{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CRQXRE6FDNL7CIVKGL4SDN6AQW","short_pith_number":"pith:CRQXRE6F","schema_version":"1.0","canonical_sha256":"14617893c51b57f122aa32f921b7c085a7b866b73fb7496bb6f5cc06dd1242b5","source":{"kind":"arxiv","id":"2407.07087","version":2},"attestation_state":"computed","paper":{"title":"CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akari Asai, Hannaneh Hajishirzi, James Grimmelmann, Luke Zettlemoyer, Niloofar Mireshghallah, Pang Wei Koh, Sewon Min, Tong Chen, Yejin Choi","submitted_at":"2024-07-09T17:58:18Z","abstract_excerpt":"Evaluating the degree of reproduction of copyright-protected content by language models (LMs) is of significant interest to the AI and legal communities. Although both literal and non-literal similarities are considered by courts when assessing the degree of reproduction, prior research has focused only on literal similarities. To bridge this gap, we introduce CopyBench, a benchmark designed to measure both literal and non-literal copying in LM generations. Using copyrighted fiction books as text sources, we provide automatic evaluation protocols to assess literal and non-literal copying, bala"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.07087","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-09T17:58:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3fbf52758b1eb3a61d68af3bb56dd15969f739be280ee2fdc23d73d75c0b826b","abstract_canon_sha256":"78b847065e832b05fb9ab40c58cce00a1f709030534482a1c6bce9cf5d8f3baf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:34.799065Z","signature_b64":"sOs91+4Z2B66FDG9lfbjYPouVXRW57LTL4iaPnzxRvhhqITLO4S8+nBVCcJilljOdKNCLzQBEzlE9HUIic85AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14617893c51b57f122aa32f921b7c085a7b866b73fb7496bb6f5cc06dd1242b5","last_reissued_at":"2026-07-05T09:15:34.798592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:34.798592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Akari Asai, Hannaneh Hajishirzi, James Grimmelmann, Luke Zettlemoyer, Niloofar Mireshghallah, Pang Wei Koh, Sewon Min, Tong Chen, Yejin Choi","submitted_at":"2024-07-09T17:58:18Z","abstract_excerpt":"Evaluating the degree of reproduction of copyright-protected content by language models (LMs) is of significant interest to the AI and legal communities. Although both literal and non-literal similarities are considered by courts when assessing the degree of reproduction, prior research has focused only on literal similarities. To bridge this gap, we introduce CopyBench, a benchmark designed to measure both literal and non-literal copying in LM generations. Using copyrighted fiction books as text sources, we provide automatic evaluation protocols to assess literal and non-literal copying, bala"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07087","kind":"arxiv","version":2},"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/2407.07087/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.07087","created_at":"2026-07-05T09:15:34.798644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07087v2","created_at":"2026-07-05T09:15:34.798644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07087","created_at":"2026-07-05T09:15:34.798644+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRQXRE6FDNL7","created_at":"2026-07-05T09:15:34.798644+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRQXRE6FDNL7CIVK","created_at":"2026-07-05T09:15:34.798644+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRQXRE6F","created_at":"2026-07-05T09:15:34.798644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.17585","citing_title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03547","citing_title":"Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW","json":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW.json","graph_json":"https://pith.science/api/pith-number/CRQXRE6FDNL7CIVKGL4SDN6AQW/graph.json","events_json":"https://pith.science/api/pith-number/CRQXRE6FDNL7CIVKGL4SDN6AQW/events.json","paper":"https://pith.science/paper/CRQXRE6F"},"agent_actions":{"view_html":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW","download_json":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW.json","view_paper":"https://pith.science/paper/CRQXRE6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07087&json=true","fetch_graph":"https://pith.science/api/pith-number/CRQXRE6FDNL7CIVKGL4SDN6AQW/graph.json","fetch_events":"https://pith.science/api/pith-number/CRQXRE6FDNL7CIVKGL4SDN6AQW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW/action/storage_attestation","attest_author":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW/action/author_attestation","sign_citation":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW/action/citation_signature","submit_replication":"https://pith.science/pith/CRQXRE6FDNL7CIVKGL4SDN6AQW/action/replication_record"}},"created_at":"2026-07-05T09:15:34.798644+00:00","updated_at":"2026-07-05T09:15:34.798644+00:00"}