{"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/maybe-apply-chat-template","entry":"maybe_apply_chat_template","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":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":4,"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":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":"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/data_utils.py","file_url":"https://github.com/Hyalinesky/DGAO/blob/HEAD/trl/data_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":"2d343f4f4297efa7","mcp_get_code":{"code_sha256":"2d343f4f4297efa7"}},{"arxiv_id":"2604.07035","paper":"/paper/arxiv-2604-07035","title":"Unified Deployment-Aware Evaluation of Open Reasoning Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"mkboch/UDAE","path":"prompts/builder.py","file_url":"https://github.com/mkboch/UDAE/blob/HEAD/prompts/builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e55180874babf570","mcp_get_code":{"code_sha256":"e55180874babf570"}},{"arxiv_id":"2509.13760","paper":"/paper/arxiv-2509-13760","title":"Iterative Prompt Refinement for Safer Text-to-Image Generation","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ku-dmlab/IPR","path":"trl/data_utils.py","file_url":"https://github.com/ku-dmlab/IPR/blob/HEAD/trl/data_utils.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":"c695ba9ac4cc3b93","mcp_get_code":{"code_sha256":"c695ba9ac4cc3b93"}},{"arxiv_id":"2505.15656","paper":"/paper/be-careful-when-fine-tuning-on-open-source","title":"Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen!","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/backdoor-data-extraction","path":"train/trl/data_utils.py","file_url":"https://github.com/thu-coai/backdoor-data-extraction/blob/HEAD/train/trl/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c695ba9ac4cc3b93","mcp_get_code":{"code_sha256":"c695ba9ac4cc3b93"}},{"arxiv_id":"2505.09655","paper":"/paper/dra-grpo-exploring-diversity-aware-reward","title":"DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models","date":"2025-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiwenc1/dra-grpo","path":"src/open_r1/trl/data_utils.py","file_url":"https://github.com/xiwenc1/dra-grpo/blob/HEAD/src/open_r1/trl/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c695ba9ac4cc3b93","mcp_get_code":{"code_sha256":"c695ba9ac4cc3b93"}},{"arxiv_id":"2504.20157","paper":"/paper/toward-evaluative-thinking-meta-policy","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","date":"2025-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minnesotanlp/mpo","path":"trl/data_utils.py","file_url":"https://github.com/minnesotanlp/mpo/blob/HEAD/trl/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"4c2c416f1561edde","mcp_get_code":{"code_sha256":"4c2c416f1561edde"}}]}