{"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/generate-score","entry":"generate_score","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":6,"n_papers_ran":2,"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":1,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"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":"2502.16182","paper":"/paper/ipo-your-language-model-is-secretly-a","title":"IPO: Your Language Model is Secretly a Preference Classifier","date":"2025-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shivank21/Implicit_Preference_Optimization","path":"Preference_Comparison/RM_Bench/self_reward_gpt.py","file_url":"https://github.com/shivank21/Implicit_Preference_Optimization/blob/HEAD/Preference_Comparison/RM_Bench/self_reward_gpt.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":"25d1aecfb6d7b2f5","mcp_get_code":{"code_sha256":"25d1aecfb6d7b2f5"}},{"arxiv_id":"2410.18693","paper":"/paper/unleashing-reasoning-capability-of-llms-via","title":"Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyding1/scalequest","path":"src/data_generation/question_filtering/generate_difficulty_score.py","file_url":"https://github.com/yyding1/scalequest/blob/HEAD/src/data_generation/question_filtering/generate_difficulty_score.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":"686a5f1d92047af3","mcp_get_code":{"code_sha256":"686a5f1d92047af3"}},{"arxiv_id":"2410.10626","paper":"/paper/efficiently-democratizing-medical-llms-for-50","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/apollomoe","path":"src/sft/train_gemma2_resume_val.py","file_url":"https://github.com/freedomintelligence/apollomoe/blob/HEAD/src/sft/train_gemma2_resume_val.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":"59d609caa2ec71b8","mcp_get_code":{"code_sha256":"59d609caa2ec71b8"}},{"arxiv_id":"2305.09235","paper":"/paper/synthetic-data-real-errors-how-not-to-publish","title":"Synthetic data, real errors: how (not) to publish and use synthetic data","date":"2023-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bvanbreugel/deep_generative_ensemble","path":"DGE_utils.py","file_url":"https://github.com/bvanbreugel/deep_generative_ensemble/blob/HEAD/DGE_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39ebf38d74f7ab03","mcp_get_code":{"code_sha256":"39ebf38d74f7ab03"}},{"arxiv_id":"2301.12260","paper":"/paper/temporai-facilitating-machine-learning","title":"TemporAI: Facilitating Machine Learning Innovation in Time Domain Tasks for Medicine","date":"2023-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vanderschaarlab/temporai","path":"src/tempor/benchmarks/utils.py","file_url":"https://github.com/vanderschaarlab/temporai/blob/HEAD/src/tempor/benchmarks/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":"bac19d1fcc07293e","mcp_get_code":{"code_sha256":"bac19d1fcc07293e"}},{"arxiv_id":"ijcai2025_1059","paper":null,"title":"arXiv:ijcai2025_1059","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kracr/moral-decision-dataset","path":"code/evaluator/mae.py","file_url":"https://github.com/kracr/moral-decision-dataset/blob/HEAD/code/evaluator/mae.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":"ff9fe39a4bb881d7","mcp_get_code":{"code_sha256":"ff9fe39a4bb881d7"}}]}