{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DT5GUJRNJAXTPY435EFVATNUQF","short_pith_number":"pith:DT5GUJRN","schema_version":"1.0","canonical_sha256":"1cfa6a262d482f37e39be90b504db481657213673d454b8933fcfbb88265d339","source":{"kind":"arxiv","id":"2606.19347","version":1},"attestation_state":"computed","paper":{"title":"How LLMs Fail and Generalize in RTL Coding for Hardware Design?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.CL","authors_text":"Brucek Khailany, Chao-Han Huck Yang, Chenhui Deng, Guan-Ting Liu, Yu-Chiang Frank Wang, Zhongzhi Yu","submitted_at":"2026-04-26T14:34:49Z","abstract_excerpt":"Translating sequential programming priors into the parallel temporal logic of hardware design remains a crucial bottleneck for large language models(LLM). To investigate this, we introduce a new error taxonomy grounded in problem solvability, inspired by cognitive theory. Our taxonomy categorizes failures into syntactic, semantic, solvable functional, and unsolvable functional types. Evaluations reveal a strict empirical ceiling on the VerilogEval benchmark, as frontier models plateau at a 90.8% initial pass rate. These plateaus are defined by unsolvable functional errors, exposing persistent "},"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":"2606.19347","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-26T14:34:49Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"45addedabca71b75a258dda048647ed41041c964cd79ece197ae22035e095285","abstract_canon_sha256":"bcb46344d4a25c119da2f9d7133ef95476cb36651c3d0581213d8b480767cc04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:22.784169Z","signature_b64":"lpS+WlIkuMoohm9tZXXw++8ylwLHNiJ62ZX32IWxNtFpp4OViPczFVEZml35/Wz0C/+BPolgIhnn7CMz9wYECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cfa6a262d482f37e39be90b504db481657213673d454b8933fcfbb88265d339","last_reissued_at":"2026-06-19T16:12:22.783816Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:22.783816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How LLMs Fail and Generalize in RTL Coding for Hardware Design?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.CL","authors_text":"Brucek Khailany, Chao-Han Huck Yang, Chenhui Deng, Guan-Ting Liu, Yu-Chiang Frank Wang, Zhongzhi Yu","submitted_at":"2026-04-26T14:34:49Z","abstract_excerpt":"Translating sequential programming priors into the parallel temporal logic of hardware design remains a crucial bottleneck for large language models(LLM). To investigate this, we introduce a new error taxonomy grounded in problem solvability, inspired by cognitive theory. Our taxonomy categorizes failures into syntactic, semantic, solvable functional, and unsolvable functional types. Evaluations reveal a strict empirical ceiling on the VerilogEval benchmark, as frontier models plateau at a 90.8% initial pass rate. These plateaus are defined by unsolvable functional errors, exposing persistent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19347","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/2606.19347/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":"2606.19347","created_at":"2026-06-19T16:12:22.783880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19347v1","created_at":"2026-06-19T16:12:22.783880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19347","created_at":"2026-06-19T16:12:22.783880+00:00"},{"alias_kind":"pith_short_12","alias_value":"DT5GUJRNJAXT","created_at":"2026-06-19T16:12:22.783880+00:00"},{"alias_kind":"pith_short_16","alias_value":"DT5GUJRNJAXTPY43","created_at":"2026-06-19T16:12:22.783880+00:00"},{"alias_kind":"pith_short_8","alias_value":"DT5GUJRN","created_at":"2026-06-19T16:12:22.783880+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/DT5GUJRNJAXTPY435EFVATNUQF","json":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF.json","graph_json":"https://pith.science/api/pith-number/DT5GUJRNJAXTPY435EFVATNUQF/graph.json","events_json":"https://pith.science/api/pith-number/DT5GUJRNJAXTPY435EFVATNUQF/events.json","paper":"https://pith.science/paper/DT5GUJRN"},"agent_actions":{"view_html":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF","download_json":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF.json","view_paper":"https://pith.science/paper/DT5GUJRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19347&json=true","fetch_graph":"https://pith.science/api/pith-number/DT5GUJRNJAXTPY435EFVATNUQF/graph.json","fetch_events":"https://pith.science/api/pith-number/DT5GUJRNJAXTPY435EFVATNUQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF/action/storage_attestation","attest_author":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF/action/author_attestation","sign_citation":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF/action/citation_signature","submit_replication":"https://pith.science/pith/DT5GUJRNJAXTPY435EFVATNUQF/action/replication_record"}},"created_at":"2026-06-19T16:12:22.783880+00:00","updated_at":"2026-06-19T16:12:22.783880+00:00"}