{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OSUGZGQOWGEVLLRD4L6KJM35RN","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":"49cea4c419be0d3e47a20d307e325ee5984f9a3217313d810fabb3d3d5dbeb30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-03T13:54:41Z","title_canon_sha256":"b613de6ddc12815a3a9ed625f89e1e966e367fa3e8f2791e5083600f9b04ea43"},"schema_version":"1.0","source":{"id":"2512.03805","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.03805","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2512.03805v2","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03805","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"OSUGZGQOWGEV","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"OSUGZGQOWGEVLLRD","created_at":"2026-06-19T16:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"OSUGZGQO","created_at":"2026-06-19T16:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:da5411a6710eb891bc4eb55859cbd4d65da9eb5e45874cec28797265715bec95","target":"graph","created_at":"2026-06-19T16:10:33Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.03805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dynamic Algorithm Configuration (DAC) studies the efficient identification of control policies for parameterized optimization algorithms. Numerous studies leverage Reinforcement Learning (RL) to address DAC challenges; however, applying RL often requires extensive domain expertise. In this work, we conduct a comprehensive study of two deep-RL algorithms--Double Deep Q-Networks (DDQN) and Proximal Policy Optimization (PPO)--for controlling the population size of the $(1+(\\lambda,\\lambda))$-GA on OneMax instances. Although OneMax is structurally simple, learning effective control policies for th","authors_text":"Andr\\'e Biedenkapp, Carola Doerr, Nguyen Dang, Phong Le, Tai Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-03T13:54:41Z","title":"Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+($\\lambda$,$\\lambda$))-GA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03805","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b43d1f1236fcde1ff6023bef83a55f3ffdf4b1f7fe03743b9b6b1daf2ec940f","target":"record","created_at":"2026-06-19T16:10:33Z","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":"49cea4c419be0d3e47a20d307e325ee5984f9a3217313d810fabb3d3d5dbeb30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-03T13:54:41Z","title_canon_sha256":"b613de6ddc12815a3a9ed625f89e1e966e367fa3e8f2791e5083600f9b04ea43"},"schema_version":"1.0","source":{"id":"2512.03805","kind":"arxiv","version":2}},"canonical_sha256":"74a86c9a0eb18955ae23e2fca4b37d8b512fde7c2c54c05b708f5e5682b17ef5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74a86c9a0eb18955ae23e2fca4b37d8b512fde7c2c54c05b708f5e5682b17ef5","first_computed_at":"2026-06-19T16:10:33.037467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:33.037467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icHQk+6cznsVYWjVfDmZN+sKQmrIhdgAza5ZwZLyZG2nUlIyMiHpjAcjEUwOPoOOGgYWwpu8x6GnkdoSssP6AQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:33.037994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.03805","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b43d1f1236fcde1ff6023bef83a55f3ffdf4b1f7fe03743b9b6b1daf2ec940f","sha256:da5411a6710eb891bc4eb55859cbd4d65da9eb5e45874cec28797265715bec95"],"state_sha256":"1cdcc922f1ac66ce7d0f7f7e0dc1530d3306361e15f54ca286156168bb374975"}