{"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/arg-parser","entry":"arg_parser","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":5,"n_papers_ran":0,"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":0,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2410.09421","paper":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuweihao/MM-Vet","path":"mm-vet_evaluator.py","file_url":"https://github.com/yuweihao/MM-Vet/blob/HEAD/mm-vet_evaluator.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":"4edc6079065ecd0f","mcp_get_code":{"code_sha256":"4edc6079065ecd0f"}},{"arxiv_id":"2410.09421","paper":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuweihao/MM-Vet","path":"v2/mm-vet-v2_evaluator.py","file_url":"https://github.com/yuweihao/MM-Vet/blob/HEAD/v2/mm-vet-v2_evaluator.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":"436825beacc9df7d","mcp_get_code":{"code_sha256":"436825beacc9df7d"}},{"arxiv_id":"2408.00765","paper":"/paper/2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"4edc6079065ecd0f","mcp_get_code":{"code_sha256":"4edc6079065ecd0f"}},{"arxiv_id":"2408.00765","paper":"/paper/2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuweihao/mm-vet","path":"v2/mm-vet-v2_evaluator.py","file_url":"https://github.com/yuweihao/mm-vet/blob/HEAD/v2/mm-vet-v2_evaluator.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":"436825beacc9df7d","mcp_get_code":{"code_sha256":"436825beacc9df7d"}},{"arxiv_id":"2405.19716","paper":"/paper/enhancing-large-vision-language-models-with","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihedeng9/stic","path":"llava/eval/eval_mm_vet.py","file_url":"https://github.com/yihedeng9/stic/blob/HEAD/llava/eval/eval_mm_vet.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":"4edc6079065ecd0f","mcp_get_code":{"code_sha256":"4edc6079065ecd0f"}},{"arxiv_id":"2308.02490","paper":"/paper/mm-vet-evaluating-large-multimodal-models-for","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"4edc6079065ecd0f","mcp_get_code":{"code_sha256":"4edc6079065ecd0f"}},{"arxiv_id":"2025.findings-acl.1381","paper":null,"title":"arXiv:2025.findings-acl.1381","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"GrishKate/ProcrustesGPT","path":"run_ppl_eval.py","file_url":"https://github.com/GrishKate/ProcrustesGPT/blob/HEAD/run_ppl_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f42ea32c4cca816","mcp_get_code":{"code_sha256":"7f42ea32c4cca816"}}]}