{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OW2AG3RKP2P2SSIWA4E6FWMYLP","short_pith_number":"pith:OW2AG3RK","schema_version":"1.0","canonical_sha256":"75b4036e2a7e9fa949160709e2d9985bfb6b45fc5fc4ff7d9832cfaad8969969","source":{"kind":"arxiv","id":"2505.06096","version":2},"attestation_state":"computed","paper":{"title":"Free and Fair Hardware: A Pathway to Copyright Infringement-Free Verilog Generation using LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jeyavijayan Rajendran, Matthew DeLorenzo, Phat Tieu, Sam Bush","submitted_at":"2025-05-09T14:44:07Z","abstract_excerpt":"Limitations in Large Language Model (LLM) capabilities for hardware design tasks, such as generating functional Verilog codes, have motivated various fine-tuning optimizations utilizing curated hardware datasets from open-source repositories. However, these datasets remain limited in size and contain minimal checks on licensing for reuse, resulting in potential copyright violations by fine-tuned LLMs. Therefore, we propose an evaluation benchmark to estimate the risk of Verilog-trained LLMs to generate copyright-protected codes. To minimize this risk, we present an open-source Verilog dataset,"},"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":"2505.06096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-09T14:44:07Z","cross_cats_sorted":[],"title_canon_sha256":"c61ff6dfd3e2dce18894028ee131f488ce78444645a78b59dedd9873787561a6","abstract_canon_sha256":"7770b70dadc69d36dd6bfdb4651c4df7d255132497d9894d8eb71467a8ac807f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:59.628305Z","signature_b64":"Ti+pk+qahngUoLYA1M1Dbg5kzIbmquA5rQklaycscCHVzIdY8NQTzGMxcRLfTl5eZ1CxpUqRstyvYZEp8Q+AAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75b4036e2a7e9fa949160709e2d9985bfb6b45fc5fc4ff7d9832cfaad8969969","last_reissued_at":"2026-07-05T11:29:59.627771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:59.627771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Free and Fair Hardware: A Pathway to Copyright Infringement-Free Verilog Generation using LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jeyavijayan Rajendran, Matthew DeLorenzo, Phat Tieu, Sam Bush","submitted_at":"2025-05-09T14:44:07Z","abstract_excerpt":"Limitations in Large Language Model (LLM) capabilities for hardware design tasks, such as generating functional Verilog codes, have motivated various fine-tuning optimizations utilizing curated hardware datasets from open-source repositories. However, these datasets remain limited in size and contain minimal checks on licensing for reuse, resulting in potential copyright violations by fine-tuned LLMs. Therefore, we propose an evaluation benchmark to estimate the risk of Verilog-trained LLMs to generate copyright-protected codes. To minimize this risk, we present an open-source Verilog dataset,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06096","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/2505.06096/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":"2505.06096","created_at":"2026-07-05T11:29:59.627836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06096v2","created_at":"2026-07-05T11:29:59.627836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06096","created_at":"2026-07-05T11:29:59.627836+00:00"},{"alias_kind":"pith_short_12","alias_value":"OW2AG3RKP2P2","created_at":"2026-07-05T11:29:59.627836+00:00"},{"alias_kind":"pith_short_16","alias_value":"OW2AG3RKP2P2SSIW","created_at":"2026-07-05T11:29:59.627836+00:00"},{"alias_kind":"pith_short_8","alias_value":"OW2AG3RK","created_at":"2026-07-05T11:29:59.627836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP","json":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP.json","graph_json":"https://pith.science/api/pith-number/OW2AG3RKP2P2SSIWA4E6FWMYLP/graph.json","events_json":"https://pith.science/api/pith-number/OW2AG3RKP2P2SSIWA4E6FWMYLP/events.json","paper":"https://pith.science/paper/OW2AG3RK"},"agent_actions":{"view_html":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP","download_json":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP.json","view_paper":"https://pith.science/paper/OW2AG3RK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06096&json=true","fetch_graph":"https://pith.science/api/pith-number/OW2AG3RKP2P2SSIWA4E6FWMYLP/graph.json","fetch_events":"https://pith.science/api/pith-number/OW2AG3RKP2P2SSIWA4E6FWMYLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP/action/storage_attestation","attest_author":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP/action/author_attestation","sign_citation":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP/action/citation_signature","submit_replication":"https://pith.science/pith/OW2AG3RKP2P2SSIWA4E6FWMYLP/action/replication_record"}},"created_at":"2026-07-05T11:29:59.627836+00:00","updated_at":"2026-07-05T11:29:59.627836+00:00"}