{"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/normalize-score","entry":"normalize_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":1,"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":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2606.02800","paper":"/paper/arxiv-2606-02800","title":"Cosmos 3: Omnimodal World Models for Physical AI NVIDIA","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"nvidia/cosmos","path":"evaluation/cosmos3/reasoner/vlmevalkit/cosmos_eval/parse_score.py","file_url":"https://github.com/nvidia/cosmos/blob/HEAD/evaluation/cosmos3/reasoner/vlmevalkit/cosmos_eval/parse_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"31b64a89bbcc58d7","mcp_get_code":{"code_sha256":"31b64a89bbcc58d7"}},{"arxiv_id":"2603.18363","paper":"/paper/arxiv-2603-18363","title":"PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Chenruishuo/PowerFlow","path":"powerflow/reward_score_cw/joke_reward.py","file_url":"https://github.com/Chenruishuo/PowerFlow/blob/HEAD/powerflow/reward_score_cw/joke_reward.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b0e684eb3611367e","mcp_get_code":{"code_sha256":"b0e684eb3611367e"}},{"arxiv_id":"2506.07972","paper":"/paper/heurigym-an-agentic-benchmark-for-llm-crafted","title":"HeuriGym: An Agentic Benchmark for LLM-Crafted Heuristics in Combinatorial Optimization","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cornell-zhang/heurigym","path":"egraph_extraction/program/metric.py","file_url":"https://github.com/cornell-zhang/heurigym/blob/HEAD/egraph_extraction/program/metric.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":"0d1082ba17362e02","mcp_get_code":{"code_sha256":"0d1082ba17362e02"}},{"arxiv_id":"2411.00056","paper":null,"title":"arXiv:2411.00056","date":null,"month_inferred_from_arxiv_id":"2024-11","title_source":null,"repo":"DarianRodriguez/NegVerse","path":"negator/Evaluation/perplex_filter.py","file_url":"https://github.com/DarianRodriguez/NegVerse/blob/HEAD/negator/Evaluation/perplex_filter.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e531191aa453eafa","mcp_get_code":{"code_sha256":"e531191aa453eafa"}},{"arxiv_id":"2404.16019","paper":"/paper/the-prism-alignment-project-what","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hannahkirk/prism-alignment","path":"src/data_analysis/ranking.py","file_url":"https://github.com/hannahkirk/prism-alignment/blob/HEAD/src/data_analysis/ranking.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e194f3f5f97031fd","mcp_get_code":{"code_sha256":"e194f3f5f97031fd"}},{"arxiv_id":"2304.10466","paper":"/paper/efficient-deep-reinforcement-learning","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","date":"2023-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evgenii-nikishin/rl_with_resets","path":"discrete_control/eval_run_experiment.py","file_url":"https://github.com/evgenii-nikishin/rl_with_resets/blob/HEAD/discrete_control/eval_run_experiment.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71d1b50edc65f329","mcp_get_code":{"code_sha256":"71d1b50edc65f329"}}]}