{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3WNPMRHOT5XNOKPQSUPOB2MZ72","short_pith_number":"pith:3WNPMRHO","schema_version":"1.0","canonical_sha256":"dd9af644ee9f6ed729f0951ee0e999feba18eeb463678716ea962caf57a2edcf","source":{"kind":"arxiv","id":"2505.02010","version":1},"attestation_state":"computed","paper":{"title":"Meta-Black-Box-Optimization through Offline Q-function Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Hongshu Guo, Yue-Jiao Gong, Zeyuan Ma, Zhiguang Cao, Zhou Jiang","submitted_at":"2025-05-04T06:41:43Z","abstract_excerpt":"Recent progress in Meta-Black-Box-Optimization (MetaBBO) has demonstrated that using RL to learn a meta-level policy for dynamic algorithm configuration (DAC) over an optimization task distribution could significantly enhance the performance of the low-level BBO algorithm. However, the online learning paradigms in existing works makes the efficiency of MetaBBO problematic. To address this, we propose an offline learning-based MetaBBO framework in this paper, termed Q-Mamba, to attain both effectiveness and efficiency in MetaBBO. Specifically, we first transform DAC task into long-sequence deci"},"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":"2505.02010","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-05-04T06:41:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f49c165aec34a45605cb5570939615b42f2a8ee223ac1f61065a1387f59a32d1","abstract_canon_sha256":"455bef9377c6c2d386ee79cd30c07cb1d701e260d07f5ad5ca85de90de8ec68b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:30.236227Z","signature_b64":"QyVXvZ+4dNJ7Nhc7G73D6K1+jAoS8EM+sU4f9e3kzujwiqWxbmtyp8iVYEUQft3Ts09xka+Cw98lARDaTQYlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd9af644ee9f6ed729f0951ee0e999feba18eeb463678716ea962caf57a2edcf","last_reissued_at":"2026-07-05T10:58:30.235729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:30.235729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Black-Box-Optimization through Offline Q-function Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Hongshu Guo, Yue-Jiao Gong, Zeyuan Ma, Zhiguang Cao, Zhou Jiang","submitted_at":"2025-05-04T06:41:43Z","abstract_excerpt":"Recent progress in Meta-Black-Box-Optimization (MetaBBO) has demonstrated that using RL to learn a meta-level policy for dynamic algorithm configuration (DAC) over an optimization task distribution could significantly enhance the performance of the low-level BBO algorithm. However, the online learning paradigms in existing works makes the efficiency of MetaBBO problematic. To address this, we propose an offline learning-based MetaBBO framework in this paper, termed Q-Mamba, to attain both effectiveness and efficiency in MetaBBO. Specifically, we first transform DAC task into long-sequence deci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02010","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/2505.02010/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":"2505.02010","created_at":"2026-07-05T10:58:30.235789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02010v1","created_at":"2026-07-05T10:58:30.235789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02010","created_at":"2026-07-05T10:58:30.235789+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WNPMRHOT5XN","created_at":"2026-07-05T10:58:30.235789+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WNPMRHOT5XNOKPQ","created_at":"2026-07-05T10:58:30.235789+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WNPMRHO","created_at":"2026-07-05T10:58:30.235789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00862","citing_title":"Meta-Black-Box Optimization with Ensemble Surrogate Modeling for Robustness-Accuracy Trade-off within SAEA","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72","json":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72.json","graph_json":"https://pith.science/api/pith-number/3WNPMRHOT5XNOKPQSUPOB2MZ72/graph.json","events_json":"https://pith.science/api/pith-number/3WNPMRHOT5XNOKPQSUPOB2MZ72/events.json","paper":"https://pith.science/paper/3WNPMRHO"},"agent_actions":{"view_html":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72","download_json":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72.json","view_paper":"https://pith.science/paper/3WNPMRHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02010&json=true","fetch_graph":"https://pith.science/api/pith-number/3WNPMRHOT5XNOKPQSUPOB2MZ72/graph.json","fetch_events":"https://pith.science/api/pith-number/3WNPMRHOT5XNOKPQSUPOB2MZ72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72/action/storage_attestation","attest_author":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72/action/author_attestation","sign_citation":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72/action/citation_signature","submit_replication":"https://pith.science/pith/3WNPMRHOT5XNOKPQSUPOB2MZ72/action/replication_record"}},"created_at":"2026-07-05T10:58:30.235789+00:00","updated_at":"2026-07-05T10:58:30.235789+00:00"}