{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V4JMUG2EE4TKALX5FUXKQEJIYH","short_pith_number":"pith:V4JMUG2E","canonical_record":{"source":{"id":"2405.18492","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T18:01:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbb42ae2aaeef9249cc0795c73880353679830b165ad6cac847b39f113e12b92","abstract_canon_sha256":"68bf92373a10a0401a86d4c811850ef05fb9c8c195b526a6420e082f8b19b82e"},"schema_version":"1.0"},"canonical_sha256":"af12ca1b442726a02efd2d2ea81128c1e5926b8f129252fecea269aa99e7e444","source":{"kind":"arxiv","id":"2405.18492","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18492","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18492v3","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18492","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"V4JMUG2EE4TK","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_16","alias_value":"V4JMUG2EE4TKALX5","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_8","alias_value":"V4JMUG2E","created_at":"2026-07-05T09:36:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V4JMUG2EE4TKALX5FUXKQEJIYH","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18492","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T18:01:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbb42ae2aaeef9249cc0795c73880353679830b165ad6cac847b39f113e12b92","abstract_canon_sha256":"68bf92373a10a0401a86d4c811850ef05fb9c8c195b526a6420e082f8b19b82e"},"schema_version":"1.0"},"canonical_sha256":"af12ca1b442726a02efd2d2ea81128c1e5926b8f129252fecea269aa99e7e444","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:41.147568Z","signature_b64":"IKVJMn32ioO8lWAbAKPEPjOai9MNYmme3S51+AfeaXuFQIbrskbCeqGR+zODM4WTZR2CXdY19MGQ2POXUFbIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af12ca1b442726a02efd2d2ea81128c1e5926b8f129252fecea269aa99e7e444","last_reissued_at":"2026-07-05T09:36:41.147066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:41.147066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18492","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+qVh3FsV3Umyizv1UO+cTVfb3/+SiRETyKFcBW8RGkkreaZ5f03qlBffybGf3T1qAVuXCoftVQMHWKyqAh5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:19.544013Z"},"content_sha256":"cae78a608630238905d45d15bbd1ba854c455546138c9b4806d6425df9143573","schema_version":"1.0","event_id":"sha256:cae78a608630238905d45d15bbd1ba854c455546138c9b4806d6425df9143573"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V4JMUG2EE4TKALX5FUXKQEJIYH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs and Memorization: On Quality and Specificity of Copyright Compliance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anna K Bernzen, Felix B Mueller, Janna C Pirk, Maximilian Poretschkin, Rebekka G\\\"orge","submitted_at":"2024-05-28T18:01:52Z","abstract_excerpt":"Memorization in large language models (LLMs) is a growing concern. LLMs have been shown to easily reproduce parts of their training data, including copyrighted work. This is an important problem to solve, as it may violate existing copyright laws as well as the European AI Act. In this work, we propose a systematic analysis to quantify the extent of potential copyright infringements in LLMs using European law as an example. Unlike previous work, we evaluate instruction-finetuned models in a realistic end-user scenario. Our analysis builds on a proposed threshold of 160 characters, which we bor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18492","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.18492/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:36:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZGC61F19ShEXOWfoCpPYU+2yOC5/DmLySmlB8ZbdAtiolBARWzeu5fb/KlpPgRPGJXQ6NHO4yC1+yua06C8rBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:38:19.544415Z"},"content_sha256":"8a8990786ca5fcd277e0ac54527a59f2d93dab0247d5a345440b3f23540c6257","schema_version":"1.0","event_id":"sha256:8a8990786ca5fcd277e0ac54527a59f2d93dab0247d5a345440b3f23540c6257"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4JMUG2EE4TKALX5FUXKQEJIYH/bundle.json","state_url":"https://pith.science/pith/V4JMUG2EE4TKALX5FUXKQEJIYH