{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2ILJJUNV4IUR6HRF4NMX6MDUBZ","short_pith_number":"pith:2ILJJUNV","schema_version":"1.0","canonical_sha256":"d21694d1b5e2291f1e25e3597f30740e654affc242983f27c2e76dcdc1e3eb8c","source":{"kind":"arxiv","id":"2601.23164","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Linear Bandits with Parameter Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alon Peled-Cohen, Daniel Ezer, Yishay Mansour","submitted_at":"2026-01-30T16:47:42Z","abstract_excerpt":"We study the stochastic linear bandits with parameter noise model, in which the reward of action $a$ is $a^\\top \\theta$ where $\\theta$ is sampled i.i.d. We show a regret upper bound of $\\widetilde{O} (\\sqrt{d T \\log (K/\\delta) \\sigma^2_{\\max})}$ for a horizon $T$, general action set of size $K$ of dimension $d$, and where $\\sigma^2_{\\max}$ is the maximal variance of the reward for any action. We further provide a lower bound of $\\widetilde{\\Omega} (d \\sqrt{T \\sigma^2_{\\max}})$ which is tight (up to logarithmic factors) whenever $\\log (K) \\approx d$. For more specific action sets, $\\ell_p$ unit"},"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":"2601.23164","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T16:47:42Z","cross_cats_sorted":[],"title_canon_sha256":"f8df3d84701ddb182a8524cc4b3d04a0c1f77e3f60e129fd86bc91e22c502e09","abstract_canon_sha256":"1e622fa2929d5d8408f3c05d13af072c9120cf7443b4ecdcd4b70108993a757c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:23.953767Z","signature_b64":"nu8VzNXiLo7+5goCn8XWnWGreLz+HZTFPscqeFC+yWOys56cWbrEOxzP+37qEWgrpJ00eBXarXW/YsEDnV2NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d21694d1b5e2291f1e25e3597f30740e654affc242983f27c2e76dcdc1e3eb8c","last_reissued_at":"2026-05-26T01:03:23.953135Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:23.953135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Linear Bandits with Parameter Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alon Peled-Cohen, Daniel Ezer, Yishay Mansour","submitted_at":"2026-01-30T16:47:42Z","abstract_excerpt":"We study the stochastic linear bandits with parameter noise model, in which the reward of action $a$ is $a^\\top \\theta$ where $\\theta$ is sampled i.i.d. We show a regret upper bound of $\\widetilde{O} (\\sqrt{d T \\log (K/\\delta) \\sigma^2_{\\max})}$ for a horizon $T$, general action set of size $K$ of dimension $d$, and where $\\sigma^2_{\\max}$ is the maximal variance of the reward for any action. We further provide a lower bound of $\\widetilde{\\Omega} (d \\sqrt{T \\sigma^2_{\\max}})$ which is tight (up to logarithmic factors) whenever $\\log (K) \\approx d$. For more specific action sets, $\\ell_p$ unit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23164","kind":"arxiv","version":2},"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/2601.23164/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":"2601.23164","created_at":"2026-05-26T01:03:23.953221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.23164v2","created_at":"2026-05-26T01:03:23.953221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23164","created_at":"2026-05-26T01:03:23.953221+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ILJJUNV4IUR","created_at":"2026-05-26T01:03:23.953221+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ILJJUNV4IUR6HRF","created_at":"2026-05-26T01:03:23.953221+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ILJJUNV","created_at":"2026-05-26T01:03:23.953221+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/2ILJJUNV4IUR6HRF4NMX6MDUBZ","json":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ.json","graph_json":"https://pith.science/api/pith-number/2ILJJUNV4IUR6HRF4NMX6MDUBZ/graph.json","events_json":"https://pith.science/api/pith-number/2ILJJUNV4IUR6HRF4NMX6MDUBZ/events.json","paper":"https://pith.science/paper/2ILJJUNV"},"agent_actions":{"view_html":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ","download_json":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ.json","view_paper":"https://pith.science/paper/2ILJJUNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.23164&json=true","fetch_graph":"https://pith.science/api/pith-number/2ILJJUNV4IUR6HRF4NMX6MDUBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2ILJJUNV4IUR6HRF4NMX6MDUBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ/action/storage_attestation","attest_author":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ/action/author_attestation","sign_citation":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ/action/citation_signature","submit_replication":"https://pith.science/pith/2ILJJUNV4IUR6HRF4NMX6MDUBZ/action/replication_record"}},"created_at":"2026-05-26T01:03:23.953221+00:00","updated_at":"2026-05-26T01:03:23.953221+00:00"}