{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OVCYLFVBDJXXZCZZN4EYQ2IDXB","short_pith_number":"pith:OVCYLFVB","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"},"canonical_sha256":"75458596a11a6f7c8b396f09886903b86da998f1b4e7545caf9c72f3bd77ae87","source":{"kind":"arxiv","id":"2604.27601","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27601","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27601v2","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27601","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"OVCYLFVBDJXX","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"OVCYLFVBDJXXZCZZ","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"OVCYLFVB","created_at":"2026-05-29T01:05:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OVCYLFVBDJXXZCZZN4EYQ2IDXB","target":"record","payload":{"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"},"canonical_sha256":"75458596a11a6f7c8b396f09886903b86da998f1b4e7545caf9c72f3bd77ae87","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"},"source_kind":"arxiv","source_id":"2604.27601","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/6evAEXe00KwQsX69pzzmaPA7SCTDj8fXrlkRQ8hSmOlcGx0UUY3/Pff5GaHSZybb2MSqX2DUeuH5oudg6+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:13.896153Z"},"content_sha256":"653493efbca775c0805f7866356a02e8302e5e96dd0ace2c6945cde2b50af76c","schema_version":"1.0","event_id":"sha256:653493efbca775c0805f7866356a02e8302e5e96dd0ace2c6945cde2b50af76c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OVCYLFVBDJXXZCZZN4EYQ2IDXB","target":"graph","payload":{"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"},"verdict_id":"694042aa-0560-4470-ac65-4b76bebe720c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qYw2WXMCxw6gJDgEZOkkdfW9x4KrNdr19DOSOC0tV2GZXF7TCaeNcszueas7Z8nbxv+m4UL7qxUNpeEZAX+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:51:13.897157Z"},"content_sha256":"d3b9185f329b2d2f3913f1b1c95d47f6948ceb20907cfe65b84291677efd3845","schema_version":"1.0","event_id":"sha256:d3b9185f329b2d2f3913f1b1c95d47f6948ceb20907cfe65b84291677efd3845"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/bundle.json","state_url":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T18:51:13Z","links":{"resolver":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB","bundle":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/bundle.json","state":"https://pith.science/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVCYLFVBDJXXZCZZN4EYQ2IDXB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OVCYLFVBDJXXZCZZN4EYQ2IDXB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"edb7636e7880f74ba2e2f88704e72a3fe328195399bac0b9163e945f74d19799","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-04-30T08:50:03Z","title_canon_sha256":"19fd408c5b174f7abe71432440bdb5ed2972bd9b814f2c16f2f57ac9923dfa10"},"schema_version":"1.0","source":{"id":"2604.27601","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27601","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27601v2","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27601","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"OVCYLFVBDJXX","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"OVCYLFVBDJXXZCZZ","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"OVCYLFVB","created_at":"2026-05-29T01:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:d3b9185f329b2d2f3913f1b1c95d47f6948ceb20907cfe65b84291677efd3845","target":"graph","created_at":"2026-05-29T01:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"instruction tuning on SecGoal enables compact models with 7B/9B parameters to achieve F1-scores above 80%, substantially outperforming larger general-purpose models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The expert-annotated security goals in the SecGoal benchmark are accurate, unbiased, and sufficient to train models that generalize to new protocol documents."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"b0ed20d17053656fd1d59c739184d666e6b4e2c00b42150120523bd9ae6838aa"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2604.27601/integrity.json","findings":[],"snapshot_sha256":"6e079c321a28a812d1624f4d253d9235e6943c257661e6cfa8b1393691da140b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Jia, Dawei Huang, Haonan Feng, Hui Li, Jingjing Guan, Xiangdong Li, Yueshuang Jiao","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-04-30T08:50:03Z","title":"SecGoal: A Benchmark for Extracting Formalizable Security Goals from Protocol Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27601","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T07:21:23.527521Z","id":"694042aa-0560-4470-ac65-4b76bebe720c","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"694042aa-0560-4470-ac65-4b76bebe720c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:653493efbca775c0805f7866356a02e8302e5e96dd0ace2c6945cde2b50af76c","target":"record","created_at":"2026-05-29T01:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"edb7636e7880f74ba2e2f88704e72a3fe328195399bac0b9163e945f74d19799","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-04-30T08:50:03Z","title_canon_sha256":"19fd408c5b174f7abe71432440bdb5ed2972bd9b814f2c16f2f57ac9923dfa10"},"schema_version":"1.0","source":{"id":"2604.27601","kind":"arxiv","version":2}},"canonical_sha256":"75458596a11a6f7c8b396f09886903b86da998f1b4e7545caf9c72f3bd77ae87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75458596a11a6f7c8b396f09886903b86da998f1b4e7545caf9c72f3bd77ae87","first_computed_at":"2026-05-29T01:05:10.997628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:10.997628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RIPYKKzT0pkpzPBAnLqNnKsHZlLCl2hzfw6iknpoKJfp1NcZKXlYN94iY+yhiyU9oVTL5m+kHHh28rFzUjXwDg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:10.998184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27601","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:653493efbca775c0805f7866356a02e8302e5e96dd0ace2c6945cde2b50af76c","sha256:d3b9185f329b2d2f3913f1b1c95d47f6948ceb20907cfe65b84291677efd3845"],"state_sha256":"8eadfdd7e3d0160a02da785050374b90c47ce59d21ee391a8443403bb60ec4c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yly1eWK1DuG5+4OQqrnqWQ7KLItmSbIjAjedVvi2XFRMmVVEN+N13+IceM7eKNy9bvnAPRcS21g7ZO6tV0VaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:51:13.903074Z","bundle_sha256":"76e0ee64491559d65bb1139e94f8a9717a01741effe2013019c257bed5471381"}}