{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/get-local-run-dir","entry":"get_local_run_dir","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":14,"n_papers_ran":13,"n_papers_ran_no_instrument_failure":2,"n_papers_ran_instrument_only":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":5,"n_samples_ran":4,"n_samples_constructed":0,"n_samples_ran_checked":1,"n_samples_instrument":3,"n_samples_unverified":1,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":3,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":1,"unverified":1},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2411.06424","arxiv_id_is_arxiv":true,"paper":"/paper/ablation-is-not-enough-to-emulate-dpo-how","title":"Beyond Toxic Neurons: A Mechanistic Analysis of DPO for Toxicity Reduction","date":"2024-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yushi-y/dpo-toxic-neurons","path":"train_dpo/dpo_utils.py","file_url":"https://github.com/yushi-y/dpo-toxic-neurons/blob/HEAD/train_dpo/dpo_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1df5ede8f8950a70","code_sha256_prefix":"1df5ede8f8950a70","mcp_get_code":{"code_sha256":"1df5ede8f8950a70"}},{"arxiv_id":"2409.17431","arxiv_id_is_arxiv":true,"paper":"/paper/on-extending-direct-preference-optimization","title":"On Extending Direct Preference Optimization to Accommodate Ties","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-mitchell/direct-preference-optimization","path":"utils.py","file_url":"https://github.com/eric-mitchell/direct-preference-optimization/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2407.10490","arxiv_id_is_arxiv":true,"paper":"/paper/learning-dynamics-of-llm-finetuning","title":"Learning Dynamics of LLM Finetuning","date":"2024-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"joshua-ren/learning_dynamics_llm","path":"src/utils.py","file_url":"https://github.com/joshua-ren/learning_dynamics_llm/blob/HEAD/src/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2407.08639","arxiv_id_is_arxiv":true,"paper":"/paper/b-dpo-direct-preference-optimization-with","title":"$β$-DPO: Direct Preference Optimization with Dynamic $β$","date":"2024-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junkangwu/beta-dpo","path":"utils.py","file_url":"https://github.com/junkangwu/beta-dpo/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, junkangwu/beta-dpo when it was checked","code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2407.07880","arxiv_id_is_arxiv":true,"paper":"/paper/towards-robust-alignment-of-language-models","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junkangwu/dr_dpo","path":"utils.py","file_url":"https://github.com/junkangwu/dr_dpo/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, junkangwu/dr_dpo when it was checked","code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2405.20304","arxiv_id_is_arxiv":true,"paper":"/paper/group-robust-preference-optimization-in","title":"Group Robust Preference Optimization in Reward-free RLHF","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rsshyam/Group-robust-preference-optimization","path":"src/utils.py","file_url":"https://github.com/rsshyam/Group-robust-preference-optimization/blob/HEAD/src/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2404.11999","arxiv_id_is_arxiv":true,"paper":"/paper/token-level-direct-preference-optimization","title":"Token-level Direct Preference Optimization","date":"2024-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vance0124/token-level-direct-preference-optimization","path":"utils.py","file_url":"https://github.com/vance0124/token-level-direct-preference-optimization/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2402.12366","arxiv_id_is_arxiv":true,"paper":"/paper/a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"architsharma97/dpo-rlaif","path":"utils.py","file_url":"https://github.com/architsharma97/dpo-rlaif/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"5edbbf974035e91f","code_sha256_prefix":"5edbbf974035e91f","mcp_get_code":{"code_sha256":"5edbbf974035e91f"}},{"arxiv_id":"2402.10958","arxiv_id_is_arxiv":true,"paper":"/paper/relative-preference-optimization-enhancing","title":"Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinyueqin/relative-preference-optimization","path":"utils.py","file_url":"https://github.com/yinyueqin/relative-preference-optimization/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"70c537e500d55211","code_sha256_prefix":"70c537e500d55211","mcp_get_code":{"code_sha256":"70c537e500d55211"}},{"arxiv_id":"2402.10571","arxiv_id_is_arxiv":true,"paper":"/paper/direct-preference-optimization-with-an-offset","title":"Direct Preference Optimization with an Offset","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rycolab/odpo","path":"utils.py","file_url":"https://github.com/rycolab/odpo/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2401.13275","arxiv_id_is_arxiv":true,"paper":"/paper/can-ai-assistants-know-what-they-don-t-know","title":"Can AI Assistants Know What They Don't Know?","date":"2024-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmoss/say-i-dont-know","path":"src/dpo/utils.py","file_url":"https://github.com/openmoss/say-i-dont-know/blob/HEAD/src/dpo/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, openmoss/say-i-dont-know when it was checked","code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}},{"arxiv_id":"2401.01967","arxiv_id_is_arxiv":true,"paper":"/paper/a-mechanistic-understanding-of-alignment","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","date":"2024-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ajyl/dpo_toxic","path":"toxicity/train_dpo/dpo_utils.py","file_url":"https://github.com/ajyl/dpo_toxic/blob/HEAD/toxicity/train_dpo/dpo_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1df5ede8f8950a70","code_sha256_prefix":"1df5ede8f8950a70","mcp_get_code":{"code_sha256":"1df5ede8f8950a70"}},{"arxiv_id":"2312.00267","arxiv_id_is_arxiv":true,"paper":"/paper/sample-efficient-reinforcement-learning-from","title":"Sample Efficient Preference Alignment in LLMs via Active Exploration","date":"2023-12-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"belakaria/active-llm-alignment","path":"utils.py","file_url":"https://github.com/belakaria/active-llm-alignment/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"96a26eed980b8eba","code_sha256_prefix":"96a26eed980b8eba","mcp_get_code":{"code_sha256":"96a26eed980b8eba"}},{"arxiv_id":"2309.16240","arxiv_id_is_arxiv":true,"paper":"/paper/beyond-reverse-kl-generalizing-direct","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alecwangcq/f-divergence-dpo","path":"utils.py","file_url":"https://github.com/alecwangcq/f-divergence-dpo/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"10ab71f27ffd7de8","code_sha256_prefix":"10ab71f27ffd7de8","mcp_get_code":{"code_sha256":"10ab71f27ffd7de8"}}],"record_sha256":"6818f01a071e690c5fee2f741aa48319ba801375db93e4b78339b0eec0aa120b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}