{"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/scheduler-step","entry":"scheduler_step","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":0,"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":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2605.11974","paper":"/paper/arxiv-2605-11974","title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Hyalinesky/DGAO","path":"trl/models/modeling_sd_base.py","file_url":"https://github.com/Hyalinesky/DGAO/blob/HEAD/trl/models/modeling_sd_base.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":"2ad63a9a0bae9859","mcp_get_code":{"code_sha256":"2ad63a9a0bae9859"}},{"arxiv_id":"2509.12521","paper":"/paper/arxiv-2509-12521","title":"Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Yifan-Lan/Phi","path":"trl/models/modeling_sd_base.py","file_url":"https://github.com/Yifan-Lan/Phi/blob/HEAD/trl/models/modeling_sd_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31a4e1994101bdd7","mcp_get_code":{"code_sha256":"31a4e1994101bdd7"}},{"arxiv_id":"2501.06911","paper":"/paper/risk-averse-finetuning-of-large-language","title":"Risk-Averse Finetuning of Large Language Models","date":"2025-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sapanachaudhary/ra-rlhf","path":"trl/models/modeling_sd_base.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/trl/models/modeling_sd_base.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":"55a252ad77e7e399","mcp_get_code":{"code_sha256":"55a252ad77e7e399"}},{"arxiv_id":"2410.06101","paper":"/paper/coevolving-with-the-other-you-fine-tuning-llm","title":"Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Harry67Hu/CORY","path":"trl/models/modeling_sd_base.py","file_url":"https://github.com/Harry67Hu/CORY/blob/HEAD/trl/models/modeling_sd_base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59046fe10dd792f4","mcp_get_code":{"code_sha256":"59046fe10dd792f4"}},{"arxiv_id":"2305.18290","paper":"/paper/direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"padlex/trl","path":"trl/models/modeling_sd_base.py","file_url":"https://github.com/padlex/trl/blob/HEAD/trl/models/modeling_sd_base.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":"ade247252fd2d3db","mcp_get_code":{"code_sha256":"ade247252fd2d3db"}}]}