{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RV2Q3CBOVTG2VB74TZNPZVQ4KP","short_pith_number":"pith:RV2Q3CBO","schema_version":"1.0","canonical_sha256":"8d750d882eaccdaa87fc9e5afcd61c53d4f6fa4c1e972ea8e98c3f5a6feeae76","source":{"kind":"arxiv","id":"2212.11140","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.PL","authors_text":"Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, Hammond Pearce, Ramesh Karri, Shailja Thakur, Siddharth Garg, Zhenxing Fan","submitted_at":"2022-12-13T16:34:39Z","abstract_excerpt":"Automating hardware design could obviate a significant amount of human error from the engineering process and lead to fewer errors. Verilog is a popular hardware description language to model and design digital systems, thus generating Verilog code is a critical first step. Emerging large language models (LLMs) are able to write high-quality code in other programming languages. In this paper, we characterize the ability of LLMs to generate useful Verilog. For this, we fine-tune pre-trained LLMs on Verilog datasets collected from GitHub and Verilog textbooks. We construct an evaluation framewor"},"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":"2212.11140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2022-12-13T16:34:39Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"81ff19b14cdd9c85f6de77f281b467be9c47195b8f27e46ed420bbb1f95299e7","abstract_canon_sha256":"f20193fa0b3aa11e55e04c3379ce479464394c989303f7eb533754d1110a521f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:27.769679Z","signature_b64":"DnGLocj6v6PA6O5cXZzRbUKUDqt+G/jSCYztYjAiMjbAhvdlM2iALuUwO+8kBVVqwBGvLTjiQMqCCsZRmJLgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d750d882eaccdaa87fc9e5afcd61c53d4f6fa4c1e972ea8e98c3f5a6feeae76","last_reissued_at":"2026-07-05T05:27:27.769154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:27.769154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.PL","authors_text":"Baleegh Ahmad, Benjamin Tan, Brendan Dolan-Gavitt, Hammond Pearce, Ramesh Karri, Shailja Thakur, Siddharth Garg, Zhenxing Fan","submitted_at":"2022-12-13T16:34:39Z","abstract_excerpt":"Automating hardware design could obviate a significant amount of human error from the engineering process and lead to fewer errors. Verilog is a popular hardware description language to model and design digital systems, thus generating Verilog code is a critical first step. Emerging large language models (LLMs) are able to write high-quality code in other programming languages. In this paper, we characterize the ability of LLMs to generate useful Verilog. For this, we fine-tune pre-trained LLMs on Verilog datasets collected from GitHub and Verilog textbooks. We construct an evaluation framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11140","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/2212.11140/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":"2212.11140","created_at":"2026-07-05T05:27:27.769215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.11140v1","created_at":"2026-07-05T05:27:27.769215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11140","created_at":"2026-07-05T05:27:27.769215+00:00"},{"alias_kind":"pith_short_12","alias_value":"RV2Q3CBOVTG2","created_at":"2026-07-05T05:27:27.769215+00:00"},{"alias_kind":"pith_short_16","alias_value":"RV2Q3CBOVTG2VB74","created_at":"2026-07-05T05:27:27.769215+00:00"},{"alias_kind":"pith_short_8","alias_value":"RV2Q3CBO","created_at":"2026-07-05T05:27:27.769215+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24218","citing_title":"RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17093","citing_title":"HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17102","citing_title":"Configuration Over Selection: Hyperparameter Sensitivity Exceeds Model Differences in Open-Source LLMs for RTL Generation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP","json":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP.json","graph_json":"https://pith.science/api/pith-number/RV2Q3CBOVTG2VB74TZNPZVQ4KP/graph.json","events_json":"https://pith.science/api/pith-number/RV2Q3CBOVTG2VB74TZNPZVQ4KP/events.json","paper":"https://pith.science/paper/RV2Q3CBO"},"agent_actions":{"view_html":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP","download_json":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP.json","view_paper":"https://pith.science/paper/RV2Q3CBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.11140&json=true","fetch_graph":"https://pith.science/api/pith-number/RV2Q3CBOVTG2VB74TZNPZVQ4KP/graph.json","fetch_events":"https://pith.science/api/pith-number/RV2Q3CBOVTG2VB74TZNPZVQ4KP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP/action/storage_attestation","attest_author":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP/action/author_attestation","sign_citation":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP/action/citation_signature","submit_replication":"https://pith.science/pith/RV2Q3CBOVTG2VB74TZNPZVQ4KP/action/replication_record"}},"created_at":"2026-07-05T05:27:27.769215+00:00","updated_at":"2026-07-05T05:27:27.769215+00:00"}