{"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/get-remote-file","entry":"get_remote_file","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":16,"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":1,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":1},"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","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2410.22891","paper":"/paper/vpo-leveraging-the-number-of-votes-in","title":"VPO: Leveraging the Number of Votes in Preference Optimization","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ku-dmlab/vpo","path":"utils.py","file_url":"https://github.com/ku-dmlab/vpo/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2409.17431","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2407.10490","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2407.08639","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2407.07880","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2405.20304","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2404.11999","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2402.14688","paper":"/paper/q-probe-a-lightweight-approach-to-reward","title":"Q-Probe: A Lightweight Approach to Reward Maximization for Language Models","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"likenneth/q_probe","path":"preference_exp/utils.py","file_url":"https://github.com/likenneth/q_probe/blob/HEAD/preference_exp/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":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2402.12366","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2402.10958","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,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2402.10571","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2401.13275","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2401.01967","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2312.00267","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}},{"arxiv_id":"2309.16240","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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e7ce4c19888c6df6","mcp_get_code":{"code_sha256":"e7ce4c19888c6df6"}}]}