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4JMUG2EE4TKALX5FUXKQEJIYH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T02:38:19Z","links":{"resolver":"https://pith.science/pith/V4JMUG2EE4TKALX5FUXKQEJIYH","bundle":"https://pith.science/pith/V4JMUG2EE4TKALX5FUXKQEJIYH/bundle.json","state":"https://pith.science/pith/V4JMUG2EE4TKALX5FUXKQEJIYH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4JMUG2EE4TKALX5FUXKQEJIYH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V4JMUG2EE4TKALX5FUXKQEJIYH","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":"68bf92373a10a0401a86d4c811850ef05fb9c8c195b526a6420e082f8b19b82e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T18:01:52Z","title_canon_sha256":"bbb42ae2aaeef9249cc0795c73880353679830b165ad6cac847b39f113e12b92"},"schema_version":"1.0","source":{"id":"2405.18492","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18492","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18492v3","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18492","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"V4JMUG2EE4TK","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_16","alias_value":"V4JMUG2EE4TKALX5","created_at":"2026-07-05T09:36:41Z"},{"alias_kind":"pith_short_8","alias_value":"V4JMUG2E","created_at":"2026-07-05T09:36:41Z"}],"graph_snapshots":[{"event_id":"sha256:8a8990786ca5fcd277e0ac54527a59f2d93dab0247d5a345440b3f23540c6257","target":"graph","created_at":"2026-07-05T09:36:41Z","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/2405.18492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Memorization in large language models (LLMs) is a growing concern. LLMs have been shown to easily reproduce parts of their training data, including copyrighted work. This is an important problem to solve, as it may violate existing copyright laws as well as the European AI Act. In this work, we propose a systematic analysis to quantify the extent of potential copyright infringements in LLMs using European law as an example. Unlike previous work, we evaluate instruction-finetuned models in a realistic end-user scenario. Our analysis builds on a proposed threshold of 160 characters, which we bor","authors_text":"Anna K Bernzen, Felix B Mueller, Janna C Pirk, Maximilian Poretschkin, Rebekka G\\\"orge","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T18:01:52Z","title":"LLMs and Memorization: On Quality and Specificity of Copyright Compliance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18492","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:cae78a608630238905d45d15bbd1ba854c455546138c9b4806d6425df9143573","target":"record","created_at":"2026-07-05T09:36:41Z","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":"68bf92373a10a0401a86d4c811850ef05fb9c8c195b526a6420e082f8b19b82e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-28T18:01:52Z","title_canon_sha256":"bbb42ae2aaeef9249cc0795c73880353679830b165ad6cac847b39f113e12b92"},"schema_version":"1.0","source":{"id":"2405.18492","kind":"arxiv","version":3}},"canonical_sha256":"af12ca1b442726a02efd2d2ea81128c1e5926b8f129252fecea269aa99e7e444","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af12ca1b442726a02efd2d2ea81128c1e5926b8f129252fecea269aa99e7e444","first_computed_at":"2026-07-05T09:36:41.147066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:41.147066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IKVJMn32ioO8lWAbAKPEPjOai9MNYmme3S51+AfeaXuFQIbrskbCeqGR+zODM4WTZR2CXdY19MGQ2POXUFbIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:41.147568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18492","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cae78a608630238905d45d15bbd1ba854c455546138c9b4806d6425df9143573","sha256:8a8990786ca5fcd277e0ac54527a59f2d93dab0247d5a345440b3f23540c6257"],"state_sha256":"2638d0097a3bacde498d4ffb0e1d8b8f7e433d61c5e80213ba6d3beeb4b7082c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ds7yVwr0TKig2GlAAsEtk/fbN9bxXSL6C2W6DBJqTQ5AK1vy8r6hy1UctNgOB2kU8MQnR3wPTSsB71qzJtQBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:38:19.547063Z","bundle_sha256":"45d10794b6ee238072d90d914b4de1e910dbb80658461bf15efa3eb20a39b56d"}}