{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZKVFCHWDPYONE2GTVB5TVH7EQ3","short_pith_number":"pith:ZKVFCHWD","schema_version":"1.0","canonical_sha256":"caaa511ec37e1cd268d3a87b3a9fe486d485d5853fcaf75df70cce146967987d","source":{"kind":"arxiv","id":"2303.15715","version":1},"attestation_state":"computed","paper":{"title":"Foundation Models and Fair Use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Dan Jurafsky, Mark A. Lemley, Percy Liang, Peter Henderson, Tatsunori Hashimoto, Xuechen Li","submitted_at":"2023-03-28T03:58:40Z","abstract_excerpt":"Existing foundation models are trained on copyrighted material. Deploying these models can pose both legal and ethical risks when data creators fail to receive appropriate attribution or compensation. In the United States and several other countries, copyrighted content may be used to build foundation models without incurring liability due to the fair use doctrine. However, there is a caveat: If the model produces output that is similar to copyrighted data, particularly in scenarios that affect the market of that data, fair use may no longer apply to the output of the model. In this work, we e"},"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":"2303.15715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2023-03-28T03:58:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"29eab2ef941a7d8ed27b46345e55bcad1926a0fcb07aa1f766406d6afdcd5c56","abstract_canon_sha256":"34d4b0fc89344c13348afb564a281672e7d50dd40159590d97721c6daae05b33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:04.340417Z","signature_b64":"sTMC+0QMN4DiUFTLD6Kmd7IxNJndjk2aixJujF6iWv5T5A6w/Mv5oy5U7nBP/RVV7iRREv7QzvM150BxsBsIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caaa511ec37e1cd268d3a87b3a9fe486d485d5853fcaf75df70cce146967987d","last_reissued_at":"2026-07-05T05:56:04.339814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:04.339814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundation Models and Fair Use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Dan Jurafsky, Mark A. Lemley, Percy Liang, Peter Henderson, Tatsunori Hashimoto, Xuechen Li","submitted_at":"2023-03-28T03:58:40Z","abstract_excerpt":"Existing foundation models are trained on copyrighted material. Deploying these models can pose both legal and ethical risks when data creators fail to receive appropriate attribution or compensation. In the United States and several other countries, copyrighted content may be used to build foundation models without incurring liability due to the fair use doctrine. However, there is a caveat: If the model produces output that is similar to copyrighted data, particularly in scenarios that affect the market of that data, fair use may no longer apply to the output of the model. In this work, we e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15715","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/2303.15715/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":"2303.15715","created_at":"2026-07-05T05:56:04.339880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.15715v1","created_at":"2026-07-05T05:56:04.339880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15715","created_at":"2026-07-05T05:56:04.339880+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKVFCHWDPYON","created_at":"2026-07-05T05:56:04.339880+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKVFCHWDPYONE2GT","created_at":"2026-07-05T05:56:04.339880+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKVFCHWD","created_at":"2026-07-05T05:56:04.339880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19116","citing_title":"Towards an Agent-First Web: Redesigning the Web for AI Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12088","citing_title":"Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00527","citing_title":"AI Native Games: A Survey and Roadmap","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10995","citing_title":"A Human-Centric Framework for Data Attribution in Large Language Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2304.05376","citing_title":"ChemCrow: Augmenting large-language models with chemistry tools","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06161","citing_title":"StarCoder: may the source be with you!","ref_index":202,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3","json":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3.json","graph_json":"https://pith.science/api/pith-number/ZKVFCHWDPYONE2GTVB5TVH7EQ3/graph.json","events_json":"https://pith.science/api/pith-number/ZKVFCHWDPYONE2GTVB5TVH7EQ3/events.json","paper":"https://pith.science/paper/ZKVFCHWD"},"agent_actions":{"view_html":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3","download_json":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3.json","view_paper":"https://pith.science/paper/ZKVFCHWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.15715&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKVFCHWDPYONE2GTVB5TVH7EQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKVFCHWDPYONE2GTVB5TVH7EQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3/action/storage_attestation","attest_author":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3/action/author_attestation","sign_citation":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3/action/citation_signature","submit_replication":"https://pith.science/pith/ZKVFCHWDPYONE2GTVB5TVH7EQ3/action/replication_record"}},"created_at":"2026-07-05T05:56:04.339880+00:00","updated_at":"2026-07-05T05:56:04.339880+00:00"}