{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2GGL5GCVGPI5V4ZKKYMJ7TUIV3","short_pith_number":"pith:2GGL5GCV","schema_version":"1.0","canonical_sha256":"d18cbe985533d1daf32a56189fce88aedbd5bf53dc636efebbfffe5e1dd28550","source":{"kind":"arxiv","id":"2006.06790","version":3},"attestation_state":"computed","paper":{"title":"On Frequentist Regret of Linear Thompson Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mohsen Bayati, Nima Hamidi","submitted_at":"2020-06-11T20:19:41Z","abstract_excerpt":"This paper studies the stochastic linear bandit problem, where a decision-maker chooses actions from possibly time-dependent sets of vectors in $\\mathbb{R}^d$ and receives noisy rewards. The objective is to minimize regret, the difference between the cumulative expected reward of the decision-maker and that of an oracle with access to the expected reward of each action, over a sequence of $T$ decisions. Linear Thompson Sampling (LinTS) is a popular Bayesian heuristic, supported by theoretical analysis that shows its Bayesian regret is bounded by $\\widetilde{\\mathcal{O}}(d\\sqrt{T})$, matching m"},"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":"2006.06790","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T20:19:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4f5e81aa10d2af7a2d904f0d7d77beae7959d0456098d28901e43f0f72bdb91e","abstract_canon_sha256":"08a14e0c29790c4fc6f21257551e2bf77de646b797a831f01ee8cf2191f1cb73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:05.368298Z","signature_b64":"fKVRmkqOcNU2OudPNX7aVIpgCC2Z1b0WnWamZlg4BX8/haBZPayE1/D+QklA/jTse+KKSkAERRZUYn+O15N7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d18cbe985533d1daf32a56189fce88aedbd5bf53dc636efebbfffe5e1dd28550","last_reissued_at":"2026-07-05T06:03:05.367749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:05.367749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Frequentist Regret of Linear Thompson Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mohsen Bayati, Nima Hamidi","submitted_at":"2020-06-11T20:19:41Z","abstract_excerpt":"This paper studies the stochastic linear bandit problem, where a decision-maker chooses actions from possibly time-dependent sets of vectors in $\\mathbb{R}^d$ and receives noisy rewards. The objective is to minimize regret, the difference between the cumulative expected reward of the decision-maker and that of an oracle with access to the expected reward of each action, over a sequence of $T$ decisions. Linear Thompson Sampling (LinTS) is a popular Bayesian heuristic, supported by theoretical analysis that shows its Bayesian regret is bounded by $\\widetilde{\\mathcal{O}}(d\\sqrt{T})$, matching m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06790","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/2006.06790/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":"2006.06790","created_at":"2026-07-05T06:03:05.367812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06790v3","created_at":"2026-07-05T06:03:05.367812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06790","created_at":"2026-07-05T06:03:05.367812+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GGL5GCVGPI5","created_at":"2026-07-05T06:03:05.367812+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GGL5GCVGPI5V4ZK","created_at":"2026-07-05T06:03:05.367812+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GGL5GCV","created_at":"2026-07-05T06:03:05.367812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00984","citing_title":"Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates","ref_index":179,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3","json":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3.json","graph_json":"https://pith.science/api/pith-number/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/graph.json","events_json":"https://pith.science/api/pith-number/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/events.json","paper":"https://pith.science/paper/2GGL5GCV"},"agent_actions":{"view_html":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3","download_json":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3.json","view_paper":"https://pith.science/paper/2GGL5GCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06790&json=true","fetch_graph":"https://pith.science/api/pith-number/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/graph.json","fetch_events":"https://pith.science/api/pith-number/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/action/storage_attestation","attest_author":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/action/author_attestation","sign_citation":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/action/citation_signature","submit_replication":"https://pith.science/pith/2GGL5GCVGPI5V4ZKKYMJ7TUIV3/action/replication_record"}},"created_at":"2026-07-05T06:03:05.367812+00:00","updated_at":"2026-07-05T06:03:05.367812+00:00"}