{"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/get-file-names","entry":"get_file_names","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":9,"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":6,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":2,"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":"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7d2672b31e9aa80e","mcp_get_code":{"code_sha256":"7d2672b31e9aa80e"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a907f50fb10a0162","mcp_get_code":{"code_sha256":"a907f50fb10a0162"}},{"arxiv_id":"2410.08964","paper":"/paper/language-imbalance-driven-rewarding-for","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","path":"utils/utils.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/utils/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"11e86e115ad397d4","mcp_get_code":{"code_sha256":"11e86e115ad397d4"}},{"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":"data_curation_pipeline/gpt_double_check.py","file_url":"https://github.com/kangreen0210/lime/blob/HEAD/data_curation_pipeline/gpt_double_check.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d6ed56746b1c0d56","mcp_get_code":{"code_sha256":"d6ed56746b1c0d56"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7d2672b31e9aa80e","mcp_get_code":{"code_sha256":"7d2672b31e9aa80e"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a907f50fb10a0162","mcp_get_code":{"code_sha256":"a907f50fb10a0162"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7d2672b31e9aa80e","mcp_get_code":{"code_sha256":"7d2672b31e9aa80e"}},{"arxiv_id":"2308.12143","paper":"/paper/a-probabilistic-fluctuation-based-membership","title":"A Probabilistic Fluctuation based Membership Inference Attack for Diffusion Models","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wjfu99/mia-gen","path":"diffusion_models/training_general.py","file_url":"https://github.com/wjfu99/mia-gen/blob/HEAD/diffusion_models/training_general.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b165ff8b04a2afe3","mcp_get_code":{"code_sha256":"b165ff8b04a2afe3"}},{"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":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"7d2672b31e9aa80e","mcp_get_code":{"code_sha256":"7d2672b31e9aa80e"}},{"arxiv_id":"2110.14000","paper":"/paper/towards-hyperparameter-free-policy-selection","title":"Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning","date":"2021-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jasonzhang929/BVFT_empirical_experiments","path":"run_exp.py","file_url":"https://github.com/jasonzhang929/BVFT_empirical_experiments/blob/HEAD/run_exp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc49e9f62cb45a02","mcp_get_code":{"code_sha256":"dc49e9f62cb45a02"}},{"arxiv_id":"2008.04990","paper":"/paper/batch-value-function-approximation-with-only","title":"Batch Value-function Approximation with Only Realizability","date":"2020-08-11","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":"dc49e9f62cb45a02","mcp_get_code":{"code_sha256":"dc49e9f62cb45a02"}}]}