{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:73HRTJAIAOKGKJUNIXOUCT6HR3","short_pith_number":"pith:73HRTJAI","schema_version":"1.0","canonical_sha256":"fecf19a408039465268d45dd414fc78eea36a9ab9bc22ec37979dc1e78b56121","source":{"kind":"arxiv","id":"2503.19174","version":2},"attestation_state":"computed","paper":{"title":"AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ghaith Bany Hamad, Haoxing Ren, Syed Suhaib, Yunsheng Bai","submitted_at":"2025-03-24T21:53:37Z","abstract_excerpt":"Generating SystemVerilog Assertions (SVAs) from natural language specifications remains a major challenge in formal verification (FV) due to the inherent ambiguity and incompleteness of specifications. Existing LLM-based approaches, such as AssertLLM, focus on extracting information solely from specification documents, often failing to capture essential internal signal interactions and design details present in the RTL code, leading to incomplete or incorrect assertions. We propose a novel approach that constructs a Knowledge Graph (KG) from both specifications and RTL, using a hardware-specif"},"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":"2503.19174","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-24T21:53:37Z","cross_cats_sorted":[],"title_canon_sha256":"d57c61f123c260da2956c56053b64c09c5a03017dd78b58daa69f07feea047a8","abstract_canon_sha256":"fbae53800de59999e383dbc0a4ccc317c60a66650be3ea3997412f092dd60f01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:22.670705Z","signature_b64":"t5SLhmjSqut/wJTfRDDp8DPH8euLtGAp9TcXHUQVxO+C036b0zqfUPE4IIMRSXH1/ria54VA5kwExfdgKHwSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecf19a408039465268d45dd414fc78eea36a9ab9bc22ec37979dc1e78b56121","last_reissued_at":"2026-07-05T11:03:22.670144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:22.670144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ghaith Bany Hamad, Haoxing Ren, Syed Suhaib, Yunsheng Bai","submitted_at":"2025-03-24T21:53:37Z","abstract_excerpt":"Generating SystemVerilog Assertions (SVAs) from natural language specifications remains a major challenge in formal verification (FV) due to the inherent ambiguity and incompleteness of specifications. Existing LLM-based approaches, such as AssertLLM, focus on extracting information solely from specification documents, often failing to capture essential internal signal interactions and design details present in the RTL code, leading to incomplete or incorrect assertions. We propose a novel approach that constructs a Knowledge Graph (KG) from both specifications and RTL, using a hardware-specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19174","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/2503.19174/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":"2503.19174","created_at":"2026-07-05T11:03:22.670204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19174v2","created_at":"2026-07-05T11:03:22.670204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19174","created_at":"2026-07-05T11:03:22.670204+00:00"},{"alias_kind":"pith_short_12","alias_value":"73HRTJAIAOKG","created_at":"2026-07-05T11:03:22.670204+00:00"},{"alias_kind":"pith_short_16","alias_value":"73HRTJAIAOKGKJUN","created_at":"2026-07-05T11:03:22.670204+00:00"},{"alias_kind":"pith_short_8","alias_value":"73HRTJAI","created_at":"2026-07-05T11:03:22.670204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21451","citing_title":"Closing the Loop on LLM-Generated RTL Assertions with Quality-Aware Formal Verification","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08976","citing_title":"RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21451","citing_title":"Closing the Loop on LLM-Generated RTL Assertions with Quality-Aware Formal Verification","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08932","citing_title":"From Indiscriminate to Targeted: Efficient RTL Verification via Functionally Key Signal-Driven LLM Assertion Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06607","citing_title":"CoverAssert: Iterative LLM Assertion Generation Driven by Functional Coverage via Syntax-Semantic Representations","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00058","citing_title":"Autoformalizing Memory Specifications with Agents","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3","json":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3.json","graph_json":"https://pith.science/api/pith-number/73HRTJAIAOKGKJUNIXOUCT6HR3/graph.json","events_json":"https://pith.science/api/pith-number/73HRTJAIAOKGKJUNIXOUCT6HR3/events.json","paper":"https://pith.science/paper/73HRTJAI"},"agent_actions":{"view_html":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3","download_json":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3.json","view_paper":"https://pith.science/paper/73HRTJAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19174&json=true","fetch_graph":"https://pith.science/api/pith-number/73HRTJAIAOKGKJUNIXOUCT6HR3/graph.json","fetch_events":"https://pith.science/api/pith-number/73HRTJAIAOKGKJUNIXOUCT6HR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3/action/storage_attestation","attest_author":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3/action/author_attestation","sign_citation":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3/action/citation_signature","submit_replication":"https://pith.science/pith/73HRTJAIAOKGKJUNIXOUCT6HR3/action/replication_record"}},"created_at":"2026-07-05T11:03:22.670204+00:00","updated_at":"2026-07-05T11:03:22.670204+00:00"}