{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2RWV3WMKYIZGS2WJEELDCC3HX2","short_pith_number":"pith:2RWV3WMK","schema_version":"1.0","canonical_sha256":"d46d5dd98ac232696ac92116310b67bea155afec37b8b4a870924c638dff52ac","source":{"kind":"arxiv","id":"2310.13771","version":1},"attestation_state":"computed","paper":{"title":"Copyright Violations and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Antonia Karamolegkou, Jiaang Li, Li Zhou","submitted_at":"2023-10-20T19:14:59Z","abstract_excerpt":"Language models may memorize more than just facts, including entire chunks of texts seen during training. Fair use exemptions to copyright laws typically allow for limited use of copyrighted material without permission from the copyright holder, but typically for extraction of information from copyrighted materials, rather than {\\em verbatim} reproduction. This work explores the issue of copyright violations and large language models through the lens of verbatim memorization, focusing on possible redistribution of copyrighted text. We present experiments with a range of language models over a "},"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":"2310.13771","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T19:14:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35d6efa96eae4ab8273a121b2eec09923874b83e911fd3c680f0cd7c51c53f01","abstract_canon_sha256":"a64c55347c484008a07898a2ff013c19483893fa09e52746f9df33071875e61d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:34.433805Z","signature_b64":"03IdRUiTu0mtrX7+l0CAo0ijHV/GazLzWQWlwHhlW8yggt8qUB8jfmYnl72lZ1U9qU45H+AQ9ErDn8x7vhW3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d46d5dd98ac232696ac92116310b67bea155afec37b8b4a870924c638dff52ac","last_reissued_at":"2026-07-05T07:03:34.433371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:34.433371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Copyright Violations and Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Antonia Karamolegkou, Jiaang Li, Li Zhou","submitted_at":"2023-10-20T19:14:59Z","abstract_excerpt":"Language models may memorize more than just facts, including entire chunks of texts seen during training. Fair use exemptions to copyright laws typically allow for limited use of copyrighted material without permission from the copyright holder, but typically for extraction of information from copyrighted materials, rather than {\\em verbatim} reproduction. This work explores the issue of copyright violations and large language models through the lens of verbatim memorization, focusing on possible redistribution of copyrighted text. We present experiments with a range of language models over a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13771","kind":"arxiv","version":1},"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/2310.13771/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":"2310.13771","created_at":"2026-07-05T07:03:34.433427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13771v1","created_at":"2026-07-05T07:03:34.433427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13771","created_at":"2026-07-05T07:03:34.433427+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RWV3WMKYIZG","created_at":"2026-07-05T07:03:34.433427+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RWV3WMKYIZGS2WJ","created_at":"2026-07-05T07:03:34.433427+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RWV3WMK","created_at":"2026-07-05T07:03:34.433427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06286","citing_title":"LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12546","citing_title":"Extracting memorized pieces of (copyrighted) books from open-weight language models","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2","json":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2.json","graph_json":"https://pith.science/api/pith-number/2RWV3WMKYIZGS2WJEELDCC3HX2/graph.json","events_json":"https://pith.science/api/pith-number/2RWV3WMKYIZGS2WJEELDCC3HX2/events.json","paper":"https://pith.science/paper/2RWV3WMK"},"agent_actions":{"view_html":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2","download_json":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2.json","view_paper":"https://pith.science/paper/2RWV3WMK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13771&json=true","fetch_graph":"https://pith.science/api/pith-number/2RWV3WMKYIZGS2WJEELDCC3HX2/graph.json","fetch_events":"https://pith.science/api/pith-number/2RWV3WMKYIZGS2WJEELDCC3HX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2/action/storage_attestation","attest_author":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2/action/author_attestation","sign_citation":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2/action/citation_signature","submit_replication":"https://pith.science/pith/2RWV3WMKYIZGS2WJEELDCC3HX2/action/replication_record"}},"created_at":"2026-07-05T07:03:34.433427+00:00","updated_at":"2026-07-05T07:03:34.433427+00:00"}