{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6VRX2R4DGFK6HSUEWLDWL74DAI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"01ff0b1f342cb21a156b9ab043355c187f0dde3b0939c62de462b3deeeb9af37","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T04:25:01Z","title_canon_sha256":"f0fdb309a9607432cfa18c08df6854603211cafdf36cd8c816addfad12822d9f"},"schema_version":"1.0","source":{"id":"2404.02936","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02936","created_at":"2026-07-05T10:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02936v4","created_at":"2026-07-05T10:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02936","created_at":"2026-07-05T10:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"6VRX2R4DGFK6","created_at":"2026-07-05T10:12:59Z"},{"alias_kind":"pith_short_16","alias_value":"6VRX2R4DGFK6HSUE","created_at":"2026-07-05T10:12:59Z"},{"alias_kind":"pith_short_8","alias_value":"6VRX2R4D","created_at":"2026-07-05T10:12:59Z"}],"graph_snapshots":[{"event_id":"sha256:63020f7ba86f7b61aa0a74e695d54bbe5ade65faf4c2ca80b3f1f5853c43bbf0","target":"graph","created_at":"2026-07-05T10:12:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.02936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The problem of pre-training data detection for large language models (LLMs) has received growing attention due to its implications in critical issues like copyright violation and test data contamination. Despite improved performance, existing methods (including the state-of-the-art, Min-K%) are mostly developed upon simple heuristics and lack solid, reasonable foundations. In this work, we propose a novel and theoretically motivated methodology for pre-training data detection, named Min-K%++. Specifically, we present a key insight that training samples tend to be local maxima of the modeled di","authors_text":"Eric Yeats, Hai Li, Hao Frank Yang, Jianyi Zhang, Jingwei Sun, Jingyang Zhang, Martin Kuo, Yang Ouyang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T04:25:01Z","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02936","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0736fca54664ab74a40f681167b23b3bb7c11b7cdba6d7abb9f0a54916c3c82f","target":"record","created_at":"2026-07-05T10:12:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"01ff0b1f342cb21a156b9ab043355c187f0dde3b0939c62de462b3deeeb9af37","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T04:25:01Z","title_canon_sha256":"f0fdb309a9607432cfa18c08df6854603211cafdf36cd8c816addfad12822d9f"},"schema_version":"1.0","source":{"id":"2404.02936","kind":"arxiv","version":4}},"canonical_sha256":"f5637d47833155e3ca84b2c765ff830227038b130e67c727957e7308e4b7ba15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5637d47833155e3ca84b2c765ff830227038b130e67c727957e7308e4b7ba15","first_computed_at":"2026-07-05T10:12:59.587285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:59.587285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xsQRLiSIDFeBd0GmjDVTUqb6oCtiGsAN4fW9zZJwHSdR6M6W2NMVJYgw1TQuf79ZfkL9TwBpwsbshjBxzWRWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:59.587785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02936","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0736fca54664ab74a40f681167b23b3bb7c11b7cdba6d7abb9f0a54916c3c82f","sha256:63020f7ba86f7b61aa0a74e695d54bbe5ade65faf4c2ca80b3f1f5853c43bbf0"],"state_sha256":"b80a4f8e1bbdce6d3e7e331e7d39b955bcea6b1ea0b6f5519dc8a983c1237480"}