{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WXZVI4V2IUP6ELAT6F3F2RTVH6","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":"bc4a9903a996f65d446d40088c32aa8de68b925250becd95fcc80ed701185193","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T17:34:03Z","title_canon_sha256":"8969aba3fbbe132a80cbafc42ebf0d4e99391987a48849647fef45ba4d99804c"},"schema_version":"1.0","source":{"id":"2505.24832","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24832","created_at":"2026-07-05T11:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24832v3","created_at":"2026-07-05T11:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24832","created_at":"2026-07-05T11:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"WXZVI4V2IUP6","created_at":"2026-07-05T11:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"WXZVI4V2IUP6ELAT","created_at":"2026-07-05T11:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"WXZVI4V2","created_at":"2026-07-05T11:23:29Z"}],"graph_snapshots":[{"event_id":"sha256:8ae98232ad8ed38d764b7f317464f243ce93fd540ac8b56f5f21b77d33374e84","target":"graph","created_at":"2026-07-05T11:23:29Z","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/2505.24832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new method for estimating how much a model knows about a datapoint and use it to measure the capacity of modern language models. Prior studies of language model memorization have struggled to disentangle memorization from generalization. We formally separate memorization into two components: unintended memorization, the information a model contains about a specific dataset, and generalization, the information a model contains about the true data-generation process. When we completely eliminate generalization, we can compute the total memorization, which provides an estimate of mod","authors_text":"Alexander M. Rush, Chawin Sitawarin, Chuan Guo, G. Edward Suh, John X. Morris, Kamalika Chaudhuri, Narine Kokhlikyan, Saeed Mahloujifar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T17:34:03Z","title":"How much do language models memorize?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24832","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":"sha256:51a05ee497d44657eb9b2cd856c6ee8ed0cb6ed9ccf7391c2211c489c06c0903","target":"record","created_at":"2026-07-05T11:23:29Z","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":"bc4a9903a996f65d446d40088c32aa8de68b925250becd95fcc80ed701185193","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T17:34:03Z","title_canon_sha256":"8969aba3fbbe132a80cbafc42ebf0d4e99391987a48849647fef45ba4d99804c"},"schema_version":"1.0","source":{"id":"2505.24832","kind":"arxiv","version":3}},"canonical_sha256":"b5f35472ba451fe22c13f1765d46753fbf1d99dca422760385fccdf2b7e27784","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5f35472ba451fe22c13f1765d46753fbf1d99dca422760385fccdf2b7e27784","first_computed_at":"2026-07-05T11:23:29.000310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:29.000310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dq3NAQHnvv/kh0fLHM97R8AqAarh8ekUDN1Ye0KvsJGZGWwTbE+sfOvvkKo9baF+UNG6FxYPABt2gRMZVwT8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:29.000819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24832","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51a05ee497d44657eb9b2cd856c6ee8ed0cb6ed9ccf7391c2211c489c06c0903","sha256:8ae98232ad8ed38d764b7f317464f243ce93fd540ac8b56f5f21b77d33374e84"],"state_sha256":"c024d1e7e798b68d1a996699922de927041c7329b3aa2123cad9fadcc36c8324"}