{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UU76MK5ZXVSSJ6PP32X72ND5WI","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":"cd2e7625c0483841bc16b07a43c9d9350e509e4a23e8262a17228b4d5e32b707","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:55:01Z","title_canon_sha256":"57a32c9b486bc8ff51a2e31513bd9b39a7a82a79a60cc3331f04034902028f1e"},"schema_version":"1.0","source":{"id":"2411.10242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10242","created_at":"2026-07-05T09:36:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10242v1","created_at":"2026-07-05T09:36:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10242","created_at":"2026-07-05T09:36:02Z"},{"alias_kind":"pith_short_12","alias_value":"UU76MK5ZXVSS","created_at":"2026-07-05T09:36:02Z"},{"alias_kind":"pith_short_16","alias_value":"UU76MK5ZXVSSJ6PP","created_at":"2026-07-05T09:36:02Z"},{"alias_kind":"pith_short_8","alias_value":"UU76MK5Z","created_at":"2026-07-05T09:36:02Z"}],"graph_snapshots":[{"event_id":"sha256:c1611da79393bb5e931001e54dcf3547f0549728aff1748334176b1c9d6a62c7","target":"graph","created_at":"2026-07-05T09:36:02Z","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/2411.10242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models memorize parts of their training data. Memorizing short snippets and facts is required to answer questions about the world and to be fluent in any language. But models have also been shown to reproduce long verbatim sequences of memorized text when prompted by a motivated adversary. In this work, we investigate an intermediate regime of memorization that we call non-adversarial reproduction, where we quantify the overlap between model responses and pretraining data when responding to natural and benign prompts. For a variety of innocuous prompt categories (e.g., writing a","authors_text":"Daphne Ippolito, Edoardo Debenedetti, Florian Tram\\`er, Javier Rando, Michael Aerni, Nicholas Carlini","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:55:01Z","title":"Measuring Non-Adversarial Reproduction of Training Data in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10242","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":"sha256:0f9b16390df05d0561092107e52d6f7d0db5414c2cdf991fc3e929f1005dc1cc","target":"record","created_at":"2026-07-05T09:36:02Z","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":"cd2e7625c0483841bc16b07a43c9d9350e509e4a23e8262a17228b4d5e32b707","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-15T14:55:01Z","title_canon_sha256":"57a32c9b486bc8ff51a2e31513bd9b39a7a82a79a60cc3331f04034902028f1e"},"schema_version":"1.0","source":{"id":"2411.10242","kind":"arxiv","version":1}},"canonical_sha256":"a53fe62bb9bd6524f9efdeaffd347db237b37d1729271cb18e47ddee614ca555","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a53fe62bb9bd6524f9efdeaffd347db237b37d1729271cb18e47ddee614ca555","first_computed_at":"2026-07-05T09:36:02.061762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:02.061762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ifhch0EL7cbKBPcmHvdbI0MZIgrGTbd+F0s/OhGJp3pDPa1PsNrSXzYYC8IqLToBP98+SbWYuQS058B3GwXxBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:02.062238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f9b16390df05d0561092107e52d6f7d0db5414c2cdf991fc3e929f1005dc1cc","sha256:c1611da79393bb5e931001e54dcf3547f0549728aff1748334176b1c9d6a62c7"],"state_sha256":"55a04d6b957a30eae196af89a1ad58a9be81887d13f37611672c4ff6d976eb04"}