{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OH7QZQ7C5QAU53DAIH2WB66ZNS","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":"650641ef8291451698d8665ab1b91051d7fba4285fed8d168585b2e402c1c311","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-21T15:25:15Z","title_canon_sha256":"cdb883047381a27d0930d476e4aff78f7d8808175c12df94d8a5b1c67f60be5d"},"schema_version":"1.0","source":{"id":"2110.11202","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.11202","created_at":"2026-07-05T04:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2110.11202v2","created_at":"2026-07-05T04:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11202","created_at":"2026-07-05T04:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"OH7QZQ7C5QAU","created_at":"2026-07-05T04:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"OH7QZQ7C5QAU53DA","created_at":"2026-07-05T04:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"OH7QZQ7C","created_at":"2026-07-05T04:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:d28ad549336293746434e9b242a54e164e7a6f731ce5d2935e035332d784e18b","target":"graph","created_at":"2026-07-05T04:13:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.11202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intrinsic rewards play a central role in handling the exploration-exploitation trade-off when designing sequential decision-making algorithms, in both foundational theory and state-of-the-art deep reinforcement learning. The LinUCB algorithm, a centerpiece of the stochastic linear bandits literature, prescribes an elliptical bonus which addresses the challenge of leveraging shared information in large action spaces. This bonus scheme cannot be directly transferred to high-dimensional exploration problems, however, due to the computational cost of maintaining the inverse covariance matrix of ac","authors_text":"Akshay Krishnamurthy, Cyril Zhang, Jordan T. Ash, Sham Kakade, Surbhi Goel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-21T15:25:15Z","title":"Anti-Concentrated Confidence Bonuses for Scalable Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11202","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":"sha256:375f7df8e6aa8dbff4587b052229036df7278cb7db18665008688c2befa3436c","target":"record","created_at":"2026-07-05T04:13:44Z","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":"650641ef8291451698d8665ab1b91051d7fba4285fed8d168585b2e402c1c311","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-21T15:25:15Z","title_canon_sha256":"cdb883047381a27d0930d476e4aff78f7d8808175c12df94d8a5b1c67f60be5d"},"schema_version":"1.0","source":{"id":"2110.11202","kind":"arxiv","version":2}},"canonical_sha256":"71ff0cc3e2ec014eec6041f560fbd96c9304b9be7f284e49c3e6b10a3d24676b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71ff0cc3e2ec014eec6041f560fbd96c9304b9be7f284e49c3e6b10a3d24676b","first_computed_at":"2026-07-05T04:13:44.372718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:44.372718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9XbxdhZA0sQlnPZuIVwdv4JD9Z92v6q7fooSbsREaqlEf30AU1TGJ5RcIsI2F/ehved17f/wR2BQq6DHdtBpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:44.373198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.11202","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:375f7df8e6aa8dbff4587b052229036df7278cb7db18665008688c2befa3436c","sha256:d28ad549336293746434e9b242a54e164e7a6f731ce5d2935e035332d784e18b"],"state_sha256":"58e3e3a47a2972e32b8a4032db7a35cf2f400c9c53f6b1a3772f555c8d18b1b2"}