{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WXIYULFZBKCNXYZUYBHKELZRZ3","short_pith_number":"pith:WXIYULFZ","schema_version":"1.0","canonical_sha256":"b5d18a2cb90a84dbe334c04ea22f31cec604f26ed55e13f1e9c6e40355246bfa","source":{"kind":"arxiv","id":"2006.07464","version":1},"attestation_state":"computed","paper":{"title":"Hypermodels for Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Ian Osband, Morteza Ibrahimi, Vikranth Dwaracherla, Xiuyuan Lu, Zheng Wen","submitted_at":"2020-06-12T20:59:21Z","abstract_excerpt":"We study the use of hypermodels to represent epistemic uncertainty and guide exploration. This generalizes and extends the use of ensembles to approximate Thompson sampling. The computational cost of training an ensemble grows with its size, and as such, prior work has typically been limited to ensembles with tens of elements. We show that alternative hypermodels can enjoy dramatic efficiency gains, enabling behavior that would otherwise require hundreds or thousands of elements, and even succeed in situations where ensemble methods fail to learn regardless of size. This allows more accurate a"},"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":"2006.07464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T20:59:21Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fa7676aee393d27abb6f208491395960e2bf8d15f66519fbd4f10bfd50bc32d9","abstract_canon_sha256":"11969e04c3c04725f9a9f493fd28f061dcd771865235539bddb928b6c20207a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:16.759072Z","signature_b64":"XibKOW3BNw2Y7EJn8uhndqx2IXhIiftSqz19CVlYMbZQhMTnrc2AxAk6rZDhCPZ4Q0caaIfm5/ZbQbNTQzSvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d18a2cb90a84dbe334c04ea22f31cec604f26ed55e13f1e9c6e40355246bfa","last_reissued_at":"2026-07-05T01:10:16.758578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:16.758578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hypermodels for Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Ian Osband, Morteza Ibrahimi, Vikranth Dwaracherla, Xiuyuan Lu, Zheng Wen","submitted_at":"2020-06-12T20:59:21Z","abstract_excerpt":"We study the use of hypermodels to represent epistemic uncertainty and guide exploration. This generalizes and extends the use of ensembles to approximate Thompson sampling. The computational cost of training an ensemble grows with its size, and as such, prior work has typically been limited to ensembles with tens of elements. We show that alternative hypermodels can enjoy dramatic efficiency gains, enabling behavior that would otherwise require hundreds or thousands of elements, and even succeed in situations where ensemble methods fail to learn regardless of size. This allows more accurate a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07464","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/2006.07464/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":"2006.07464","created_at":"2026-07-05T01:10:16.758637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07464v1","created_at":"2026-07-05T01:10:16.758637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07464","created_at":"2026-07-05T01:10:16.758637+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXIYULFZBKCN","created_at":"2026-07-05T01:10:16.758637+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXIYULFZBKCNXYZU","created_at":"2026-07-05T01:10:16.758637+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXIYULFZ","created_at":"2026-07-05T01:10:16.758637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13394","citing_title":"Concurrent Learning with Aggregated States via Randomized Least Squares Value Iteration","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3","json":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3.json","graph_json":"https://pith.science/api/pith-number/WXIYULFZBKCNXYZUYBHKELZRZ3/graph.json","events_json":"https://pith.science/api/pith-number/WXIYULFZBKCNXYZUYBHKELZRZ3/events.json","paper":"https://pith.science/paper/WXIYULFZ"},"agent_actions":{"view_html":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3","download_json":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3.json","view_paper":"https://pith.science/paper/WXIYULFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07464&json=true","fetch_graph":"https://pith.science/api/pith-number/WXIYULFZBKCNXYZUYBHKELZRZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/WXIYULFZBKCNXYZUYBHKELZRZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3/action/storage_attestation","attest_author":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3/action/author_attestation","sign_citation":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3/action/citation_signature","submit_replication":"https://pith.science/pith/WXIYULFZBKCNXYZUYBHKELZRZ3/action/replication_record"}},"created_at":"2026-07-05T01:10:16.758637+00:00","updated_at":"2026-07-05T01:10:16.758637+00:00"}