{"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/is-openai-format","entry":"is_openai_format","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":13,"n_papers_ran":11,"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":3,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":2},"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":"2606.09124","paper":"/paper/arxiv-2606-09124","title":"A Regret Minimization Framework on Preference Learning in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"YSLIU627/Regularized-Preference-Optimization","path":"alignment-handbook/src/alignment/data.py","file_url":"https://github.com/YSLIU627/Regularized-Preference-Optimization/blob/HEAD/alignment-handbook/src/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2604.20051","paper":"/paper/arxiv-2604-20051","title":"Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"HCY123902/POP","path":"training/data_utils.py","file_url":"https://github.com/HCY123902/POP/blob/HEAD/training/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f3bf55f62a71b365","mcp_get_code":{"code_sha256":"f3bf55f62a71b365"}},{"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/utils.py","file_url":"https://github.com/soufiane001/plop/blob/HEAD/sft/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0cd2fea90cee405","mcp_get_code":{"code_sha256":"e0cd2fea90cee405"}},{"arxiv_id":"2503.12524","paper":"/paper/exaone-deep-reasoning-enhanced-language","title":"EXAONE Deep: Reasoning Enhanced Language Models","date":"2025-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tengxiao1/simper","path":"alignment/data.py","file_url":"https://github.com/tengxiao1/simper/blob/HEAD/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2502.18274","paper":"/paper/citrus-leveraging-expert-cognitive-pathways","title":"Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support","date":"2025-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jdh-algo/Citrus","path":"model_train/alignment/data.py","file_url":"https://github.com/jdh-algo/Citrus/blob/HEAD/model_train/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2412.14516","paper":"/paper/cal-dpo-calibrated-direct-preference","title":"Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment","date":"2024-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tengxiao1/cal-dpo","path":"scripts/run_dpo.py","file_url":"https://github.com/tengxiao1/cal-dpo/blob/HEAD/scripts/run_dpo.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2410.18027","paper":"/paper/cross-lingual-transfer-of-reward-models-in","title":"Cross-lingual Transfer of Reward Models in Multilingual Alignment","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iq-kaist/rm-lingual-transfer","path":"src/utils.py","file_url":"https://github.com/iq-kaist/rm-lingual-transfer/blob/HEAD/src/utils.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2410.10148","paper":"/paper/a-dpo-adaptive-reward-margin-is-what-direct","title":"$α$-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junkangwu/alpha-dpo","path":"alignment/data.py","file_url":"https://github.com/junkangwu/alpha-dpo/blob/HEAD/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2409.03444","paper":"/paper/fine-tuning-large-language-models-for-domain-1","title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","date":"2024-09-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lamm-mit/llm-finetuning","path":"alignment-handbook/src/alignment/data.py","file_url":"https://github.com/lamm-mit/llm-finetuning/blob/HEAD/alignment-handbook/src/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2407.09014","paper":"/paper/compact-compressing-retrieved-documents","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmis-lab/CompAct","path":"alignment-handbook/src/alignment/data.py","file_url":"https://github.com/dmis-lab/CompAct/blob/HEAD/alignment-handbook/src/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2406.19371","paper":"/paper/suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chtmp223/suri","path":"ft/lib/alignment_mod/data.py","file_url":"https://github.com/chtmp223/suri/blob/HEAD/ft/lib/alignment_mod/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2406.08414","paper":"/paper/discovering-preference-optimization","title":"Discovering Preference Optimization Algorithms with and for Large Language Models","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luchris429/DiscoPOP","path":"src/alignment/data.py","file_url":"https://github.com/luchris429/DiscoPOP/blob/HEAD/src/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}},{"arxiv_id":"2405.14734","paper":"/paper/simpo-simple-preference-optimization-with-a","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/SimPO","path":"alignment/data.py","file_url":"https://github.com/princeton-nlp/SimPO/blob/HEAD/alignment/data.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4253aac010c4504f","mcp_get_code":{"code_sha256":"4253aac010c4504f"}}]}