{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F5JPWDPMA7VA75DVQFQFXQ63J2","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":"039e70f6c3b5745a7a9436b905dcdd38064f24b0ee9a4de85dd59d07fe403d8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T06:00:30Z","title_canon_sha256":"38c8b8a5c1fe9582a6199dc276bb5ce01072553e3a73de0185bb14269c9f179e"},"schema_version":"1.0","source":{"id":"2604.12325","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.12325","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"2604.12325v2","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.12325","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"F5JPWDPMA7VA","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"pith_short_16","alias_value":"F5JPWDPMA7VA75DV","created_at":"2026-05-20T00:03:11Z"},{"alias_kind":"pith_short_8","alias_value":"F5JPWDPM","created_at":"2026-05-20T00:03:11Z"}],"graph_snapshots":[{"event_id":"sha256:dda73ea045b807c8866919c9315ee70d0cf234ee809aa2617500398566bde032","target":"graph","created_at":"2026-05-20T00:03:11Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Across diverse continuous and discrete offline optimization benchmarks, OptBias consistently outperforms state-of-the-art baselines in small data regimes."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That optimization bias learned from Gaussian process synthetic tasks will transfer to and improve ranking on real-world small datasets whose underlying functions may differ substantially from the GP prior."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"OptBias meta-learns reusable optimization bias from Gaussian process synthetic tasks to improve surrogate ranking performance on small offline black-box optimization datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Meta-learning optimization bias from Gaussian process synthetic tasks improves surrogate ranking for offline black-box optimization in small data regimes."}],"snapshot_sha256":"33649d8ebba7d58af908ee845c49471367c2fc7be94185a07b4c2011cd81f9d0"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.12325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of offline black-box optimization, where the goal is to discover optimal designs (e.g., molecules or materials) from past experimental data. A key challenge in this setting is data scarcity: in many scientific applications, only small or poor-quality datasets are available, which severely limits the effectiveness of existing algorithms. Prior work has theoretically and empirically shown that performance of offline optimization algorithms depends on how well the surrogate model captures the optimization bias (i.e., ability to rank input designs correctly), which is chall","authors_text":"Azza Fadhel, Jana Doppa, The Hung Tran, Trong Nghia Hoang","cross_cats":["cs.AI"],"headline":"Meta-learning optimization bias from Gaussian process synthetic tasks improves surrogate ranking for offline black-box optimization in small data regimes.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T06:00:30Z","title":"Black-Box Optimization From Small Offline Datasets via Meta Learning with Synthetic Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.12325","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:00:34.263942Z","id":"d7bfbbe7-ef52-47e4-8d7a-2a7df439f418","model_set":{"reader":"grok-4.3"},"one_line_summary":"OptBias meta-learns reusable optimization bias from Gaussian process synthetic tasks to improve surrogate ranking performance on small offline black-box optimization datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Meta-learning optimization bias from Gaussian process synthetic tasks improves surrogate ranking for offline black-box optimization in small data regimes.","strongest_claim":"Across diverse continuous and discrete offline optimization benchmarks, OptBias consistently outperforms state-of-the-art baselines in small data regimes.","weakest_assumption":"That optimization bias learned from Gaussian process synthetic tasks will transfer to and improve ranking on real-world small datasets whose underlying functions may differ substantially from the GP prior."}},"verdict_id":"d7bfbbe7-ef52-47e4-8d7a-2a7df439f418"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c14de4fad3473eb1c7c8b04ec394341aa0007d2f98ca7098bb0f2a9231191279","target":"record","created_at":"2026-05-20T00:03:11Z","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":"039e70f6c3b5745a7a9436b905dcdd38064f24b0ee9a4de85dd59d07fe403d8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-14T06:00:30Z","title_canon_sha256":"38c8b8a5c1fe9582a6199dc276bb5ce01072553e3a73de0185bb14269c9f179e"},"schema_version":"1.0","source":{"id":"2604.12325","kind":"arxiv","version":2}},"canonical_sha256":"2f52fb0dec07ea0ff47581605bc3db4eac0faeb75a164817758560f6ea13f3e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f52fb0dec07ea0ff47581605bc3db4eac0faeb75a164817758560f6ea13f3e1","first_computed_at":"2026-05-20T00:03:11.219849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:11.219849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PubqLjQj4a1k6ij+r8ON3ahLxbXLHd3R32o9ZFngG1CBkjgS5w0LtuBrDTwrZoDCEnBD0PQStuXZc7urp79ZAg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:11.220851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.12325","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c14de4fad3473eb1c7c8b04ec394341aa0007d2f98ca7098bb0f2a9231191279","sha256:dda73ea045b807c8866919c9315ee70d0cf234ee809aa2617500398566bde032"],"state_sha256":"e7cad6691eeb7137845c3d10862c55354d598343096faf9974af2e4bcc848543"}