{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RQ4SOKB6SQS4IT5OWU4S2Z5WTZ","short_pith_number":"pith:RQ4SOKB6","schema_version":"1.0","canonical_sha256":"8c3927283e9425c44faeb5392d67b69e55d0c4e4bbb00e739c57dbb9c8b3a8b8","source":{"kind":"arxiv","id":"2408.02487","version":3},"attestation_state":"computed","paper":{"title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Hao He, Kai Gao, Minghui Zhou, Weiwei Xu","submitted_at":"2024-08-05T14:09:30Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have revolutionized code generation, leading to widespread adoption of AI coding tools by developers. However, LLMs can generate license-protected code without providing the necessary license information, leading to potential intellectual property violations during software production. This paper addresses the critical, yet underexplored, issue of license compliance in LLM-generated code by establishing a benchmark to evaluate the ability of LLMs to provide accurate license information for their generated code. To establish this benchmark, we con"},"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":"2408.02487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-08-05T14:09:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"44c4ded97e57e0ac44553be7bdf4335d5f57be32813e4a1b7a6d8989300754c3","abstract_canon_sha256":"031980ea7eb03630caac63b0a55a5e1cc1c339579da6150e70eddb7e75699197"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:26.729635Z","signature_b64":"LX/dK6PuEfYXb4bekYBp9JLnikUErXMV7Mf6AC0EGLjofYIWbT833gItJnchxfQJ2tNzT/mirquwFsXU/UQACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c3927283e9425c44faeb5392d67b69e55d0c4e4bbb00e739c57dbb9c8b3a8b8","last_reissued_at":"2026-07-05T10:19:26.729161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:26.729161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiCoEval: Evaluating LLMs on License Compliance in Code Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Hao He, Kai Gao, Minghui Zhou, Weiwei Xu","submitted_at":"2024-08-05T14:09:30Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have revolutionized code generation, leading to widespread adoption of AI coding tools by developers. However, LLMs can generate license-protected code without providing the necessary license information, leading to potential intellectual property violations during software production. This paper addresses the critical, yet underexplored, issue of license compliance in LLM-generated code by establishing a benchmark to evaluate the ability of LLMs to provide accurate license information for their generated code. To establish this benchmark, we con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02487","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/2408.02487/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":"2408.02487","created_at":"2026-07-05T10:19:26.729220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02487v3","created_at":"2026-07-05T10:19:26.729220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02487","created_at":"2026-07-05T10:19:26.729220+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQ4SOKB6SQS4","created_at":"2026-07-05T10:19:26.729220+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQ4SOKB6SQS4IT5O","created_at":"2026-07-05T10:19:26.729220+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQ4SOKB6","created_at":"2026-07-05T10:19:26.729220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23495","citing_title":"Ensuring Open Source Integrity: The Intersection of Copy-Based Reuse and License Compliance","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16377","citing_title":"GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22604","citing_title":"Vibe coding for clinicians: democratising bespoke software development for digital health innovation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ","json":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ.json","graph_json":"https://pith.science/api/pith-number/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/graph.json","events_json":"https://pith.science/api/pith-number/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/events.json","paper":"https://pith.science/paper/RQ4SOKB6"},"agent_actions":{"view_html":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ","download_json":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ.json","view_paper":"https://pith.science/paper/RQ4SOKB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02487&json=true","fetch_graph":"https://pith.science/api/pith-number/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/action/storage_attestation","attest_author":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/action/author_attestation","sign_citation":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/action/citation_signature","submit_replication":"https://pith.science/pith/RQ4SOKB6SQS4IT5OWU4S2Z5WTZ/action/replication_record"}},"created_at":"2026-07-05T10:19:26.729220+00:00","updated_at":"2026-07-05T10:19:26.729220+00:00"}