{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6LDABG62QF4WJBT45EICYC5VC3","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":"a1a915eeffd79de6d07bb74dd79caf5db3c4d3cae6b9a5efb668d4b3b300d765","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:32:16Z","title_canon_sha256":"21ef64110452ec5f0af2304444104549dff27b619993fb8f9bd1b753f4a9c18f"},"schema_version":"1.0","source":{"id":"2406.17746","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17746","created_at":"2026-07-05T10:59:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17746v2","created_at":"2026-07-05T10:59:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17746","created_at":"2026-07-05T10:59:59Z"},{"alias_kind":"pith_short_12","alias_value":"6LDABG62QF4W","created_at":"2026-07-05T10:59:59Z"},{"alias_kind":"pith_short_16","alias_value":"6LDABG62QF4WJBT4","created_at":"2026-07-05T10:59:59Z"},{"alias_kind":"pith_short_8","alias_value":"6LDABG62","created_at":"2026-07-05T10:59:59Z"}],"graph_snapshots":[{"event_id":"sha256:be4190e1a9962f5dc7310b7e42760607dfbd769f444eb07f30c019cd26e56754","target":"graph","created_at":"2026-07-05T10:59:59Z","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/2406.17746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Memorization in language models is typically treated as a homogenous phenomenon, neglecting the specifics of the memorized data. We instead model memorization as the effect of a set of complex factors that describe each sample and relate it to the model and corpus. To build intuition around these factors, we break memorization down into a taxonomy: recitation of highly duplicated sequences, reconstruction of inherently predictable sequences, and recollection of sequences that are neither. We demonstrate the usefulness of our taxonomy by using it to construct a predictive model for memorization","authors_text":"Alvin Deng, Christopher A. Choquette-Choo, Jacob Ray Fuehne, Jaydeep Borkar, Jyothir S V, Katherine Lee, Kyle O'Brien, Mohammad Aflah Khan, Naomi Saphra, Stella Biderman, Tracy Ke, USVSN Sai Prashanth","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:32:16Z","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17746","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":"sha256:707e3286287df9695169ea00a0d6e644491cf02fcfdcdb0ad0d682dbab8ce26b","target":"record","created_at":"2026-07-05T10:59:59Z","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":"a1a915eeffd79de6d07bb74dd79caf5db3c4d3cae6b9a5efb668d4b3b300d765","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T17:32:16Z","title_canon_sha256":"21ef64110452ec5f0af2304444104549dff27b619993fb8f9bd1b753f4a9c18f"},"schema_version":"1.0","source":{"id":"2406.17746","kind":"arxiv","version":2}},"canonical_sha256":"f2c6009bda817964867ce9102c0bb516e774e0626183a0d3274ac5cafdcb398a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2c6009bda817964867ce9102c0bb516e774e0626183a0d3274ac5cafdcb398a","first_computed_at":"2026-07-05T10:59:59.084328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:59.084328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tlTTMlwDiiMwIZu4seRLDz+vTazo0nIse40lyEuby/BywwhiWI4WAJ8TB/7IVfGgtfQbrZ9S8Dm1GaAfKzt2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:59.084835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17746","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:707e3286287df9695169ea00a0d6e644491cf02fcfdcdb0ad0d682dbab8ce26b","sha256:be4190e1a9962f5dc7310b7e42760607dfbd769f444eb07f30c019cd26e56754"],"state_sha256":"d3ff86092e5f860a548a2232a46613ea273b999f1badd115e9cc5c4f8f074947"}