{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2WKPANPMKJ3MUIMQYC4DBCZPHO","short_pith_number":"pith:2WKPANPM","schema_version":"1.0","canonical_sha256":"d594f035ec5276ca2190c0b8308b2f3bb9cffc41a930008fca6d4eaaed22f525","source":{"kind":"arxiv","id":"2607.05001","version":1},"attestation_state":"computed","paper":{"title":"TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.CR","authors_text":"Gregory Blanc, Mouhamed Amine Bouchiha","submitted_at":"2026-07-06T12:41:11Z","abstract_excerpt":"Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning. Cybersecurity Knowledge Graphs (CSKGs) provide a structured representation of adversarial entities, actions, and relations, but constructing such graphs from free-text CTI remains a challenge. Recent approaches rely on monolithic Large Language Models (LLMs) to perform end-to-end extraction and completion, leading to high cost, limited controllability, and unstable performance. This paper introduces TACTIC-KG, an agentic fra"},"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":"2607.05001","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-06T12:41:11Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"f4a1a21f93df866529ae93318c009b10ed6eebc6e0d83ab2d7c1a41b0c0afea8","abstract_canon_sha256":"72828d6874bc278d453b95be889be07183d14fb6047e7f26e1203551e4346db5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:20:17.724434Z","signature_b64":"1HWH1AwWUDpjU/zFclBs8Jmwlr1wEsSwg/Rxdkc6Vyxv7edOTP4arlep2PGzZOq6g4DHoHNUD2qlLvYdWt/4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d594f035ec5276ca2190c0b8308b2f3bb9cffc41a930008fca6d4eaaed22f525","last_reissued_at":"2026-07-07T02:20:17.723722Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:20:17.723722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.CR","authors_text":"Gregory Blanc, Mouhamed Amine Bouchiha","submitted_at":"2026-07-06T12:41:11Z","abstract_excerpt":"Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning. Cybersecurity Knowledge Graphs (CSKGs) provide a structured representation of adversarial entities, actions, and relations, but constructing such graphs from free-text CTI remains a challenge. Recent approaches rely on monolithic Large Language Models (LLMs) to perform end-to-end extraction and completion, leading to high cost, limited controllability, and unstable performance. This paper introduces TACTIC-KG, an agentic fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05001","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/2607.05001/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":"2607.05001","created_at":"2026-07-07T02:20:17.723823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05001v1","created_at":"2026-07-07T02:20:17.723823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05001","created_at":"2026-07-07T02:20:17.723823+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WKPANPMKJ3M","created_at":"2026-07-07T02:20:17.723823+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WKPANPMKJ3MUIMQ","created_at":"2026-07-07T02:20:17.723823+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WKPANPM","created_at":"2026-07-07T02:20:17.723823+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/2WKPANPMKJ3MUIMQYC4DBCZPHO","json":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO.json","graph_json":"https://pith.science/api/pith-number/2WKPANPMKJ3MUIMQYC4DBCZPHO/graph.json","events_json":"https://pith.science/api/pith-number/2WKPANPMKJ3MUIMQYC4DBCZPHO/events.json","paper":"https://pith.science/paper/2WKPANPM"},"agent_actions":{"view_html":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO","download_json":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO.json","view_paper":"https://pith.science/paper/2WKPANPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05001&json=true","fetch_graph":"https://pith.science/api/pith-number/2WKPANPMKJ3MUIMQYC4DBCZPHO/graph.json","fetch_events":"https://pith.science/api/pith-number/2WKPANPMKJ3MUIMQYC4DBCZPHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO/action/storage_attestation","attest_author":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO/action/author_attestation","sign_citation":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO/action/citation_signature","submit_replication":"https://pith.science/pith/2WKPANPMKJ3MUIMQYC4DBCZPHO/action/replication_record"}},"created_at":"2026-07-07T02:20:17.723823+00:00","updated_at":"2026-07-07T02:20:17.723823+00:00"}