{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FISNAD566JC2WEDUFYBXC565UD","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":"135df78d755c7864d85f7dbf9e440545ea1d7429cba284bc08ae376333ec6c63","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T01:15:16Z","title_canon_sha256":"62baabbbe5523646476fbc6ddf652e681fa3179dfd481e21ac9877361f134d52"},"schema_version":"1.0","source":{"id":"2603.24917","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.24917","created_at":"2026-07-22T01:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2603.24917v2","created_at":"2026-07-22T01:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.24917","created_at":"2026-07-22T01:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"FISNAD566JC2","created_at":"2026-07-22T01:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"FISNAD566JC2WEDU","created_at":"2026-07-22T01:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"FISNAD56","created_at":"2026-07-22T01:22:39Z"}],"graph_snapshots":[{"event_id":"sha256:adf1c9e4a5747d5d2d2456403b528553ebdf78c58e4dbc33cf2c4fc77df88226","target":"graph","created_at":"2026-07-22T01:22:39Z","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/2603.24917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences. Probabilistic extraction -- computing the probability of generating a target suffix given a prefix under a decoding scheme -- addresses this, but is tractable only for verbatim memorization, missing near-verbatim instances that pose similar privacy and copyright risks. Quantifying near-verbatim extraction risk is expensive: the set of near-verbatim suffixes is combinatorially large, and reliable Monte Carlo (MC) estimation can require ~100,00","authors_text":"A. Feder Cooper, Allison Casasola, Christopher De Sa, Daniel E. Ho, Jamie Hayes, Katherine Lee, Lea Duesterwald, Mark A. Lemley, Percy Liang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T01:15:16Z","title":"Estimating near-verbatim extraction risk in language models with decoding-constrained beam search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.24917","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":"sha256:2cf127e4088efe13d0109f8ffed04eb67b08d687cbbb15d12a3de69870025df0","target":"record","created_at":"2026-07-22T01:22:39Z","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":"135df78d755c7864d85f7dbf9e440545ea1d7429cba284bc08ae376333ec6c63","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-26T01:15:16Z","title_canon_sha256":"62baabbbe5523646476fbc6ddf652e681fa3179dfd481e21ac9877361f134d52"},"schema_version":"1.0","source":{"id":"2603.24917","kind":"arxiv","version":2}},"canonical_sha256":"2a24d00fbef245ab10742e037177dda0cf4a226677aca1708c3da0b415385457","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a24d00fbef245ab10742e037177dda0cf4a226677aca1708c3da0b415385457","first_computed_at":"2026-07-22T01:22:39.099133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:22:39.099133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rYrAFVAl9xNWZuCv2o4K1GaXdRDe+mhYjoB08fNJyB3TViuM24GErlz5J6I9j7hWtvUP3i/w7IZa8YDSAbhwBA==","signature_status":"signed_v1","signed_at":"2026-07-22T01:22:39.100061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.24917","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cf127e4088efe13d0109f8ffed04eb67b08d687cbbb15d12a3de69870025df0","sha256:adf1c9e4a5747d5d2d2456403b528553ebdf78c58e4dbc33cf2c4fc77df88226"],"state_sha256":"8a427515ec096ec79b0c93cd5212bd540c23b5772e73c68d145b5ef14693adb7"}