{"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/first-true-indices","entry":"first_true_indices","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":4,"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":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":1},"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":"2602.13551","paper":"/paper/arxiv-2602-13551","title":"Small Reward Models via Backward Inference","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"yikee/FLIP","path":"open-instruct/open_instruct/model_utils.py","file_url":"https://github.com/yikee/FLIP/blob/HEAD/open-instruct/open_instruct/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2c0bb9254a04a7d","mcp_get_code":{"code_sha256":"b2c0bb9254a04a7d"}},{"arxiv_id":"2506.20629","paper":"/paper/plop-precise-lora-placement-for-efficient","title":"PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"soufiane001/plop","path":"sft/model_utils.py","file_url":"https://github.com/soufiane001/plop/blob/HEAD/sft/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2c0bb9254a04a7d","mcp_get_code":{"code_sha256":"b2c0bb9254a04a7d"}},{"arxiv_id":"2503.13538","paper":"/paper/from-demonstrations-to-rewards-alignment","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","date":"2025-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hong-Lab-UMN-ECE/IRLAlignment","path":"summarize_from_feedback_details/IRL_reward.py","file_url":"https://github.com/Hong-Lab-UMN-ECE/IRLAlignment/blob/HEAD/summarize_from_feedback_details/IRL_reward.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"579f0202bb30e003","mcp_get_code":{"code_sha256":"579f0202bb30e003"}},{"arxiv_id":"2410.04612","paper":"/paper/regressing-the-relative-future-efficient","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","date":"2024-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaolingao/refuel","path":"setting_two/anthropic_hh/refuel.py","file_url":"https://github.com/zhaolingao/refuel/blob/HEAD/setting_two/anthropic_hh/refuel.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":"579f0202bb30e003","mcp_get_code":{"code_sha256":"579f0202bb30e003"}},{"arxiv_id":"2404.16767","paper":"/paper/rebel-reinforcement-learning-via-regressing","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaolingao/rebel","path":"src/nectar/rebel.py","file_url":"https://github.com/zhaolingao/rebel/blob/HEAD/src/nectar/rebel.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":"579f0202bb30e003","mcp_get_code":{"code_sha256":"579f0202bb30e003"}},{"arxiv_id":"2403.17031","paper":"/paper/the-n-implementation-details-of-rlhf-with-ppo","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","date":"2024-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vwxyzjn/summarize_from_feedback_details","path":"summarize_from_feedback_details/dpo.py","file_url":"https://github.com/vwxyzjn/summarize_from_feedback_details/blob/HEAD/summarize_from_feedback_details/dpo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"579f0202bb30e003","mcp_get_code":{"code_sha256":"579f0202bb30e003"}}]}