{"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-advantage","entry":"compute_advantage","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":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":5,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2605.24331","paper":"/paper/arxiv-2605-24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"zhyzmath/CurveRL","path":"recipe/sppo/sppo_ray_trainer.py","file_url":"https://github.com/zhyzmath/CurveRL/blob/HEAD/recipe/sppo/sppo_ray_trainer.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":"480d8f57402fc9cf","mcp_get_code":{"code_sha256":"480d8f57402fc9cf"}},{"arxiv_id":"2402.12621","paper":"/paper/reflect-rl-two-player-online-rl-fine-tuning","title":"Reflect-RL: Two-Player Online RL Fine-Tuning for LMs","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhourunlong/Reflect-RL","path":"trainers/ppotrainer.py","file_url":"https://github.com/zhourunlong/Reflect-RL/blob/HEAD/trainers/ppotrainer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39a497facb3b1a48","mcp_get_code":{"code_sha256":"39a497facb3b1a48"}},{"arxiv_id":"2308.07272","paper":"/paper/dialogue-for-prompting-a-policy-gradient","title":"Dialogue for Prompting: a Policy-Gradient-Based Discrete Prompt Generation for Few-shot Learning","date":"2023-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czx-li/DP2O","path":"Utils.py","file_url":"https://github.com/czx-li/DP2O/blob/HEAD/Utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f89d232490cc2fad","mcp_get_code":{"code_sha256":"f89d232490cc2fad"}},{"arxiv_id":"2209.13508","paper":"/paper/motion-transformer-with-global-intention","title":"Motion Transformer with Global Intention Localization and Local Movement Refinement","date":"2022-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nikeke19/safe-mult-rl","path":"models/common/buffers.py","file_url":"https://github.com/nikeke19/safe-mult-rl/blob/HEAD/models/common/buffers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e1bebfaa850ab645","mcp_get_code":{"code_sha256":"e1bebfaa850ab645"}},{"arxiv_id":"1606.03476","paper":"/paper/generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KAIST-AILab/deeprl_practice_colab","path":"day3/gail/policyopt/rl.py","file_url":"https://github.com/KAIST-AILab/deeprl_practice_colab/blob/HEAD/day3/gail/policyopt/rl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12a65e5d7d9e912d","mcp_get_code":{"code_sha256":"12a65e5d7d9e912d"}}]}