{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VAOKUHKV4WNMW35WA3FAWQWHGR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3c014f900f917debf298f1e1c643135d114513e8e3a5674184dd8be1e19e6929","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-04T20:46:35Z","title_canon_sha256":"c49f5b133b0522447d270def847a5f442a208e918e69858e243d23eae2869c0a"},"schema_version":"1.0","source":{"id":"2504.03926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.03926","created_at":"2026-07-05T10:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2504.03926v1","created_at":"2026-07-05T10:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03926","created_at":"2026-07-05T10:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"VAOKUHKV4WNM","created_at":"2026-07-05T10:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"VAOKUHKV4WNMW35W","created_at":"2026-07-05T10:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"VAOKUHKV","created_at":"2026-07-05T10:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:153d6137c29a1d26ca075546b0330e51631bb7410078697f45c77638b9fc2c8c","target":"graph","created_at":"2026-07-05T10:44:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.03926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bruno Sinopoli, Jonathan Gornet, Yilin Mo","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-04T20:46:35Z","title":"An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03926","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:895262fa2643a08dd44803f0e7192b3a9461f5f506b642ce1d82421c9f13b9c0","target":"record","created_at":"2026-07-05T10:44:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3c014f900f917debf298f1e1c643135d114513e8e3a5674184dd8be1e19e6929","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-04T20:46:35Z","title_canon_sha256":"c49f5b133b0522447d270def847a5f442a208e918e69858e243d23eae2869c0a"},"schema_version":"1.0","source":{"id":"2504.03926","kind":"arxiv","version":1}},"canonical_sha256":"a81caa1d55e59acb6fb606ca0b42c7347a7aec46493e7a93e191dbd149c504c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a81caa1d55e59acb6fb606ca0b42c7347a7aec46493e7a93e191dbd149c504c5","first_computed_at":"2026-07-05T10:44:51.358017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:51.358017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MX7E3xFzCtpzUn8pkSPtZC2DfdAU7CBptJWFp8L09LJ+N+8sbUI9SuHLziWoL17VfEzM3cnYztYWH4Mw0uW3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:51.358509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.03926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:895262fa2643a08dd44803f0e7192b3a9461f5f506b642ce1d82421c9f13b9c0","sha256:153d6137c29a1d26ca075546b0330e51631bb7410078697f45c77638b9fc2c8c"],"state_sha256":"25b95d30404dae2883af469e6e2094355774eff5eed2477004b828f92e584c40"}