{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OVCYLFVBDJXXZCZZN4EYQ2IDXB","short_pith_number":"pith:OVCYLFVB","schema_version":"1.0","canonical_sha256":"75458596a11a6f7c8b396f09886903b86da998f1b4e7545caf9c72f3bd77ae87","source":{"kind":"arxiv","id":"2604.27601","version":2},"attestation_state":"computed","paper":{"title":"SecGoal: A Benchmark for Extracting Formalizable Security Goals from Protocol Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Instruction tuning on SecGoal lets 7B and 9B models extract security goals from protocol documents at over 80% F1 while larger general models fall below 15% precision.","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bo Jia, Dawei Huang, Haonan Feng, Hui Li, Jingjing Guan, Xiangdong Li, Yueshuang Jiao","submitted_at":"2026-04-30T08:50:03Z","abstract_excerpt":"Formal verification provides rigorous guarantees for cryptographic security, yet extracting formalizable security goals from natural-language protocol documents remains largely manual. We introduce SecGoal, a dedicated expert-annotated dataset and benchmark for extracting formalizable security goal statements from protocol documents, covering 15 widely deployed protocols, together with AIFG, a schema- and flow-conditioned framework for structured formal security property generation. Our evaluation shows that frontier and large LLMs achieve high property recall but low extraction precision beca"},"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":"2604.27601","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-04-30T08:50:03Z","cross_cats_sorted":[],"title_canon_sha256":"19fd408c5b174f7abe71432440bdb5ed2972bd9b814f2c16f2f57ac9923dfa10","abstract_canon_sha256":"edb7636e7880f74ba2e2f88704e72a3fe328195399bac0b9163e945f74d19799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:10.998184Z","signature_b64":"RIPYKKzT0pkpzPBAnLqNnKsHZlLCl2hzfw6iknpoKJfp1NcZKXlYN94iY+yhiyU9oVTL5m+kHHh28rFzUjXwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75458596a11a6f7c8b396f09886903b86da998f1b4e7545caf9c72f3bd77ae87","last_reissued_at":"2026-05-29T01:05:10.997628Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:10.997628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SecGoal: A Benchmark for Extracting Formalizable Security Goals from Protocol Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Instruction tuning on SecGoal lets 7B and 9B models extract security goals from protocol documents at over 80% F1 while larger general models fall below 15% precision.","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bo Jia, Dawei Huang, Haonan Feng, Hui Li, Jingjing Guan, Xiangdong Li, Yueshuang Jiao","submitted_at":"2026-04-30T08:50:03Z","abstract_excerpt":"Formal verification provides rigorous guarantees for cryptographic security, yet extracting formalizable security goals from natural-language protocol documents remains largely manual. We introduce SecGoal, a dedicated expert-annotated dataset and benchmark for extracting formalizable security goal statements from protocol documents, covering 15 widely deployed protocols, together with AIFG, a schema- and flow-conditioned framework for structured formal security property generation. Our evaluation shows that frontier and large LLMs achieve high property recall but low extraction precision beca"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"instruction tuning on SecGoal enables compact models with 7B/9B parameters to achieve F1-scores above 80%, substantially outperforming larger general-purpose models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The expert-annotated security goals in the SecGoal benchmark are accurate, unbiased, and sufficient to train models that generalize to new protocol documents.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper presents SecGoal, the first expert-annotated benchmark for security goal extraction from protocol documents, and demonstrates that fine-tuned 7B/9B parameter models achieve over 80% F1 score, outperforming larger general LLMs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Instruction tuning on SecGoal lets 7B and 9B models extract security goals from protocol documents at over 80% F1 while larger general models fall below 15% precision.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b0ed20d17053656fd1d59c739184d666e6b4e2c00b42150120523bd9ae6838aa"},"source":{"id":"2604.27601","kind":"arxiv","version":2},"verdict":{"id":"694042aa-0560-4470-ac65-4b76bebe720c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T07:21:23.527521Z","strongest_claim":"instruction tuning on SecGoal enables compact models with 7B/9B parameters to achieve F1-scores above 80%, substantially outperforming larger general-purpose models.","one_line_summary":"The paper presents SecGoal, the first expert-annotated benchmark for security goal extraction from protocol documents, and demonstrates that fine-tuned 7B/9B parameter models achieve over 80% F1 score, outperforming larger general LLMs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The expert-annotated security goals in the SecGoal benchmark are accurate, unbiased, and sufficient to train models that generalize to new protocol documents.","pith_extraction_headline":"Instruction tuning on SecGoal lets 7B and 9B models extract security goals from protocol documents at over 80% F1 while larger general models fall below 15% precision."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.27601/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T21:43:41.392900Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:04:00.337887Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6e079c321a28a812d1624f4d253d9235e6943c257661e6cfa8b1393691da140b"},"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":"2604.27601","created_at":"2026-05-29T01:05:10.997704+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.27601v2","created_at":"2026-05-29T01:05:10.997704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27601","created_at":"2026-05-29T01:05:10.997704+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVCYLFVBDJXX","created_at":"2026-05-29T01:05:10.997704+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVCYLFVBDJXXZCZZ","created_at":"2026-05-29T01:05:10.997704+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVCYLFVB","created_at":"2026-05-29T01:05:10.997704+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/OVCYLFVBDJXXZCZZN4EYQ2IDXB","json":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB.json","graph_json":"https://pith.science/api/pith-number/OVCYLFVBDJXXZCZZN4EYQ2IDXB/graph.json","events_json":"https://pith.science/api/pith-number/OVCYLFVBDJXXZCZZN4EYQ2IDXB/events.json","paper":"https://pith.science/paper/OVCYLFVB"},"agent_actions":{"view_html":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB","download_json":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB.json","view_paper":"https://pith.science/paper/OVCYLFVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.27601&json=true","fetch_graph":"https://pith.science/api/pith-number/OVCYLFVBDJXXZCZZN4EYQ2IDXB/graph.json","fetch_events":"https://pith.science/api/pith-number/OVCYLFVBDJXXZCZZN4EYQ2IDXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/action/storage_attestation","attest_author":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/action/author_attestation","sign_citation":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/action/citation_signature","submit_replication":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/action/replication_record"}},"created_at":"2026-05-29T01:05:10.997704+00:00","updated_at":"2026-05-29T01:05:10.997704+00:00"}