{"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/compute-reward-modeling-metrics","entry":"compute_reward_modeling_metrics","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":5,"n_papers_ran":5,"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":2,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"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":"2501.09620","paper":"/paper/beyond-reward-hacking-causal-rewards-for","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","date":"2025-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tatsu-lab/alpaca_farm","path":"src/alpaca_farm/reward_modeling_trainer.py","file_url":"https://github.com/tatsu-lab/alpaca_farm/blob/HEAD/src/alpaca_farm/reward_modeling_trainer.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":"cca45bb9a111ab77","mcp_get_code":{"code_sha256":"cca45bb9a111ab77"}},{"arxiv_id":"2403.09472","paper":"/paper/easy-to-hard-generalization-scalable","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"edward-sun/easy-to-hard","path":"train_rl_dpo.py","file_url":"https://github.com/edward-sun/easy-to-hard/blob/HEAD/train_rl_dpo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"d4969006e20577f6","mcp_get_code":{"code_sha256":"d4969006e20577f6"}},{"arxiv_id":"2402.05133","paper":"/paper/personalized-language-modeling-from","title":"Personalized Language Modeling from Personalized Human Feedback","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"humainlab/personalized_rlhf","path":"evaluate/alpaca_farm/reward_modeling_trainer.py","file_url":"https://github.com/humainlab/personalized_rlhf/blob/HEAD/evaluate/alpaca_farm/reward_modeling_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cca45bb9a111ab77","mcp_get_code":{"code_sha256":"cca45bb9a111ab77"}},{"arxiv_id":"2310.11564","paper":"/paper/personalized-soups-personalized-large","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joeljang/rlphf","path":"gpt4_evaluate/alpaca_farm/reward_modeling_trainer.py","file_url":"https://github.com/joeljang/rlphf/blob/HEAD/gpt4_evaluate/alpaca_farm/reward_modeling_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cca45bb9a111ab77","mcp_get_code":{"code_sha256":"cca45bb9a111ab77"}},{"arxiv_id":"2309.09055","paper":"/paper/exploring-the-impact-of-low-rank-adaptation","title":"Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF","date":"2023-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simengsun/alpaca_farm_lora","path":"alpaca_farm/src/alpaca_farm/reward_modeling_trainer.py","file_url":"https://github.com/simengsun/alpaca_farm_lora/blob/HEAD/alpaca_farm/src/alpaca_farm/reward_modeling_trainer.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":"cca45bb9a111ab77","mcp_get_code":{"code_sha256":"cca45bb9a111ab77"}}]}