{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:7UUIGZU75ODO3RDBLP4OTKZEUC","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":"d64ff04b5312791e9c89568a45443ef95ef497702d8a1279a4c251d32f81f561","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-20T14:21:42Z","title_canon_sha256":"0dd3fb5aad9859ba71cb4952d0e67297d4448fc17b3eff54a9b2230bf3a2a50f"},"schema_version":"1.0","source":{"id":"1607.05970","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05970","created_at":"2026-05-18T00:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05970v2","created_at":"2026-05-18T00:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05970","created_at":"2026-05-18T00:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"7UUIGZU75ODO","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7UUIGZU75ODO3RDB","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7UUIGZU7","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:0660776cd17087378e8277fb0aa40cb38dcc18c9d641f321a88fc707071432b1","target":"graph","created_at":"2026-05-18T00:46:55Z","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":"The Knowledge Gradient (KG) policy was originally proposed for online ranking and selection problems but has recently been adapted for use in online decision making in general and multi-armed bandit problems (MABs) in particular. We study its use in a class of exponential family MABs and identify weaknesses, including a propensity to take actions which are dominated with respect to both exploitation and exploration. We propose variants of KG which avoid such errors. These new policies include an index heuristic which deploys a KG approach to develop an approximation to the Gittins index. A num","authors_text":"James Edwards, Kevin Glazebrook, Paul Fearnhead","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-20T14:21:42Z","title":"On the Identification and Mitigation of Weaknesses in the Knowledge Gradient Policy for Multi-Armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05970","kind":"arxiv","version":2},"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":"sha256:9cc6ee4c22a846ec1d64ba9df4b2bf546f9ad6c104ab61fc2d33ec465e637174","target":"record","created_at":"2026-05-18T00:46:55Z","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":"d64ff04b5312791e9c89568a45443ef95ef497702d8a1279a4c251d32f81f561","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-07-20T14:21:42Z","title_canon_sha256":"0dd3fb5aad9859ba71cb4952d0e67297d4448fc17b3eff54a9b2230bf3a2a50f"},"schema_version":"1.0","source":{"id":"1607.05970","kind":"arxiv","version":2}},"canonical_sha256":"fd2883669feb86edc4615bf8e9ab24a0b55a22f12598926f37a3a193f65bd78c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd2883669feb86edc4615bf8e9ab24a0b55a22f12598926f37a3a193f65bd78c","first_computed_at":"2026-05-18T00:46:55.636334Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:55.636334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IfsDkSX4O+F4CU8R6q2+rgGfme5fG13ffaf2ZzlcPdPn2UVx8o+FOHBkPm8LU0vXBtkVV3Y5ggXuA8zbFUGaDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:55.636728Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.05970","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cc6ee4c22a846ec1d64ba9df4b2bf546f9ad6c104ab61fc2d33ec465e637174","sha256:0660776cd17087378e8277fb0aa40cb38dcc18c9d641f321a88fc707071432b1"],"state_sha256":"4f8c8058c6acfc386c746ec525d4328abf6f15b2627e5bf6047f0e235b17bd1d"}