{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:37XGBZ36CEWYVCIHSGZCTQJQRT","short_pith_number":"pith:37XGBZ36","schema_version":"1.0","canonical_sha256":"dfee60e77e112d8a890791b229c1308ccc6f6005af7ec4afa4def8edf7800d1b","source":{"kind":"arxiv","id":"2606.04305","version":1},"attestation_state":"computed","paper":{"title":"Offline-to-Online Learning in Linear Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kushagra Chandak, Toshinori Kitamura, Xiaoqi Tan","submitted_at":"2026-06-03T00:18:46Z","abstract_excerpt":"We study online learning with an additional offline dataset in the stochastic linear bandit setting. Although this problem arises frequently in practice, the offline-to-online tradeoff remains poorly understood in structured environments. We propose a linear bandit algorithm that balances this tradeoff: it relies on offline data during early rounds, and increasingly favors exploration as the horizon grows. We establish regret bounds showing that our method is simultaneously competitive with both purely online and purely offline solutions. In particular, it achieves sublinear regret relative to"},"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":"2606.04305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T00:18:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"253d35ebb9208cd096bed949156476009cc7c522049de9ba6a98c6147966ca38","abstract_canon_sha256":"f1abd74b43e57cc568ee5f5245bbc60c254b9b0d5917b8dfeb7ed5aef5a713ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:02.976548Z","signature_b64":"ah9x4KaNH/c+ME3gWNvfaPj1Na4vpdQVjJci87lvQrh8CmErPSBqMrxgGz1xiWEc33l2+NSd4b9Q8avNJgNBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfee60e77e112d8a890791b229c1308ccc6f6005af7ec4afa4def8edf7800d1b","last_reissued_at":"2026-06-04T01:09:02.976062Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:02.976062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline-to-Online Learning in Linear Bandits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kushagra Chandak, Toshinori Kitamura, Xiaoqi Tan","submitted_at":"2026-06-03T00:18:46Z","abstract_excerpt":"We study online learning with an additional offline dataset in the stochastic linear bandit setting. Although this problem arises frequently in practice, the offline-to-online tradeoff remains poorly understood in structured environments. We propose a linear bandit algorithm that balances this tradeoff: it relies on offline data during early rounds, and increasingly favors exploration as the horizon grows. We establish regret bounds showing that our method is simultaneously competitive with both purely online and purely offline solutions. In particular, it achieves sublinear regret relative to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04305","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/2606.04305/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":"2606.04305","created_at":"2026-06-04T01:09:02.976136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04305v1","created_at":"2026-06-04T01:09:02.976136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04305","created_at":"2026-06-04T01:09:02.976136+00:00"},{"alias_kind":"pith_short_12","alias_value":"37XGBZ36CEWY","created_at":"2026-06-04T01:09:02.976136+00:00"},{"alias_kind":"pith_short_16","alias_value":"37XGBZ36CEWYVCIH","created_at":"2026-06-04T01:09:02.976136+00:00"},{"alias_kind":"pith_short_8","alias_value":"37XGBZ36","created_at":"2026-06-04T01:09:02.976136+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/37XGBZ36CEWYVCIHSGZCTQJQRT","json":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT.json","graph_json":"https://pith.science/api/pith-number/37XGBZ36CEWYVCIHSGZCTQJQRT/graph.json","events_json":"https://pith.science/api/pith-number/37XGBZ36CEWYVCIHSGZCTQJQRT/events.json","paper":"https://pith.science/paper/37XGBZ36"},"agent_actions":{"view_html":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT","download_json":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT.json","view_paper":"https://pith.science/paper/37XGBZ36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04305&json=true","fetch_graph":"https://pith.science/api/pith-number/37XGBZ36CEWYVCIHSGZCTQJQRT/graph.json","fetch_events":"https://pith.science/api/pith-number/37XGBZ36CEWYVCIHSGZCTQJQRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT/action/storage_attestation","attest_author":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT/action/author_attestation","sign_citation":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT/action/citation_signature","submit_replication":"https://pith.science/pith/37XGBZ36CEWYVCIHSGZCTQJQRT/action/replication_record"}},"created_at":"2026-06-04T01:09:02.976136+00:00","updated_at":"2026-06-04T01:09:02.976136+00:00"}