMEvalKit/vlmeval/vlm/llava_qwen2_uhd_v3.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":"fb3f8b5f16ed11cb","mcp_get_code":{"code_sha256":"fb3f8b5f16ed11cb"}},{"arxiv_id":"2410.18336","paper":"/paper/assessing-the-creativity-of-llms-in-proposing","title":"Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junyiye/creativemath","path":"src/utils.py","file_url":"https://github.com/junyiye/creativemath/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67f0150cdc2e0c55","mcp_get_code":{"code_sha256":"67f0150cdc2e0c55"}},{"arxiv_id":"2409.06851","paper":"/paper/lime-m-less-is-more-for-evaluation-of-mllms","title":"LIME: Less Is More for MLLM Evaluation","date":"2024-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kangreen0210/lime","path":"lmms_eval/evaluate_demo.py","file_url":"https://github.com/kangreen0210/lime/blob/HEAD/lmms_eval/evaluate_demo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"328b134fb56d3c6e","mcp_get_code":{"code_sha256":"328b134fb56d3c6e"}},{"arxiv_id":"2407.17379","paper":"/paper/mmra-a-benchmark-for-multi-granularity-multi","title":"MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models","date":"2024-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wusiwei0410/mmra","path":"evaluate/evaluate_demo.py","file_url":"https://github.com/wusiwei0410/mmra/blob/HEAD/evaluate/evaluate_demo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"328b134fb56d3c6e","mcp_get_code":{"code_sha256":"328b134fb56d3c6e"}},{"arxiv_id":"openreview_bgtUrDtKjF","paper":null,"title":"arXiv:openreview_bgtUrDtKjF","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LAW1223/AlignVid","path":"evaluation/vqa_based/qwen.py","file_url":"https://github.com/LAW1223/AlignVid/blob/HEAD/evaluation/vqa_based/qwen.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":"73d3c93fa23c80ac","mcp_get_code":{"code_sha256":"73d3c93fa23c80ac"}}]}