{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6BAD2ZVHTJW2SYOZTPJY2P5QEK","short_pith_number":"pith:6BAD2ZVH","canonical_record":{"source":{"id":"2007.01891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T18:10:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e8bd84cfd2791741991ac61d9dadf3c0fbbeec58023c8cd5ee388e845f7fd7db","abstract_canon_sha256":"000ada9586b27bafb3aea0f6811b60d4517a56b011a177bcad5368705d5f8356"},"schema_version":"1.0"},"canonical_sha256":"f0403d66a79a6da961d99bd38d3fb022a56bed34da8ee13908c5a944e7d133c9","source":{"kind":"arxiv","id":"2007.01891","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01891","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01891v1","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01891","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"pith_short_12","alias_value":"6BAD2ZVHTJW2","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"pith_short_16","alias_value":"6BAD2ZVHTJW2SYOZ","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"pith_short_8","alias_value":"6BAD2ZVH","created_at":"2026-07-05T01:16:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6BAD2ZVHTJW2SYOZTPJY2P5QEK","target":"record","payload":{"canonical_record":{"source":{"id":"2007.01891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T18:10:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e8bd84cfd2791741991ac61d9dadf3c0fbbeec58023c8cd5ee388e845f7fd7db","abstract_canon_sha256":"000ada9586b27bafb3aea0f6811b60d4517a56b011a177bcad5368705d5f8356"},"schema_version":"1.0"},"canonical_sha256":"f0403d66a79a6da961d99bd38d3fb022a56bed34da8ee13908c5a944e7d133c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:17.154655Z","signature_b64":"B95g0y2YTZKJdGjv23a0QqbDMQvkjvGiOPWSZNY9S8LMNZTVGU31onVTUi7Pl+H5IFUXZCKKUqcHvSlLeZjRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0403d66a79a6da961d99bd38d3fb022a56bed34da8ee13908c5a944e7d133c9","last_reissued_at":"2026-07-05T01:16:17.154140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:17.154140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.01891","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":"2026-07-05T01:16:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WkSUBiLuQ2XJ2784PbPNNjzQKU8UdtqpmoVhHTuZji3YQw6sGbebwtSIncdcsTS06OMHi0odR3Xso/V6tSF+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:46:01.567716Z"},"content_sha256":"3e567f3c6658e6b016a6678cb7a45e98127eaad656186c5a40cc8a793e2056c9","schema_version":"1.0","event_id":"sha256:3e567f3c6658e6b016a6678cb7a45e98127eaad656186c5a40cc8a793e2056c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6BAD2ZVHTJW2SYOZTPJY2P5QEK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Unifying View of Optimism in Episodic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ciara Pike-Burke, Gergely Neu","submitted_at":"2020-07-03T18:10:30Z","abstract_excerpt":"The principle of optimism in the face of uncertainty underpins many theoretically successful reinforcement learning algorithms. In this paper we provide a general framework for designing, analyzing and implementing such algorithms in the episodic reinforcement learning problem. This framework is built upon Lagrangian duality, and demonstrates that every model-optimistic algorithm that constructs an optimistic MDP has an equivalent representation as a value-optimistic dynamic programming algorithm. Typically, it was thought that these two classes of algorithms were distinct, with model-optimist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01891","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/2007.01891/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":"2026-07-05T01:16:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FjkFIr1FZarrdqrQmhlvqzGsX1s52VVVvahqVvOPhBbx3P1V5ELBF/Ohx5N3Ph3ATta135lYvIAYgIZl1kuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:46:01.568212Z"},"content_sha256":"e955312173b7484135ab99eb1f4ba2f571d87fb62eacd9d54e450ade52f3a68f","schema_version":"1.0","event_id":"sha256:e955312173b7484135ab99eb1f4ba2f571d87fb62eacd9d54e450ade52f3a68f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6BAD2ZVHTJW2SYOZTPJY2P5QEK/bundle.json","state_url":"https://pith.science/pith/6BAD2ZVHTJW2SYOZTPJY2P5QEK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6BAD2ZVHTJW2SYOZTPJY2P5QEK/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":"2026-08-04T07:46:01Z","links":{"resolver":"https://pith.science/pith/6BAD2ZVHTJW2SYOZTPJY2P5QEK","bundle":"https://pith.science/pith/6BAD2ZVHTJW2SYOZTPJY2P5QEK/bundle.json","state":"https://pith.science/pith/6BAD2ZVHTJW2SYOZTPJY2P5QEK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6BAD2ZVHTJW2SYOZTPJY2P5QEK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6BAD2ZVHTJW2SYOZTPJY2P5QEK","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":"000ada9586b27bafb3aea0f6811b60d4517a56b011a177bcad5368705d5f8356","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T18:10:30Z","title_canon_sha256":"e8bd84cfd2791741991ac61d9dadf3c0fbbeec58023c8cd5ee388e845f7fd7db"},"schema_version":"1.0","source":{"id":"2007.01891","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.01891","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"arxiv_version","alias_value":"2007.01891v1","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01891","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"pith_short_12","alias_value":"6BAD2ZVHTJW2","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"pith_short_16","alias_value":"6BAD2ZVHTJW2SYOZ","created_at":"2026-07-05T01:16:17Z"},{"alias_kind":"pith_short_8","alias_value":"6BAD2ZVH","created_at":"2026-07-05T01:16:17Z"}],"graph_snapshots":[{"event_id":"sha256:e955312173b7484135ab99eb1f4ba2f571d87fb62eacd9d54e450ade52f3a68f","target":"graph","created_at":"2026-07-05T01:16:17Z","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/2007.01891/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The principle of optimism in the face of uncertainty underpins many theoretically successful reinforcement learning algorithms. In this paper we provide a general framework for designing, analyzing and implementing such algorithms in the episodic reinforcement learning problem. This framework is built upon Lagrangian duality, and demonstrates that every model-optimistic algorithm that constructs an optimistic MDP has an equivalent representation as a value-optimistic dynamic programming algorithm. Typically, it was thought that these two classes of algorithms were distinct, with model-optimist","authors_text":"Ciara Pike-Burke, Gergely Neu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T18:10:30Z","title":"A Unifying View of Optimism in Episodic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01891","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":"sha256:3e567f3c6658e6b016a6678cb7a45e98127eaad656186c5a40cc8a793e2056c9","target":"record","created_at":"2026-07-05T01:16:17Z","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":"000ada9586b27bafb3aea0f6811b60d4517a56b011a177bcad5368705d5f8356","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-03T18:10:30Z","title_canon_sha256":"e8bd84cfd2791741991ac61d9dadf3c0fbbeec58023c8cd5ee388e845f7fd7db"},"schema_version":"1.0","source":{"id":"2007.01891","kind":"arxiv","version":1}},"canonical_sha256":"f0403d66a79a6da961d99bd38d3fb022a56bed34da8ee13908c5a944e7d133c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0403d66a79a6da961d99bd38d3fb022a56bed34da8ee13908c5a944e7d133c9","first_computed_at":"2026-07-05T01:16:17.154140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:17.154140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B95g0y2YTZKJdGjv23a0QqbDMQvkjvGiOPWSZNY9S8LMNZTVGU31onVTUi7Pl+H5IFUXZCKKUqcHvSlLeZjRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:17.154655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.01891","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e567f3c6658e6b016a6678cb7a45e98127eaad656186c5a40cc8a793e2056c9","sha256:e955312173b7484135ab99eb1f4ba2f571d87fb62eacd9d54e450ade52f3a68f"],"state_sha256":"fc8987b5c6dacbf98f809f057bcfab01f8f1e80f81abbc01f16bd8decfd1020e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SG//YrjuKJTXin85beJSMy11MC8Wl6VdScC84L3+QKRJ/YnXIA40BvqzPnDlRWT3dg9jmP0bt/nX51wcYv4PAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:46:01.602744Z","bundle_sha256":"9041d00da724d7a542b53771a243a52179e232ba4444a90196f478c7f8c5a219"}}