{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:46UDHJFMM4X7VVDSPVUG55YAMG","short_pith_number":"pith:46UDHJFM","schema_version":"1.0","canonical_sha256":"e7a833a4ac672ffad4727d686ef700619a060aeb8f0aa79fcd2a681353cb4b8a","source":{"kind":"arxiv","id":"2512.00517","version":3},"attestation_state":"computed","paper":{"title":"No-Regret Gaussian Process Optimization of Time-Varying Functions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Andrea Simonetto, Eliabelle Mauduit, Elo\\\"ise Berthier","submitted_at":"2025-11-29T15:22:30Z","abstract_excerpt":"Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings. However, for time-varying objectives, no-regret is unattainable under pure bandit feedback unless strong and often unrealistic assumptions are imposed. We propose a novel method for optimizing time-varying rewards in the frequentist setting, where the objective has bounded RKHS norm almost surely. Time variations are captured through uncertainty injection, enabling heteroscedastic Gaussian process re"},"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":"2512.00517","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-11-29T15:22:30Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"864830efe2d3d9061668815ceb576ac8c29549b8db00beeb7dcf762aa5168334","abstract_canon_sha256":"4c0d27d243c269edc35f35a098a4622f45dda2721241c9d4f4c1b8de53440c70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:19:08.590571Z","signature_b64":"OHfYif3JJAnyUMbwZuXz9ysvylD5MpYSH/XkPrKS8gBmKLi2XaM9s0w1/2PfN6FppI4hLRoFkwuJWplWBATQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a833a4ac672ffad4727d686ef700619a060aeb8f0aa79fcd2a681353cb4b8a","last_reissued_at":"2026-07-08T01:19:08.590038Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:19:08.590038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No-Regret Gaussian Process Optimization of Time-Varying Functions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Andrea Simonetto, Eliabelle Mauduit, Elo\\\"ise Berthier","submitted_at":"2025-11-29T15:22:30Z","abstract_excerpt":"Sequential optimization of black-box functions from noisy evaluations has been widely studied, with Gaussian Process bandit algorithms such as GP-UCB guaranteeing no-regret in stationary settings. However, for time-varying objectives, no-regret is unattainable under pure bandit feedback unless strong and often unrealistic assumptions are imposed. We propose a novel method for optimizing time-varying rewards in the frequentist setting, where the objective has bounded RKHS norm almost surely. Time variations are captured through uncertainty injection, enabling heteroscedastic Gaussian process re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.00517","kind":"arxiv","version":3},"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/2512.00517/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":"2512.00517","created_at":"2026-07-08T01:19:08.590101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.00517v3","created_at":"2026-07-08T01:19:08.590101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00517","created_at":"2026-07-08T01:19:08.590101+00:00"},{"alias_kind":"pith_short_12","alias_value":"46UDHJFMM4X7","created_at":"2026-07-08T01:19:08.590101+00:00"},{"alias_kind":"pith_short_16","alias_value":"46UDHJFMM4X7VVDS","created_at":"2026-07-08T01:19:08.590101+00:00"},{"alias_kind":"pith_short_8","alias_value":"46UDHJFM","created_at":"2026-07-08T01:19:08.590101+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/46UDHJFMM4X7VVDSPVUG55YAMG","json":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG.json","graph_json":"https://pith.science/api/pith-number/46UDHJFMM4X7VVDSPVUG55YAMG/graph.json","events_json":"https://pith.science/api/pith-number/46UDHJFMM4X7VVDSPVUG55YAMG/events.json","paper":"https://pith.science/paper/46UDHJFM"},"agent_actions":{"view_html":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG","download_json":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG.json","view_paper":"https://pith.science/paper/46UDHJFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.00517&json=true","fetch_graph":"https://pith.science/api/pith-number/46UDHJFMM4X7VVDSPVUG55YAMG/graph.json","fetch_events":"https://pith.science/api/pith-number/46UDHJFMM4X7VVDSPVUG55YAMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG/action/storage_attestation","attest_author":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG/action/author_attestation","sign_citation":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG/action/citation_signature","submit_replication":"https://pith.science/pith/46UDHJFMM4X7VVDSPVUG55YAMG/action/replication_record"}},"created_at":"2026-07-08T01:19:08.590101+00:00","updated_at":"2026-07-08T01:19:08.590101+00:00"}