{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4UVMQWVSMMU7BLVM3H5PVOZI77","short_pith_number":"pith:4UVMQWVS","schema_version":"1.0","canonical_sha256":"e52ac85ab26329f0aeacd9fafabb28ffc2f0292ac7ee8175f141fd0bc6b79aac","source":{"kind":"arxiv","id":"2509.10983","version":1},"attestation_state":"computed","paper":{"title":"Strategic Cyber Defense via Reinforcement Learning-Guided Combinatorial Auctions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Mai Pham, Peter Chin, Vikrant Vaze","submitted_at":"2025-09-13T21:08:01Z","abstract_excerpt":"Cyber defense operations increasingly require long-term strategic planning under uncertainty and resource constraints. We propose a new use of combinatorial auctions for allocating defensive action bundles in a realistic cyber environment, using host-specific valuations derived from reinforcement learning (RL) Q-values. These Q-values encode long-term expected utility, allowing upstream planning. We train CAFormer, a differentiable Transformer-based auction mechanism, to produce allocations that are approximately incentive-compatible under misreporting. Rather than benchmarking against existin"},"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":"2509.10983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2025-09-13T21:08:01Z","cross_cats_sorted":[],"title_canon_sha256":"3c124f178f934f5b3dd98f3a3636ec6b8f81842ea8fb3af2e37fc90b9745c28c","abstract_canon_sha256":"9aca3d3fba87a68c2b17c0996893f8b27cc4a97ae3363975d3d3987e8a8246a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:31.483490Z","signature_b64":"ITgPejKGG7zkOyOnCrbT68tUlYSPGOfiEEjM6hGAIGJsHHa/bV2UHoovyNJg4R5wVssR6rHHEgavY9DVnVCPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e52ac85ab26329f0aeacd9fafabb28ffc2f0292ac7ee8175f141fd0bc6b79aac","last_reissued_at":"2026-07-05T12:11:31.482925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:31.482925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strategic Cyber Defense via Reinforcement Learning-Guided Combinatorial Auctions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.GT","authors_text":"Mai Pham, Peter Chin, Vikrant Vaze","submitted_at":"2025-09-13T21:08:01Z","abstract_excerpt":"Cyber defense operations increasingly require long-term strategic planning under uncertainty and resource constraints. We propose a new use of combinatorial auctions for allocating defensive action bundles in a realistic cyber environment, using host-specific valuations derived from reinforcement learning (RL) Q-values. These Q-values encode long-term expected utility, allowing upstream planning. We train CAFormer, a differentiable Transformer-based auction mechanism, to produce allocations that are approximately incentive-compatible under misreporting. Rather than benchmarking against existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10983","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/2509.10983/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":"2509.10983","created_at":"2026-07-05T12:11:31.482984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10983v1","created_at":"2026-07-05T12:11:31.482984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10983","created_at":"2026-07-05T12:11:31.482984+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UVMQWVSMMU7","created_at":"2026-07-05T12:11:31.482984+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UVMQWVSMMU7BLVM","created_at":"2026-07-05T12:11:31.482984+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UVMQWVS","created_at":"2026-07-05T12:11:31.482984+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/4UVMQWVSMMU7BLVM3H5PVOZI77","json":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77.json","graph_json":"https://pith.science/api/pith-number/4UVMQWVSMMU7BLVM3H5PVOZI77/graph.json","events_json":"https://pith.science/api/pith-number/4UVMQWVSMMU7BLVM3H5PVOZI77/events.json","paper":"https://pith.science/paper/4UVMQWVS"},"agent_actions":{"view_html":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77","download_json":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77.json","view_paper":"https://pith.science/paper/4UVMQWVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10983&json=true","fetch_graph":"https://pith.science/api/pith-number/4UVMQWVSMMU7BLVM3H5PVOZI77/graph.json","fetch_events":"https://pith.science/api/pith-number/4UVMQWVSMMU7BLVM3H5PVOZI77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77/action/storage_attestation","attest_author":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77/action/author_attestation","sign_citation":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77/action/citation_signature","submit_replication":"https://pith.science/pith/4UVMQWVSMMU7BLVM3H5PVOZI77/action/replication_record"}},"created_at":"2026-07-05T12:11:31.482984+00:00","updated_at":"2026-07-05T12:11:31.482984+00:00"}