{"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/is-correct","entry":"is_correct","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":12,"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":13,"n_samples_ran":8,"n_samples_fingerprinted":4,"n_places":13,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":5},"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":"2609.15180","paper":"/paper/arxiv-2609-15180","title":"RETHINKING CORRECTNESS FOR UNCERTAINTY ESTIMATION IN CLINICAL PREDICTION WITH VISION-LANGUAGE MODELS","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"JasonZuu/EHR-Correctness","path":"core/rouge.py","file_url":"https://github.com/JasonZuu/EHR-Correctness/blob/HEAD/core/rouge.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ee74428f57878f4","mcp_get_code":{"code_sha256":"7ee74428f57878f4"}},{"arxiv_id":"2607.19847","paper":"/paper/arxiv-2607-19847","title":"Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"lyrain2001/auto-fill","path":"inference/run_specialists.py","file_url":"https://github.com/lyrain2001/auto-fill/blob/HEAD/inference/run_specialists.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0f5bade67326da22","mcp_get_code":{"code_sha256":"0f5bade67326da22"}},{"arxiv_id":"2607.13124","paper":"/paper/arxiv-2607-13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"VisionOPD/Vision-OPD","path":"eval/cal_acc.py","file_url":"https://github.com/VisionOPD/Vision-OPD/blob/HEAD/eval/cal_acc.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":"3d659f15a1dfc162","mcp_get_code":{"code_sha256":"3d659f15a1dfc162"}},{"arxiv_id":"2511.08043","paper":"/paper/arxiv-2511-08043","title":"DYNAACT: Large Language Model Reasoning with Dynamic Action Spaces","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"zhaoxlpku/DynaAct","path":"utils.py","file_url":"https://github.com/zhaoxlpku/DynaAct/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f16a5b5b62e395e9","mcp_get_code":{"code_sha256":"f16a5b5b62e395e9"}},{"arxiv_id":"2504.15466","paper":"/paper/learning-adaptive-parallel-reasoning-with","title":"Learning Adaptive Parallel Reasoning with Language Models","date":"2025-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"parallel-reasoning/apr","path":"tinyrl/rollout/sos_utils.py","file_url":"https://github.com/parallel-reasoning/apr/blob/HEAD/tinyrl/rollout/sos_utils.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":"b26c2e702307ed07","mcp_get_code":{"code_sha256":"b26c2e702307ed07"}},{"arxiv_id":"2410.06101","paper":"/paper/coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Harry67Hu/CORY","path":"gsm8k_utils/gsm8k_utils.py","file_url":"https://github.com/Harry67Hu/CORY/blob/HEAD/gsm8k_utils/gsm8k_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e198da7bdc5637e3","mcp_get_code":{"code_sha256":"e198da7bdc5637e3"}},{"arxiv_id":"2406.07230","paper":"/paper/needle-in-a-multimodal-haystack","title":"Needle In A Multimodal Haystack","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/mm-niah","path":"val_mmniah.py","file_url":"https://github.com/opengvlab/mm-niah/blob/HEAD/val_mmniah.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cf772b6df6ac2f48","mcp_get_code":{"code_sha256":"cf772b6df6ac2f48"}},{"arxiv_id":"2402.14874","paper":"/paper/distillation-contrastive-decoding-improving","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pphuc25/distil-cd","path":"dcd_eval/src/chorse/utils.py","file_url":"https://github.com/pphuc25/distil-cd/blob/HEAD/dcd_eval/src/chorse/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"91b5a26d6a8fe4e5","mcp_get_code":{"code_sha256":"91b5a26d6a8fe4e5"}},{"arxiv_id":"2402.08219","paper":"/paper/bbox-adapter-lightweight-adapting-for-black","title":"BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haotiansun14/bbox-adapter","path":"utils/gsm8k_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/gsm8k_metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e1cdcbfba6b4853","mcp_get_code":{"code_sha256":"5e1cdcbfba6b4853"}},{"arxiv_id":"2402.08219","paper":"/paper/bbox-adapter-lightweight-adapting-for-black","title":"BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haotiansun14/bbox-adapter","path":"utils/scienceqa_metric.py","file_url":"https://github.com/haotiansun14/bbox-adapter/blob/HEAD/utils/scienceqa_metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ab7fd2652fb1b93","mcp_get_code":{"code_sha256":"1ab7fd2652fb1b93"}},{"arxiv_id":"2311.08803","paper":"/paper/strategyllm-large-language-models-as-strategy","title":"StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gao-xiao-bai/StrategyLLM","path":"source/dataset/utils.py","file_url":"https://github.com/gao-xiao-bai/StrategyLLM/blob/HEAD/source/dataset/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e122b45f16bbdc68","mcp_get_code":{"code_sha256":"e122b45f16bbdc68"}},{"arxiv_id":"2311.08711","paper":"/paper/plug-leveraging-pivot-language-in-cross","title":"PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ytyz1307zzh/plug","path":"src/evaluate/svamp/evaluate_svamp.py","file_url":"https://github.com/ytyz1307zzh/plug/blob/HEAD/src/evaluate/svamp/evaluate_svamp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8615bd4175ccc380","mcp_get_code":{"code_sha256":"8615bd4175ccc380"}},{"arxiv_id":"2301.13379","paper":"/paper/faithful-chain-of-thought-reasoning","title":"Faithful Chain-of-Thought Reasoning","date":"2023-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"veronica320/faithful-cot","path":"source/evaluate/evaluate_answer_acc.py","file_url":"https://github.com/veronica320/faithful-cot/blob/HEAD/source/evaluate/evaluate_answer_acc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26a0c594eb40f371","mcp_get_code":{"code_sha256":"26a0c594eb40f371"}}]}