{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MQH2ASQVH27RO4NOOI4J3MH7R2","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":"b563ec375e9fff8c6dfb66d3afec2ffe60fd8060291fff8e068d20566d88114d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-25T18:25:45Z","title_canon_sha256":"696ae03a4e8b61da53ec367cd528b681c1e85487b3e21e5089fa02d8a963a6af"},"schema_version":"1.0","source":{"id":"1807.09809","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09809","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09809v1","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09809","created_at":"2026-05-18T00:09:46Z"},{"alias_kind":"pith_short_12","alias_value":"MQH2ASQVH27R","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MQH2ASQVH27RO4NO","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MQH2ASQV","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:65e7ec3637c40c3b4c942187ac9fb06585e93a9d8bba47944083243cc340d143","target":"graph","created_at":"2026-05-18T00:09:46Z","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"},"paper":{"abstract_excerpt":"Contextual multi-armed bandit problems arise frequently in important industrial applications. Existing solutions model the context either linearly, which enables uncertainty driven (principled) exploration, or non-linearly, by using epsilon-greedy exploration policies. Here we present a deep learning framework for contextual multi-armed bandits that is both non-linear and enables principled exploration at the same time. We tackle the exploration vs. exploitation trade-off through Thompson sampling by exploiting the connection between inference time dropout and sampling from the posterior over ","authors_text":"Hector Urdiales Llorens, Mark Collier","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-25T18:25:45Z","title":"Deep Contextual Multi-armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09809","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:ee23bab9da28e55d0808c3d7cd782c76cd5c2cfb749f50f56e4f8f0e9e683e5a","target":"record","created_at":"2026-05-18T00:09:46Z","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":"b563ec375e9fff8c6dfb66d3afec2ffe60fd8060291fff8e068d20566d88114d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-25T18:25:45Z","title_canon_sha256":"696ae03a4e8b61da53ec367cd528b681c1e85487b3e21e5089fa02d8a963a6af"},"schema_version":"1.0","source":{"id":"1807.09809","kind":"arxiv","version":1}},"canonical_sha256":"640fa04a153ebf1771ae72389db0ff8ea9e87063d36a2d7eb076fd0659274637","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"640fa04a153ebf1771ae72389db0ff8ea9e87063d36a2d7eb076fd0659274637","first_computed_at":"2026-05-18T00:09:46.564620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:46.564620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qs90xPj+nNhOUfn55+zPRL6/SRjBJuUGHPXx6Re1wbxxCC4+DwwqMk5v5/3QluT7LVfq+Mh0KZ+0AGE2J1d2Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:46.565334Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09809","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee23bab9da28e55d0808c3d7cd782c76cd5c2cfb749f50f56e4f8f0e9e683e5a","sha256:65e7ec3637c40c3b4c942187ac9fb06585e93a9d8bba47944083243cc340d143"],"state_sha256":"63c5254033217620da9c3ab1fab83940102ae7b74ff84f541402cdee864bebf6"}