{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4HI6Q5RXON35RI3M7DTPHPPNZY","short_pith_number":"pith:4HI6Q5RX","canonical_record":{"source":{"id":"2212.09510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-19T14:46:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ed0f21d5ed62b62e2f6519939777490fb5c3a6c91297fd034cd407bdf04c4771","abstract_canon_sha256":"2bbe9238ba3fdbedc8341e05962bd28dae6c01424d9402dccc9750bfa40b641b"},"schema_version":"1.0"},"canonical_sha256":"e1d1e876377377d8a36cf8e6f3bdedce36c072643486ecb7b382f0a9294f887b","source":{"kind":"arxiv","id":"2212.09510","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09510","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09510v1","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09510","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"pith_short_12","alias_value":"4HI6Q5RXON35","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"4HI6Q5RXON35RI3M","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"4HI6Q5RX","created_at":"2026-07-05T05:26:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4HI6Q5RXON35RI3M7DTPHPPNZY","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-19T14:46:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ed0f21d5ed62b62e2f6519939777490fb5c3a6c91297fd034cd407bdf04c4771","abstract_canon_sha256":"2bbe9238ba3fdbedc8341e05962bd28dae6c01424d9402dccc9750bfa40b641b"},"schema_version":"1.0"},"canonical_sha256":"e1d1e876377377d8a36cf8e6f3bdedce36c072643486ecb7b382f0a9294f887b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:22.996430Z","signature_b64":"7mdF9YQ/4Uyd9ssHbzgYYkU6z4UsOg0x89D8fGDWaTB6MGVyrO2x2jxpeGdekAonuYV+OVl8Zk8WZp5E2LO4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1d1e876377377d8a36cf8e6f3bdedce36c072643486ecb7b382f0a9294f887b","last_reissued_at":"2026-07-05T05:26:22.995955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:22.995955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09510","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ws7NdLy+9dM2j3G+l7zBbEiAP2v5w5tu3bBTOnVmXbha9+vxkqpVUjvSRvnCp1lAwyl9I97JWxAXZbTT/VTpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:55:56.270085Z"},"content_sha256":"d286adfbc3ef9a8a05c747e7c5e0501ef9c53d91851e13abc6c05671f9870370","schema_version":"1.0","event_id":"sha256:d286adfbc3ef9a8a05c747e7c5e0501ef9c53d91851e13abc6c05671f9870370"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4HI6Q5RXON35RI3M7DTPHPPNZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-optimal Policy Identification in Active Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Ian Char, Ilija Bogunovic, Jeff Schneider, Johannes Kirschner, Viraj Mehta, Willie Neiswanger, Xiang Li","submitted_at":"2022-12-19T14:46:57Z","abstract_excerpt":"Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces. In cases where the transition dynamics can be readily evaluated at specified states (e.g., via a simulator), agents can operate in what is often referred to as planning with a \\emph{generative model}. We propose the AE-LSVI algorithm for best-policy identification, a novel variant of the kernelized least-squares value iteration (LSVI) algorithm that combines optimism with pessimism for active exploration (AE). AE-LSVI provably ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09510","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/2212.09510/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SaOoJV8ZfMiuYqN4V7UOqp4mzWm7YwYhT8oVfHZAQLmRv6QaoKWCFAPAc13eishLwKQA2+0LvcJOuy3fyhyZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T21:55:56.271059Z"},"content_sha256":"f469e1e67a29a7bb904ceb3a28268a2ae1aaf2a8705096fb92d9e7f5059ae59f","schema_version":"1.0","event_id":"sha256:f469e1e67a29a7bb904ceb3a28268a2ae1aaf2a8705096fb92d9e7f5059ae59f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HI6Q5RXON35RI3M7DTPHPPNZY/bundle.json","state_url":"https://pith.science/pith/4HI6Q5RXON35RI3M7DTPHPPNZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