{"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-unpad-data","entry":"get_unpad_data","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":5,"n_papers_ran":4,"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":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"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":"OpenRLHF/openrlhf/models/packing_utils.py","file_url":"https://github.com/YSLIU627/Regularized-Preference-Optimization/blob/HEAD/OpenRLHF/openrlhf/models/packing_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":"08e261d2bbc45dbc","mcp_get_code":{"code_sha256":"08e261d2bbc45dbc"}},{"arxiv_id":"2503.10990","paper":"/paper/statistical-impossibility-and-possibility-of","title":"Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium","date":"2025-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"szk123456789/Nash_RS","path":"openrlhf/models/packing_utils.py","file_url":"https://github.com/szk123456789/Nash_RS/blob/HEAD/openrlhf/models/packing_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"08e261d2bbc45dbc","mcp_get_code":{"code_sha256":"08e261d2bbc45dbc"}},{"arxiv_id":"2501.04961","paper":"/paper/demystifying-domain-adaptive-post-training","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","date":"2025-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforceairesearch/findap","path":"FinDAP/utils/packing/monkey_patch_packing.py","file_url":"https://github.com/salesforceairesearch/findap/blob/HEAD/FinDAP/utils/packing/monkey_patch_packing.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"6167fdcdd4d5d961","mcp_get_code":{"code_sha256":"6167fdcdd4d5d961"}},{"arxiv_id":"2408.15793","paper":"/paper/language-adaptation-on-a-tight-academic","title":"Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"konstantinjdobler/tight-budget-llm-adaptation","path":"helpers/mokey_patch_fa_packing.py","file_url":"https://github.com/konstantinjdobler/tight-budget-llm-adaptation/blob/HEAD/helpers/mokey_patch_fa_packing.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6167fdcdd4d5d961","mcp_get_code":{"code_sha256":"6167fdcdd4d5d961"}},{"arxiv_id":"2402.12030","paper":"/paper/towards-cross-tokenizer-distillation-the","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arcee-ai/distillkit","path":"distillkit/monkey_patch_packing.py","file_url":"https://github.com/arcee-ai/distillkit/blob/HEAD/distillkit/monkey_patch_packing.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":"0616e148972493f0","mcp_get_code":{"code_sha256":"0616e148972493f0"}}]}