{"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/unlearncollector","entry":"unlearncollector","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":7,"n_papers_ran":2,"n_papers_ran_no_instrument_failure":0,"n_papers_ran_instrument_only":2,"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":4,"n_samples_ran":2,"n_samples_constructed":0,"n_samples_ran_checked":0,"n_samples_instrument":2,"n_samples_unverified":2,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":2,"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":2,"ran_fixture":0,"ran":0,"unverified":2},"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":"2605.08765","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-08765","title":"Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"OPTML-Group/ReVa","path":"src/eval/dataset/Base.py","file_url":"https://github.com/OPTML-Group/ReVa/blob/HEAD/src/eval/dataset/Base.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, OPTML-Group/ReVa when it was checked","code_sha256":"a378b7ead7ef288e","code_sha256_prefix":"a378b7ead7ef288e","mcp_get_code":{"code_sha256":"a378b7ead7ef288e"}},{"arxiv_id":"2605.06076","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-06076","title":"Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Zodiark-ch/MechLocalization","path":"src/dataset/Base.py","file_url":"https://github.com/Zodiark-ch/MechLocalization/blob/HEAD/src/dataset/Base.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, Zodiark-ch/MechLocalization when it was checked","code_sha256":"365b264039b356f2","code_sha256_prefix":"365b264039b356f2","mcp_get_code":{"code_sha256":"365b264039b356f2"}},{"arxiv_id":"2506.01339","arxiv_id_is_arxiv":true,"paper":"/paper/invariance-makes-llm-unlearning-resilient","title":"Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPTML-Group/Unlearn-ILU","path":"src/dataset/Base.py","file_url":"https://github.com/OPTML-Group/Unlearn-ILU/blob/HEAD/src/dataset/Base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"21b851de3f5356c4","code_sha256_prefix":"21b851de3f5356c4","mcp_get_code":{"code_sha256":"21b851de3f5356c4"}},{"arxiv_id":"2410.17509","arxiv_id_is_arxiv":true,"paper":"/paper/wagle-strategic-weight-attribution-for","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPTML-Group/WAGLE","path":"src/dataset/Base.py","file_url":"https://github.com/OPTML-Group/WAGLE/blob/HEAD/src/dataset/Base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"21b851de3f5356c4","code_sha256_prefix":"21b851de3f5356c4","mcp_get_code":{"code_sha256":"21b851de3f5356c4"}},{"arxiv_id":"2410.07163","arxiv_id_is_arxiv":true,"paper":"/paper/simplicity-prevails-rethinking-negative","title":"Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OPTML-Group/Unlearn-Simple","path":"TOFU/data_module.py","file_url":"https://github.com/OPTML-Group/Unlearn-Simple/blob/HEAD/TOFU/data_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"52f769b837c6e32a","code_sha256_prefix":"52f769b837c6e32a","mcp_get_code":{"code_sha256":"52f769b837c6e32a"}},{"arxiv_id":"2404.18239","arxiv_id_is_arxiv":true,"paper":"/paper/soul-unlocking-the-power-of-second-order","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","date":"2024-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"optml-group/soul","path":"src/dataset/Base.py","file_url":"https://github.com/optml-group/soul/blob/HEAD/src/dataset/Base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"21b851de3f5356c4","code_sha256_prefix":"21b851de3f5356c4","mcp_get_code":{"code_sha256":"21b851de3f5356c4"}},{"arxiv_id":"2025.findings-acl.949","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2025.findings-acl.949","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"renjie3/GRUN","path":"baseline/data_module.py","file_url":"https://github.com/renjie3/GRUN/blob/HEAD/baseline/data_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"52f769b837c6e32a","code_sha256_prefix":"52f769b837c6e32a","mcp_get_code":{"code_sha256":"52f769b837c6e32a"}}],"record_sha256":"83de458fa21794e85a747314b5762e5121d7523ad3a31e733ded0770051f2ad8","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}