{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RS4FH7HIM4YGZCHEZLM3YVTNW5","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":"9c0e49263722c12de258a279650128c6511dc20f59784f847e502282764a3324","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-22T10:05:30Z","title_canon_sha256":"eb1c6ba440fdc9c2665e93b70f4458422395847f5c02e5c6eb53849fcebeaa3c"},"schema_version":"1.0","source":{"id":"2507.16414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.16414","created_at":"2026-07-05T11:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.16414v1","created_at":"2026-07-05T11:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16414","created_at":"2026-07-05T11:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"RS4FH7HIM4YG","created_at":"2026-07-05T11:41:09Z"},{"alias_kind":"pith_short_16","alias_value":"RS4FH7HIM4YGZCHE","created_at":"2026-07-05T11:41:09Z"},{"alias_kind":"pith_short_8","alias_value":"RS4FH7HI","created_at":"2026-07-05T11:41:09Z"}],"graph_snapshots":[{"event_id":"sha256:075c36177c03a3acdec38f3313f0b86070f9b3bd0900812dd661214ef0d49bd2","target":"graph","created_at":"2026-07-05T11:41:09Z","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/2507.16414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of large language models (LLMs) is closely tied to their training data, which can include copyrighted material or private information, raising legal and ethical concerns. Additionally, LLMs face criticism for dataset contamination and internalizing biases. To address these issues, the Pre-Training Data Detection (PDD) task was proposed to identify if specific data was included in an LLM's pre-training corpus. However, existing PDD methods often rely on superficial features like prediction confidence and loss, resulting in mediocre performance. To improve this, we introduce NA-P","authors_text":"Hongyi Tang, Yi Yang, Zhihao Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-22T10:05:30Z","title":"Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16414","kind":"arxiv","version":1},"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":"sha256:3eccf727642f14de70206830a191bf818c162d4a82c059e222ceefe794424ff0","target":"record","created_at":"2026-07-05T11:41:09Z","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":"9c0e49263722c12de258a279650128c6511dc20f59784f847e502282764a3324","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-22T10:05:30Z","title_canon_sha256":"eb1c6ba440fdc9c2665e93b70f4458422395847f5c02e5c6eb53849fcebeaa3c"},"schema_version":"1.0","source":{"id":"2507.16414","kind":"arxiv","version":1}},"canonical_sha256":"8cb853fce867306c88e4cad9bc566db774b3345ab829efb3cf8ec902c6fd14d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cb853fce867306c88e4cad9bc566db774b3345ab829efb3cf8ec902c6fd14d5","first_computed_at":"2026-07-05T11:41:09.046140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:09.046140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RnyR3JzwE7N9jbhbZtuGarB3z4ub3elnaDezkRAcrz0x/O6jnnVOZZulcgrqHEiVMKwmQHQuZPVQ4UTLLy/OBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:09.046561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.16414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3eccf727642f14de70206830a191bf818c162d4a82c059e222ceefe794424ff0","sha256:075c36177c03a3acdec38f3313f0b86070f9b3bd0900812dd661214ef0d49bd2"],"state_sha256":"c7780383ee973a4b25986028154d532adbbbb734de6024a2afc2686c12ccd202"}