{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FTVHAQJPQRHKVUUEH4DANS4SBP","short_pith_number":"pith:FTVHAQJP","schema_version":"1.0","canonical_sha256":"2cea70412f844eaad2843f0606cb920bc5d0f01f50e28cf77762a0980374bc70","source":{"kind":"arxiv","id":"2608.12635","version":1},"attestation_state":"computed","paper":{"title":"GateTruth: Auditing the Rigor of RTL Design Benchmarks via Mutation Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Meet Bhadra","submitted_at":"2026-08-12T22:50:11Z","abstract_excerpt":"Benchmarks for evaluating large language models on register-transfer-level (RTL) hardware design have proliferated rapidly, yet none reports having applied mutation testing, an established hardware-verification technique for quantifying testbench quality, to ask whether its own testbenches are trustworthy. A testbench that never fails is not evidence of a correct design; it may simply never stimulate the logic that is actually broken. We introduce GateTruth, a mutation-testing engine and methodology for auditing RTL benchmark testbench rigor: inject a deterministic, seeded set of semantic muta"},"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":"2608.12635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-08-12T22:50:11Z","cross_cats_sorted":[],"title_canon_sha256":"55c91ccec5812d7b59795a8ab279205382a03062abe718c4fea46a39c6e32ad5","abstract_canon_sha256":"bbea1d160e85ff1af855c5f91362d137c3ef36f0da2fc6afeeba1fe13501f029"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:46:20.035089Z","signature_b64":"KfMjCxyvl0DnPI9Jh+SobSyFl2muMtZXoPeb9z1g/yttYjA3Vc750KVXLALDgW9k/aUAm+zLI5+NWF4wqy4GCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cea70412f844eaad2843f0606cb920bc5d0f01f50e28cf77762a0980374bc70","last_reissued_at":"2026-08-14T00:46:20.030069Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:46:20.030069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GateTruth: Auditing the Rigor of RTL Design Benchmarks via Mutation Testing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Meet Bhadra","submitted_at":"2026-08-12T22:50:11Z","abstract_excerpt":"Benchmarks for evaluating large language models on register-transfer-level (RTL) hardware design have proliferated rapidly, yet none reports having applied mutation testing, an established hardware-verification technique for quantifying testbench quality, to ask whether its own testbenches are trustworthy. A testbench that never fails is not evidence of a correct design; it may simply never stimulate the logic that is actually broken. We introduce GateTruth, a mutation-testing engine and methodology for auditing RTL benchmark testbench rigor: inject a deterministic, seeded set of semantic muta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12635","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/2608.12635/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":"2608.12635","created_at":"2026-08-14T00:46:20.031100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12635v1","created_at":"2026-08-14T00:46:20.031100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12635","created_at":"2026-08-14T00:46:20.031100+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTVHAQJPQRHK","created_at":"2026-08-14T00:46:20.031100+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTVHAQJPQRHKVUUE","created_at":"2026-08-14T00:46:20.031100+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTVHAQJP","created_at":"2026-08-14T00:46:20.031100+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/FTVHAQJPQRHKVUUEH4DANS4SBP","json":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP.json","graph_json":"https://pith.science/api/pith-number/FTVHAQJPQRHKVUUEH4DANS4SBP/graph.json","events_json":"https://pith.science/api/pith-number/FTVHAQJPQRHKVUUEH4DANS4SBP/events.json","paper":"https://pith.science/paper/FTVHAQJP"},"agent_actions":{"view_html":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP","download_json":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP.json","view_paper":"https://pith.science/paper/FTVHAQJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12635&json=true","fetch_graph":"https://pith.science/api/pith-number/FTVHAQJPQRHKVUUEH4DANS4SBP/graph.json","fetch_events":"https://pith.science/api/pith-number/FTVHAQJPQRHKVUUEH4DANS4SBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP/action/storage_attestation","attest_author":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP/action/author_attestation","sign_citation":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP/action/citation_signature","submit_replication":"https://pith.science/pith/FTVHAQJPQRHKVUUEH4DANS4SBP/action/replication_record"}},"created_at":"2026-08-14T00:46:20.031100+00:00","updated_at":"2026-08-14T00:46:20.031100+00:00"}