{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QFFIFIQZVRWQZ2P245K6BOLPBF","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":"46e76f20ad17396cef3da6771a15c96573cca04a66ca27213ed9b33e88ec97b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T08:04:20Z","title_canon_sha256":"c869b5438d692d7e5065b45287ba47e6e8e0ed307b385e923984a71292264ffe"},"schema_version":"1.0","source":{"id":"2508.17767","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17767","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17767v2","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17767","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"QFFIFIQZVRWQ","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"QFFIFIQZVRWQZ2P2","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"QFFIFIQZ","created_at":"2026-07-05T12:11:20Z"}],"graph_snapshots":[{"event_id":"sha256:292ae69267f8e55fc725db33a66995803f15d1877d31ed348dfbcb59f0a819d9","target":"graph","created_at":"2026-07-05T12:11:20Z","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/2508.17767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but pose risks of inadvertently exposing copyrighted or proprietary data, especially when such data is used for training but not intended for distribution. Traditional methods address these leaks only after content is generated, which can lead to the exposure of sensitive information. This study introduces a proactive approach: examining LLMs' internal states before text generation to detect potential leaks. By using a curated dataset of copyrighted materials, we trained a neural network classifier to identify r","authors_text":"Cheng Qian, Denghui Zhang, Guangwei Zhang, Jiateng Liu, Qisheng Su, Yanjie Fu, Yanzhou Pan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T08:04:20Z","title":"ISACL: Internal State Analyzer for Copyrighted Training Data Leakage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17767","kind":"arxiv","version":2},"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":"sha256:1fad60dcf5d32b6b2d1ee23d4f31f53ec2ac754433e00c668829cd6d21e9eb0b","target":"record","created_at":"2026-07-05T12:11:20Z","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":"46e76f20ad17396cef3da6771a15c96573cca04a66ca27213ed9b33e88ec97b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-25T08:04:20Z","title_canon_sha256":"c869b5438d692d7e5065b45287ba47e6e8e0ed307b385e923984a71292264ffe"},"schema_version":"1.0","source":{"id":"2508.17767","kind":"arxiv","version":2}},"canonical_sha256":"814a82a219ac6d0ce9fae755e0b96f0970ce2f9730f0a06a48a437799fa7231c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"814a82a219ac6d0ce9fae755e0b96f0970ce2f9730f0a06a48a437799fa7231c","first_computed_at":"2026-07-05T12:11:20.136356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:20.136356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+c3KNnZAEBJmvxWU9knw3G4ntypZsjU/aCsNsJiVU0o/1Kg7c7gMF3kaqHjIRF3rPogAQmsaVLNFkAltpFc2Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:20.136927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17767","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fad60dcf5d32b6b2d1ee23d4f31f53ec2ac754433e00c668829cd6d21e9eb0b","sha256:292ae69267f8e55fc725db33a66995803f15d1877d31ed348dfbcb59f0a819d9"],"state_sha256":"d7e96296e5bc0cbac477555e733ff4748a4fe0986d7e69f8c3389c204e868804"}