{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OJHFYRGOQDFYR5SN7GF5GLL4KE","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":"ed43342ded91d2e0c53fbc64be11c4fceb79d3998714cff2ea0354ce98982778","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-16T18:49:27Z","title_canon_sha256":"e94a2a340628604fba43514747157e1e192a73f24722027eabcdd57b3fdef6a4"},"schema_version":"1.0","source":{"id":"2402.10892","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10892","created_at":"2026-07-05T08:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10892v3","created_at":"2026-07-05T08:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10892","created_at":"2026-07-05T08:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"OJHFYRGOQDFY","created_at":"2026-07-05T08:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"OJHFYRGOQDFYR5SN","created_at":"2026-07-05T08:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"OJHFYRGO","created_at":"2026-07-05T08:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:a172cebf605dc9c48fffa69da07469d01eec1ff88351f2bb50840b6c7c017ba8","target":"graph","created_at":"2026-07-05T08:56:17Z","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/2402.10892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting whether copyright holders' works were used in LLM pretraining is poised to be an important problem. This work proposes using data watermarks to enable principled detection with only black-box model access, provided that the rightholder contributed multiple training documents and watermarked them before public release. By applying a randomly sampled data watermark, detection can be framed as hypothesis testing, which provides guarantees on the false detection rate. We study two watermarks: one that inserts random sequences, and another that randomly substitutes characters with Unicode","authors_text":"Johnny Tian-Zheng Wei, Robin Jia, Ryan Yixiang Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-16T18:49:27Z","title":"Proving membership in LLM pretraining data via data watermarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10892","kind":"arxiv","version":3},"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":"sha256:5454d035d92eeeafbdbccbd71e2450e0afba2d176f68392564a51ee11622362e","target":"record","created_at":"2026-07-05T08:56:17Z","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":"ed43342ded91d2e0c53fbc64be11c4fceb79d3998714cff2ea0354ce98982778","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-02-16T18:49:27Z","title_canon_sha256":"e94a2a340628604fba43514747157e1e192a73f24722027eabcdd57b3fdef6a4"},"schema_version":"1.0","source":{"id":"2402.10892","kind":"arxiv","version":3}},"canonical_sha256":"724e5c44ce80cb88f64df98bd32d7c5101aa844586b927cf85519f842508b0ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"724e5c44ce80cb88f64df98bd32d7c5101aa844586b927cf85519f842508b0ca","first_computed_at":"2026-07-05T08:56:17.222487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:17.222487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TFdGRlHYGcaX7/UPGdbdkNvws7VZTR2uD5yWdhgWLz1YaHILQs/EtYtvHh9nfB5l1GePTS7a1p85DK3s0OsgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:17.222965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10892","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5454d035d92eeeafbdbccbd71e2450e0afba2d176f68392564a51ee11622362e","sha256:a172cebf605dc9c48fffa69da07469d01eec1ff88351f2bb50840b6c7c017ba8"],"state_sha256":"cf62e0d6691e5a651ca345f259972c5436d62562d309805e98a8a5294f26584c"}