{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MQH2ASQVH27RO4NOOI4J3MH7R2","short_pith_number":"pith:MQH2ASQV","schema_version":"1.0","canonical_sha256":"640fa04a153ebf1771ae72389db0ff8ea9e87063d36a2d7eb076fd0659274637","source":{"kind":"arxiv","id":"1807.09809","version":1},"attestation_state":"computed","paper":{"title":"Deep Contextual Multi-armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hector Urdiales Llorens, Mark Collier","submitted_at":"2018-07-25T18:25:45Z","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 "},"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":"1807.09809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-25T18:25:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"696ae03a4e8b61da53ec367cd528b681c1e85487b3e21e5089fa02d8a963a6af","abstract_canon_sha256":"b563ec375e9fff8c6dfb66d3afec2ffe60fd8060291fff8e068d20566d88114d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:46.565334Z","signature_b64":"qs90xPj+nNhOUfn55+zPRL6/SRjBJuUGHPXx6Re1wbxxCC4+DwwqMk5v5/3QluT7LVfq+Mh0KZ+0AGE2J1d2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"640fa04a153ebf1771ae72389db0ff8ea9e87063d36a2d7eb076fd0659274637","last_reissued_at":"2026-05-18T00:09:46.564620Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:46.564620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Contextual Multi-armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hector Urdiales Llorens, Mark Collier","submitted_at":"2018-07-25T18:25:45Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09809","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":""},"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":"1807.09809","created_at":"2026-05-18T00:09:46.564723+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09809v1","created_at":"2026-05-18T00:09:46.564723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09809","created_at":"2026-05-18T00:09:46.564723+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQH2ASQVH27R","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQH2ASQVH27RO4NO","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQH2ASQV","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07618","citing_title":"Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2","json":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2.json","graph_json":"https://pith.science/api/pith-number/MQH2ASQVH27RO4NOOI4J3MH7R2/graph.json","events_json":"https://pith.science/api/pith-number/MQH2ASQVH27RO4NOOI4J3MH7R2/events.json","paper":"https://pith.science/paper/MQH2ASQV"},"agent_actions":{"view_html":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2","download_json":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2.json","view_paper":"https://pith.science/paper/MQH2ASQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09809&json=true","fetch_graph":"https://pith.science/api/pith-number/MQH2ASQVH27RO4NOOI4J3MH7R2/graph.json","fetch_events":"https://pith.science/api/pith-number/MQH2ASQVH27RO4NOOI4J3MH7R2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2/action/storage_attestation","attest_author":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2/action/author_attestation","sign_citation":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2/action/citation_signature","submit_replication":"https://pith.science/pith/MQH2ASQVH27RO4NOOI4J3MH7R2/action/replication_record"}},"created_at":"2026-05-18T00:09:46.564723+00:00","updated_at":"2026-05-18T00:09:46.564723+00:00"}