{"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-answer-from-output","entry":"extract_answer_from_output","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":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":3,"n_samples_ran":3,"n_samples_fingerprinted":2,"n_places":7,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":0,"unverified":0},"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":"2509.16598","paper":"/paper/arxiv-2509-16598","title":"PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"hoeng4/PruneCD","path":"2_benchmark/1_tfqa_gen.py","file_url":"https://github.com/hoeng4/PruneCD/blob/HEAD/2_benchmark/1_tfqa_gen.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":"96fe095fcc6b821a","mcp_get_code":{"code_sha256":"96fe095fcc6b821a"}},{"arxiv_id":"2504.04635","paper":null,"title":"arXiv:2504.04635","date":null,"month_inferred_from_arxiv_id":"2025-04","title_source":null,"repo":"patqdasilva/steering-off-course","path":"DoLa/factor_eval.py","file_url":"https://github.com/patqdasilva/steering-off-course/blob/HEAD/DoLa/factor_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96fe095fcc6b821a","mcp_get_code":{"code_sha256":"96fe095fcc6b821a"}},{"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96fe095fcc6b821a","mcp_get_code":{"code_sha256":"96fe095fcc6b821a"}},{"arxiv_id":"2403.01548","paper":"/paper/in-context-sharpness-as-alerts-an-inner","title":"In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation","date":"2024-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkust-nlp/activation_decoding","path":"eval_knowledge_qa.py","file_url":"https://github.com/hkust-nlp/activation_decoding/blob/HEAD/eval_knowledge_qa.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":"11575f75b626d3cb","mcp_get_code":{"code_sha256":"11575f75b626d3cb"}},{"arxiv_id":"2401.13986","paper":"/paper/towards-consistent-natural-language","title":"Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning","date":"2024-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yandachen/explanation-consistency-finetuning","path":"src/expl_generation.py","file_url":"https://github.com/yandachen/explanation-consistency-finetuning/blob/HEAD/src/expl_generation.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":"1a39aa47d58da56a","mcp_get_code":{"code_sha256":"1a39aa47d58da56a"}},{"arxiv_id":"2401.05930","paper":"/paper/sh2-self-highlighted-hesitation-helps-you","title":"SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully","date":"2024-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"0-kaikai-0/sh2","path":"factor_eval.py","file_url":"https://github.com/0-kaikai-0/sh2/blob/HEAD/factor_eval.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":"96fe095fcc6b821a","mcp_get_code":{"code_sha256":"96fe095fcc6b821a"}},{"arxiv_id":"2309.03883","paper":"/paper/dola-decoding-by-contrasting-layers-improves","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","date":"2023-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"voidism/DoLa","path":"factor_eval.py","file_url":"https://github.com/voidism/DoLa/blob/HEAD/factor_eval.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":"96fe095fcc6b821a","mcp_get_code":{"code_sha256":"96fe095fcc6b821a"}}]}