{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OYVD2QXRUDKPOS27WH4HUZDWPU","short_pith_number":"pith:OYVD2QXR","schema_version":"1.0","canonical_sha256":"762a3d42f1a0d4f74b5fb1f87a64767d17870ed92dac084b9c6b0b9e3302fb55","source":{"kind":"arxiv","id":"2608.06778","version":1},"attestation_state":"computed","paper":{"title":"Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Jiayun Zhang, Junshen Xu, Yi Fan, Zejun Xie","submitted_at":"2026-08-07T03:52:33Z","abstract_excerpt":"Mapping cyber threat intelligence (CTI) text to MITRE ATT&CK techniques is essential for structured threat analysis, yet manual annotation is costly and does not scale. The ATT&CK taxonomy comprises several hundred attack techniques, and a single CTI passage may describe multiple techniques, making accurate and complete extraction challenging. Existing automated approaches fall short in different ways: multi-label classifiers struggle with severe class imbalance and the large label space, while LLM-based methods--retrieval pipelines and fine-tuned generators--optimize token-level objectives th"},"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":"2608.06778","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-07T03:52:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0bbaa42acc31de4c283ca801e1105d48529cba31647a566380c96312d986b080","abstract_canon_sha256":"6dbed5c888e86db654f34953d3d4803783d0027a3e5a5f5632aaf70943968eea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:12:00.680420Z","signature_b64":"dHYtmOARRqftmZ9i55da2KnY3Bj++tJwN5LPyiDFlnJj7OKx9X7kujovi9jZT2aFjGGvWJfjzNlDR0vMVLTQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"762a3d42f1a0d4f74b5fb1f87a64767d17870ed92dac084b9c6b0b9e3302fb55","last_reissued_at":"2026-08-10T01:12:00.677901Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:12:00.677901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CR","authors_text":"Jiayun Zhang, Junshen Xu, Yi Fan, Zejun Xie","submitted_at":"2026-08-07T03:52:33Z","abstract_excerpt":"Mapping cyber threat intelligence (CTI) text to MITRE ATT&CK techniques is essential for structured threat analysis, yet manual annotation is costly and does not scale. The ATT&CK taxonomy comprises several hundred attack techniques, and a single CTI passage may describe multiple techniques, making accurate and complete extraction challenging. Existing automated approaches fall short in different ways: multi-label classifiers struggle with severe class imbalance and the large label space, while LLM-based methods--retrieval pipelines and fine-tuned generators--optimize token-level objectives th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06778","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/2608.06778/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":"2608.06778","created_at":"2026-08-10T01:12:00.679006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06778v1","created_at":"2026-08-10T01:12:00.679006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06778","created_at":"2026-08-10T01:12:00.679006+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYVD2QXRUDKP","created_at":"2026-08-10T01:12:00.679006+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYVD2QXRUDKPOS27","created_at":"2026-08-10T01:12:00.679006+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYVD2QXR","created_at":"2026-08-10T01:12:00.679006+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/OYVD2QXRUDKPOS27WH4HUZDWPU","json":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU.json","graph_json":"https://pith.science/api/pith-number/OYVD2QXRUDKPOS27WH4HUZDWPU/graph.json","events_json":"https://pith.science/api/pith-number/OYVD2QXRUDKPOS27WH4HUZDWPU/events.json","paper":"https://pith.science/paper/OYVD2QXR"},"agent_actions":{"view_html":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU","download_json":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU.json","view_paper":"https://pith.science/paper/OYVD2QXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06778&json=true","fetch_graph":"https://pith.science/api/pith-number/OYVD2QXRUDKPOS27WH4HUZDWPU/graph.json","fetch_events":"https://pith.science/api/pith-number/OYVD2QXRUDKPOS27WH4HUZDWPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU/action/storage_attestation","attest_author":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU/action/author_attestation","sign_citation":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU/action/citation_signature","submit_replication":"https://pith.science/pith/OYVD2QXRUDKPOS27WH4HUZDWPU/action/replication_record"}},"created_at":"2026-08-10T01:12:00.679006+00:00","updated_at":"2026-08-10T01:12:00.679006+00:00"}