{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DXHU5IDQUD56KK7NS7A4QKU7MM","short_pith_number":"pith:DXHU5IDQ","schema_version":"1.0","canonical_sha256":"1dcf4ea070a0fbe52bed97c1c82a9f632f44922063c83e8b3cf1c051ffa4b38e","source":{"kind":"arxiv","id":"2302.09205","version":1},"attestation_state":"computed","paper":{"title":"Approximate Thompson Sampling via Epistemic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Ian Osband, Morteza Ibrahimi, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Zheng Wen","submitted_at":"2023-02-18T01:58:15Z","abstract_excerpt":"Thompson sampling (TS) is a popular heuristic for action selection, but it requires sampling from a posterior distribution. Unfortunately, this can become computationally intractable in complex environments, such as those modeled using neural networks. Approximate posterior samples can produce effective actions, but only if they reasonably approximate joint predictive distributions of outputs across inputs. Notably, accuracy of marginal predictive distributions does not suffice. Epistemic neural networks (ENNs) are designed to produce accurate joint predictive distributions. We compare a range"},"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":"2302.09205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-18T01:58:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"038e09952aa49b400f191d80481bf8c6d439988871caa72fbeceab870b522f1d","abstract_canon_sha256":"cfa4444e1a5fecfc7dff24cae11c8634745ac9183b1c7d3c556c3386f2b1a64e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:22.443744Z","signature_b64":"WWgPnxn/6mzD9R7YzHVa7l0741BmTWAVJ6+cCgT/ix35pmFrRG7Mdit3FZzGHR6J9PyE51ALWqAxZOjC4EjXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dcf4ea070a0fbe52bed97c1c82a9f632f44922063c83e8b3cf1c051ffa4b38e","last_reissued_at":"2026-07-05T05:43:22.443304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:22.443304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximate Thompson Sampling via Epistemic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Ian Osband, Morteza Ibrahimi, Seyed Mohammad Asghari, Vikranth Dwaracherla, Xiuyuan Lu, Zheng Wen","submitted_at":"2023-02-18T01:58:15Z","abstract_excerpt":"Thompson sampling (TS) is a popular heuristic for action selection, but it requires sampling from a posterior distribution. Unfortunately, this can become computationally intractable in complex environments, such as those modeled using neural networks. Approximate posterior samples can produce effective actions, but only if they reasonably approximate joint predictive distributions of outputs across inputs. Notably, accuracy of marginal predictive distributions does not suffice. Epistemic neural networks (ENNs) are designed to produce accurate joint predictive distributions. We compare a range"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09205","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/2302.09205/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":"2302.09205","created_at":"2026-07-05T05:43:22.443383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.09205v1","created_at":"2026-07-05T05:43:22.443383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09205","created_at":"2026-07-05T05:43:22.443383+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXHU5IDQUD56","created_at":"2026-07-05T05:43:22.443383+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXHU5IDQUD56KK7N","created_at":"2026-07-05T05:43:22.443383+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXHU5IDQ","created_at":"2026-07-05T05:43:22.443383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21458","citing_title":"Mind the Sim-to-Real Gap & Think Like a Scientist","ref_index":134,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM","json":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM.json","graph_json":"https://pith.science/api/pith-number/DXHU5IDQUD56KK7NS7A4QKU7MM/graph.json","events_json":"https://pith.science/api/pith-number/DXHU5IDQUD56KK7NS7A4QKU7MM/events.json","paper":"https://pith.science/paper/DXHU5IDQ"},"agent_actions":{"view_html":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM","download_json":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM.json","view_paper":"https://pith.science/paper/DXHU5IDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.09205&json=true","fetch_graph":"https://pith.science/api/pith-number/DXHU5IDQUD56KK7NS7A4QKU7MM/graph.json","fetch_events":"https://pith.science/api/pith-number/DXHU5IDQUD56KK7NS7A4QKU7MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM/action/storage_attestation","attest_author":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM/action/author_attestation","sign_citation":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM/action/citation_signature","submit_replication":"https://pith.science/pith/DXHU5IDQUD56KK7NS7A4QKU7MM/action/replication_record"}},"created_at":"2026-07-05T05:43:22.443383+00:00","updated_at":"2026-07-05T05:43:22.443383+00:00"}