HI6Q5RXON35RI3M7DTPHPPNZY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T21:55:56Z","links":{"resolver":"https://pith.science/pith/4HI6Q5RXON35RI3M7DTPHPPNZY","bundle":"https://pith.science/pith/4HI6Q5RXON35RI3M7DTPHPPNZY/bundle.json","state":"https://pith.science/pith/4HI6Q5RXON35RI3M7DTPHPPNZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HI6Q5RXON35RI3M7DTPHPPNZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4HI6Q5RXON35RI3M7DTPHPPNZY","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":"2bbe9238ba3fdbedc8341e05962bd28dae6c01424d9402dccc9750bfa40b641b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-19T14:46:57Z","title_canon_sha256":"ed0f21d5ed62b62e2f6519939777490fb5c3a6c91297fd034cd407bdf04c4771"},"schema_version":"1.0","source":{"id":"2212.09510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09510","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09510v1","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09510","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"pith_short_12","alias_value":"4HI6Q5RXON35","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"4HI6Q5RXON35RI3M","created_at":"2026-07-05T05:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"4HI6Q5RX","created_at":"2026-07-05T05:26:22Z"}],"graph_snapshots":[{"event_id":"sha256:f469e1e67a29a7bb904ceb3a28268a2ae1aaf2a8705096fb92d9e7f5059ae59f","target":"graph","created_at":"2026-07-05T05:26:22Z","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/2212.09510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces. In cases where the transition dynamics can be readily evaluated at specified states (e.g., via a simulator), agents can operate in what is often referred to as planning with a \\emph{generative model}. We propose the AE-LSVI algorithm for best-policy identification, a novel variant of the kernelized least-squares value iteration (LSVI) algorithm that combines optimism with pessimism for active exploration (AE). AE-LSVI provably ide","authors_text":"Andreas Krause, Ian Char, Ilija Bogunovic, Jeff Schneider, Johannes Kirschner, Viraj Mehta, Willie Neiswanger, Xiang Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-19T14:46:57Z","title":"Near-optimal Policy Identification in Active Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09510","kind":"arxiv","version":1},"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:d286adfbc3ef9a8a05c747e7c5e0501ef9c53d91851e13abc6c05671f9870370","target":"record","created_at":"2026-07-05T05:26:22Z","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":"2bbe9238ba3fdbedc8341e05962bd28dae6c01424d9402dccc9750bfa40b641b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-19T14:46:57Z","title_canon_sha256":"ed0f21d5ed62b62e2f6519939777490fb5c3a6c91297fd034cd407bdf04c4771"},"schema_version":"1.0","source":{"id":"2212.09510","kind":"arxiv","version":1}},"canonical_sha256":"e1d1e876377377d8a36cf8e6f3bdedce36c072643486ecb7b382f0a9294f887b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1d1e876377377d8a36cf8e6f3bdedce36c072643486ecb7b382f0a9294f887b","first_computed_at":"2026-07-05T05:26:22.995955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:22.995955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7mdF9YQ/4Uyd9ssHbzgYYkU6z4UsOg0x89D8fGDWaTB6MGVyrO2x2jxpeGdekAonuYV+OVl8Zk8WZp5E2LO4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:22.996430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d286adfbc3ef9a8a05c747e7c5e0501ef9c53d91851e13abc6c05671f9870370","sha256:f469e1e67a29a7bb904ceb3a28268a2ae1aaf2a8705096fb92d9e7f5059ae59f"],"state_sha256":"4c3d7acdefe76b5e18808d0e752f03cea59f53aabfb7bd41c5df6b8617337f61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Y4Hd8YkHszhsYsI1+qoacTTJ75EOCWPUfQBfi5E1+IQ37fXhW0/BLcUoDzxOxAG4mxyBPkBe7tBMWtY0ZdRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T21:55:56.279404Z","bundle_sha256":"e16a275b40dedf65a5ad854d67610758fc3cbdf7fee93656116d00f909e2b788"}}