{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UIF6NSQIAHHB4GSL53SW2YXU4J","short_pith_number":"pith:UIF6NSQI","schema_version":"1.0","canonical_sha256":"a20be6ca0801ce1e1a4beee56d62f4e26b817b73f30fce7779910e752b0188c0","source":{"kind":"arxiv","id":"2605.20962","version":1},"attestation_state":"computed","paper":{"title":"No-regret optimization of time-varying bilevel problems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Andrea Simonetto, Eliabelle Mauduit, Elo\\\"ise Berthier","submitted_at":"2026-05-20T09:48:46Z","abstract_excerpt":"Bilevel optimization problems arise in many applications where decisions must account for the optimal response of another system, such as in game-theoretic settings. However, these problems are notoriously challenging, as even linear bilevel programs are strongly NP-hard. In this work, we consider bilevel optimization with a known upper-level objective and an unknown, potentially time-varying lower-level response, accessible only through noisy zeroth-order observations. We propose W-SparQ-BL, a Bayesian optimization framework that models the lower-level mapping using multi-output Gaussian proc"},"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":"2605.20962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-20T09:48:46Z","cross_cats_sorted":[],"title_canon_sha256":"bc2fb799a579273183f5ed15ea8d45600b1db5373fc3ab7672405f44256cada2","abstract_canon_sha256":"e78d9a315f2cb75334814925cc3ac14a7b07fb21e32cc503dc1b2a408acab81c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:30.034987Z","signature_b64":"6pR/HUQgIIbC0u6q3x6pz3DrruscrAcxATzOkqjIi4XBFHxRge34ubJ98F3xqVHBJYtPPlEOizWoey9Gz2c6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a20be6ca0801ce1e1a4beee56d62f4e26b817b73f30fce7779910e752b0188c0","last_reissued_at":"2026-05-21T01:05:30.034408Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:30.034408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No-regret optimization of time-varying bilevel problems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Andrea Simonetto, Eliabelle Mauduit, Elo\\\"ise Berthier","submitted_at":"2026-05-20T09:48:46Z","abstract_excerpt":"Bilevel optimization problems arise in many applications where decisions must account for the optimal response of another system, such as in game-theoretic settings. However, these problems are notoriously challenging, as even linear bilevel programs are strongly NP-hard. In this work, we consider bilevel optimization with a known upper-level objective and an unknown, potentially time-varying lower-level response, accessible only through noisy zeroth-order observations. We propose W-SparQ-BL, a Bayesian optimization framework that models the lower-level mapping using multi-output Gaussian proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20962","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/2605.20962/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":"2605.20962","created_at":"2026-05-21T01:05:30.034518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20962v1","created_at":"2026-05-21T01:05:30.034518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20962","created_at":"2026-05-21T01:05:30.034518+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIF6NSQIAHHB","created_at":"2026-05-21T01:05:30.034518+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIF6NSQIAHHB4GSL","created_at":"2026-05-21T01:05:30.034518+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIF6NSQI","created_at":"2026-05-21T01:05:30.034518+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/UIF6NSQIAHHB4GSL53SW2YXU4J","json":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J.json","graph_json":"https://pith.science/api/pith-number/UIF6NSQIAHHB4GSL53SW2YXU4J/graph.json","events_json":"https://pith.science/api/pith-number/UIF6NSQIAHHB4GSL53SW2YXU4J/events.json","paper":"https://pith.science/paper/UIF6NSQI"},"agent_actions":{"view_html":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J","download_json":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J.json","view_paper":"https://pith.science/paper/UIF6NSQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20962&json=true","fetch_graph":"https://pith.science/api/pith-number/UIF6NSQIAHHB4GSL53SW2YXU4J/graph.json","fetch_events":"https://pith.science/api/pith-number/UIF6NSQIAHHB4GSL53SW2YXU4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J/action/storage_attestation","attest_author":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J/action/author_attestation","sign_citation":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J/action/citation_signature","submit_replication":"https://pith.science/pith/UIF6NSQIAHHB4GSL53SW2YXU4J/action/replication_record"}},"created_at":"2026-05-21T01:05:30.034518+00:00","updated_at":"2026-05-21T01:05:30.034518+00:00"}