{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VAOKUHKV4WNMW35WA3FAWQWHGR","short_pith_number":"pith:VAOKUHKV","schema_version":"1.0","canonical_sha256":"a81caa1d55e59acb6fb606ca0b42c7347a7aec46493e7a93e191dbd149c504c5","source":{"kind":"arxiv","id":"2504.03926","version":1},"attestation_state":"computed","paper":{"title":"An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Bruno Sinopoli, Jonathan Gornet, Yilin Mo","submitted_at":"2025-04-04T20:46:35Z","abstract_excerpt":"In stochastic multi-armed bandits, a major problem the learner faces is the trade-off between exploration and exploitation. Recently, exploration-free methods -- methods that commit to the action predicted to return the highest reward -- have been studied from the perspective of linear bandits. In this paper, we introduce a linear bandit setting where the reward is the output of a linear Gaussian dynamical system. Motivated by a problem encountered in hyperparameter optimization for reinforcement learning, where the number of actions is much higher than the number of training iterations, we pr"},"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":"2504.03926","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-04T20:46:35Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"c49f5b133b0522447d270def847a5f442a208e918e69858e243d23eae2869c0a","abstract_canon_sha256":"3c014f900f917debf298f1e1c643135d114513e8e3a5674184dd8be1e19e6929"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:51.358509Z","signature_b64":"MX7E3xFzCtpzUn8pkSPtZC2DfdAU7CBptJWFp8L09LJ+N+8sbUI9SuHLziWoL17VfEzM3cnYztYWH4Mw0uW3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a81caa1d55e59acb6fb606ca0b42c7347a7aec46493e7a93e191dbd149c504c5","last_reissued_at":"2026-07-05T10:44:51.358017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:51.358017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Bruno Sinopoli, Jonathan Gornet, Yilin Mo","submitted_at":"2025-04-04T20:46:35Z","abstract_excerpt":"In stochastic multi-armed bandits, a major problem the learner faces is the trade-off between exploration and exploitation. Recently, exploration-free methods -- methods that commit to the action predicted to return the highest reward -- have been studied from the perspective of linear bandits. In this paper, we introduce a linear bandit setting where the reward is the output of a linear Gaussian dynamical system. Motivated by a problem encountered in hyperparameter optimization for reinforcement learning, where the number of actions is much higher than the number of training iterations, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03926","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/2504.03926/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":"2504.03926","created_at":"2026-07-05T10:44:51.358075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03926v1","created_at":"2026-07-05T10:44:51.358075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03926","created_at":"2026-07-05T10:44:51.358075+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAOKUHKV4WNM","created_at":"2026-07-05T10:44:51.358075+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAOKUHKV4WNMW35W","created_at":"2026-07-05T10:44:51.358075+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAOKUHKV","created_at":"2026-07-05T10:44:51.358075+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/VAOKUHKV4WNMW35WA3FAWQWHGR","json":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR.json","graph_json":"https://pith.science/api/pith-number/VAOKUHKV4WNMW35WA3FAWQWHGR/graph.json","events_json":"https://pith.science/api/pith-number/VAOKUHKV4WNMW35WA3FAWQWHGR/events.json","paper":"https://pith.science/paper/VAOKUHKV"},"agent_actions":{"view_html":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR","download_json":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR.json","view_paper":"https://pith.science/paper/VAOKUHKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03926&json=true","fetch_graph":"https://pith.science/api/pith-number/VAOKUHKV4WNMW35WA3FAWQWHGR/graph.json","fetch_events":"https://pith.science/api/pith-number/VAOKUHKV4WNMW35WA3FAWQWHGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR/action/storage_attestation","attest_author":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR/action/author_attestation","sign_citation":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR/action/citation_signature","submit_replication":"https://pith.science/pith/VAOKUHKV4WNMW35WA3FAWQWHGR/action/replication_record"}},"created_at":"2026-07-05T10:44:51.358075+00:00","updated_at":"2026-07-05T10:44:51.358075+00:00"}