{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3FJTOY4EPCSGK5RPB6L4ECQ7JG","short_pith_number":"pith:3FJTOY4E","schema_version":"1.0","canonical_sha256":"d95337638478a465762f0f97c20a1f49afa9d1cdee60aceb7ff5e52a8f1edf7f","source":{"kind":"arxiv","id":"2607.28460","version":1},"attestation_state":"computed","paper":{"title":"Cybersecurity Detection Classification with Reasoning-enabled Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Alexandru Apostu, Amol Khanna, Chase Helwig, Chase Midler, Cristian Viorel Popa, Diana Bolocan, Edward Raff, Joan Pujol-Roig, Laura Vasilie, Manu Nandan, Michael Brautbar, Mihaela Gaman, Sven Krasser","submitted_at":"2026-07-30T16:22:13Z","abstract_excerpt":"A major issue in Security Operations Centers (SOCs) is alert fatigue, as the number of detections reported is more than staff can triage in a given day. Prior work prompts or fine-tunes large language models (LLMs) to emit a triage label directly, but does not train them to reason about whether a detection is a genuine threat. We train a chain-of-thought (CoT) reasoning-enabled triage classifier on real, human-labeled Windows endpoint detections by combining automated prompt optimization, self-training, and reinforcement learning with verifiable rewards. We find that CoT reasoning also degrade"},"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":"2607.28460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T16:22:13Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"73cadc275c83d404076696c02440f82c95d6afe13798fff167f91d2f6bd88465","abstract_canon_sha256":"66de0167d627bb2809df2df56ad6620bf515eddbb2f896b8925a85d785af7131"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d95337638478a465762f0f97c20a1f49afa9d1cdee60aceb7ff5e52a8f1edf7f","last_reissued_at":"2026-07-31T01:37:41.337155Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:41.337155Z"},"graph_snapshot":{"paper":{"title":"Cybersecurity Detection Classification with Reasoning-enabled Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Alexandru Apostu, Amol Khanna, Chase Helwig, Chase Midler, Cristian Viorel Popa, Diana Bolocan, Edward Raff, Joan Pujol-Roig, Laura Vasilie, Manu Nandan, Michael Brautbar, Mihaela Gaman, Sven Krasser","submitted_at":"2026-07-30T16:22:13Z","abstract_excerpt":"A major issue in Security Operations Centers (SOCs) is alert fatigue, as the number of detections reported is more than staff can triage in a given day. Prior work prompts or fine-tunes large language models (LLMs) to emit a triage label directly, but does not train them to reason about whether a detection is a genuine threat. We train a chain-of-thought (CoT) reasoning-enabled triage classifier on real, human-labeled Windows endpoint detections by combining automated prompt optimization, self-training, and reinforcement learning with verifiable rewards. We find that CoT reasoning also degrade"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28460","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/2607.28460/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":"2607.28460","created_at":"2026-07-31T01:37:41.340305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28460v1","created_at":"2026-07-31T01:37:41.340305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28460","created_at":"2026-07-31T01:37:41.340305+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FJTOY4EPCSG","created_at":"2026-07-31T01:37:41.340305+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FJTOY4EPCSGK5RP","created_at":"2026-07-31T01:37:41.340305+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FJTOY4E","created_at":"2026-07-31T01:37:41.340305+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/3FJTOY4EPCSGK5RPB6L4ECQ7JG","json":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG.json","graph_json":"https://pith.science/api/pith-number/3FJTOY4EPCSGK5RPB6L4ECQ7JG/graph.json","events_json":"https://pith.science/api/pith-number/3FJTOY4EPCSGK5RPB6L4ECQ7JG/events.json","paper":"https://pith.science/paper/3FJTOY4E"},"agent_actions":{"view_html":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG","download_json":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG.json","view_paper":"https://pith.science/paper/3FJTOY4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28460&json=true","fetch_graph":"https://pith.science/api/pith-number/3FJTOY4EPCSGK5RPB6L4ECQ7JG/graph.json","fetch_events":"https://pith.science/api/pith-number/3FJTOY4EPCSGK5RPB6L4ECQ7JG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG/action/storage_attestation","attest_author":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG/action/author_attestation","sign_citation":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG/action/citation_signature","submit_replication":"https://pith.science/pith/3FJTOY4EPCSGK5RPB6L4ECQ7JG/action/replication_record"}},"created_at":"2026-07-31T01:37:41.340305+00:00","updated_at":"2026-07-31T01:37:41.340305+00:00"}