{"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/flat-grad","entry":"flat_grad","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":8,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":3},"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":"2608.24460","paper":"/paper/arxiv-2608-24460","title":"Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"lyj20071013/Shortcut-Before-Circuit","path":"an_grad.py","file_url":"https://github.com/lyj20071013/Shortcut-Before-Circuit/blob/HEAD/an_grad.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":"235e26c1c810b459","mcp_get_code":{"code_sha256":"235e26c1c810b459"}},{"arxiv_id":"2605.31175","paper":"/paper/arxiv-2605-31175","title":"Towards Efficient LLMs Annealing with Principled Sample Selection","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"xuyj233/Direct","path":"direct/selector.py","file_url":"https://github.com/xuyj233/Direct/blob/HEAD/direct/selector.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa5be0d1f9a7483c","mcp_get_code":{"code_sha256":"fa5be0d1f9a7483c"}},{"arxiv_id":"2310.04373","paper":"/paper/confronting-reward-model-overoptimization","title":"Confronting Reward Model Overoptimization with Constrained RLHF","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tedmoskovitz/constrainedrl4lms","path":"rl4lms/algorithms/common/algo_utils.py","file_url":"https://github.com/tedmoskovitz/constrainedrl4lms/blob/HEAD/rl4lms/algorithms/common/algo_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"206123801663c69f","mcp_get_code":{"code_sha256":"206123801663c69f"}},{"arxiv_id":"2305.08844","paper":"/paper/rl4f-generating-natural-language-feedback","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","date":"2023-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/RL4LMs","path":"rl4lms/algorithms/common/algo_utils.py","file_url":"https://github.com/allenai/RL4LMs/blob/HEAD/rl4lms/algorithms/common/algo_utils.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":"206123801663c69f","mcp_get_code":{"code_sha256":"206123801663c69f"}},{"arxiv_id":"2302.11520","paper":"/paper/guiding-large-language-models-via-directional-1","title":"Guiding Large Language Models via Directional Stimulus Prompting","date":"2023-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leezekun/directional-stimulus-prompting","path":"rl4lms/algorithms/common/algo_utils.py","file_url":"https://github.com/leezekun/directional-stimulus-prompting/blob/HEAD/rl4lms/algorithms/common/algo_utils.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":"206123801663c69f","mcp_get_code":{"code_sha256":"206123801663c69f"}},{"arxiv_id":"2302.00808","paper":"/paper/average-constrained-policy-optimization","title":"ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/safety-starter-agents","path":"safe_rl/pg/trust_region.py","file_url":"https://github.com/openai/safety-starter-agents/blob/HEAD/safe_rl/pg/trust_region.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"331e2222a5374f81","mcp_get_code":{"code_sha256":"331e2222a5374f81"}},{"arxiv_id":"2008.06081","paper":"/paper/adversarial-training-and-provable-robustness","title":"Adversarial Training and Provable Robustness: A Tale of Two Objectives","date":"2020-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JmfanBU/AdvIBP","path":"IBP_Adv_Training/torch/flat_grad.py","file_url":"https://github.com/JmfanBU/AdvIBP/blob/HEAD/IBP_Adv_Training/torch/flat_grad.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f89badf903725d22","mcp_get_code":{"code_sha256":"f89badf903725d22"}},{"arxiv_id":"2006.14171","paper":"/paper/a-closer-look-at-invalid-action-masking-in","title":"A Closer Look at Invalid Action Masking in Policy Gradient Algorithms","date":"2020-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Stable-Baselines-Team/stable-baselines3-contrib","path":"sb3_contrib/common/utils.py","file_url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/blob/HEAD/sb3_contrib/common/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"530d3c238c8e12f0","mcp_get_code":{"code_sha256":"530d3c238c8e12f0"}}]}