{"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/prepare-sample-text","entry":"prepare_sample_text","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":10,"n_papers_ran":9,"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":7,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":3,"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":"2409.18618","paper":"/paper/model-based-preference-optimization-in","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","date":"2024-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cjaep/MPO","path":"preferred_FT.py","file_url":"https://github.com/cjaep/MPO/blob/HEAD/preferred_FT.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"556aa92bf20578ab","mcp_get_code":{"code_sha256":"556aa92bf20578ab"}},{"arxiv_id":"2409.18618","paper":"/paper/model-based-preference-optimization-in","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","date":"2024-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cjaep/MPO","path":"sft.py","file_url":"https://github.com/cjaep/MPO/blob/HEAD/sft.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3cfed02e13013093","mcp_get_code":{"code_sha256":"3cfed02e13013093"}},{"arxiv_id":"2407.12043","paper":"/paper/the-art-of-saying-no-contextual-noncompliance","title":"The Art of Saying No: Contextual Noncompliance in Language Models","date":"2024-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/compred","path":"sft.py","file_url":"https://github.com/allenai/compred/blob/HEAD/sft.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":"148dc2c38b7cd922","mcp_get_code":{"code_sha256":"148dc2c38b7cd922"}},{"arxiv_id":"2406.10960","paper":"/paper/escot-towards-interpretable-emotional-support","title":"ESCoT: Towards Interpretable Emotional Support Dialogue Systems","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TeigenZhang/ESCoT","path":"supervised_finetuning_cot.py","file_url":"https://github.com/TeigenZhang/ESCoT/blob/HEAD/supervised_finetuning_cot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b660a6bb2cfcc092","mcp_get_code":{"code_sha256":"b660a6bb2cfcc092"}},{"arxiv_id":"2406.07971","paper":"/paper/it-takes-two-on-the-seamlessness-between","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"taiminglu/seamless","path":"code/train/sft.py","file_url":"https://github.com/taiminglu/seamless/blob/HEAD/code/train/sft.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"148dc2c38b7cd922","mcp_get_code":{"code_sha256":"148dc2c38b7cd922"}},{"arxiv_id":"2405.01511","paper":"/paper/d2po-discriminator-guided-dpo-with-response","title":"D2PO: Discriminator-Guided DPO with Response Evaluation Models","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PrasannS/d2po","path":"src/trainsft.py","file_url":"https://github.com/PrasannS/d2po/blob/HEAD/src/trainsft.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"148dc2c38b7cd922","mcp_get_code":{"code_sha256":"148dc2c38b7cd922"}},{"arxiv_id":"2401.00788","paper":"/paper/astraios-parameter-efficient-instruction","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","date":"2024-01-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigcode-project/astraios","path":"training/finetune.py","file_url":"https://github.com/bigcode-project/astraios/blob/HEAD/training/finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1163ae6f8c7ed82a","mcp_get_code":{"code_sha256":"1163ae6f8c7ed82a"}},{"arxiv_id":"2310.11564","paper":"/paper/personalized-soups-personalized-large","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joeljang/rlphf","path":"training/multitask_training.py","file_url":"https://github.com/joeljang/rlphf/blob/HEAD/training/multitask_training.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c91f5610ae8e27c8","mcp_get_code":{"code_sha256":"c91f5610ae8e27c8"}},{"arxiv_id":"2309.16155","paper":"/paper/the-trickle-down-impact-of-reward-in","title":"The Trickle-down Impact of Reward (In-)consistency on RLHF","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shadowkiller33/contrast-instruction","path":"code/supervised_finetuning.py","file_url":"https://github.com/shadowkiller33/contrast-instruction/blob/HEAD/code/supervised_finetuning.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"148dc2c38b7cd922","mcp_get_code":{"code_sha256":"148dc2c38b7cd922"}},{"arxiv_id":"2305.06161","paper":"/paper/starcoder-may-the-source-be-with-you","title":"StarCoder: may the source be with you!","date":"2023-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigcode-project/starcoder","path":"finetune/finetune.py","file_url":"https://github.com/bigcode-project/starcoder/blob/HEAD/finetune/finetune.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6e471bf54711b54f","mcp_get_code":{"code_sha256":"6e471bf54711b54f"}},{"arxiv_id":"2301.03988","paper":"/paper/santacoder-don-t-reach-for-the-stars","title":"SantaCoder: don't reach for the stars!","date":"2023-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"6e471bf54711b54f","mcp_get_code":{"code_sha256":"6e471bf54711b54f"}}]}