{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:A2EZBORBEINK4QFRUKGSMEJAGF","short_pith_number":"pith:A2EZBORB","canonical_record":{"source":{"id":"2001.00805","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-03T12:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac3b840d73eac0455de4bc6626dfa0d3e0e92c6aaca933cdf746729f56b3b432","abstract_canon_sha256":"e2ef4095e72db85bc697bc92eb17c1d2fc61a074cddbd0e23a8072854e954083"},"schema_version":"1.0"},"canonical_sha256":"068990ba21221aae40b1a28d2611203153e99e023d662455a9952b75eb49a197","source":{"kind":"arxiv","id":"2001.00805","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00805","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00805v3","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00805","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"A2EZBORBEINK","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"pith_short_16","alias_value":"A2EZBORBEINK4QFR","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"pith_short_8","alias_value":"A2EZBORB","created_at":"2026-07-05T01:49:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:A2EZBORBEINK4QFRUKGSMEJAGF","target":"record","payload":{"canonical_record":{"source":{"id":"2001.00805","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-03T12:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ac3b840d73eac0455de4bc6626dfa0d3e0e92c6aaca933cdf746729f56b3b432","abstract_canon_sha256":"e2ef4095e72db85bc697bc92eb17c1d2fc61a074cddbd0e23a8072854e954083"},"schema_version":"1.0"},"canonical_sha256":"068990ba21221aae40b1a28d2611203153e99e023d662455a9952b75eb49a197","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:01.269292Z","signature_b64":"D1wZeahiD2q6+sOtNAxdSqhtrRb9/iZnyQg53AxDqOSpKWZ3FLYwFQ/z1jpc0Gzjn673WJbAIPLY8voTggSvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"068990ba21221aae40b1a28d2611203153e99e023d662455a9952b75eb49a197","last_reissued_at":"2026-07-05T01:49:01.268943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:01.268943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.00805","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fg5QTskCQ4QifZr4K3AEIBpw9dDhA4UR/2lfUD2CDThWhX3H3Tnoe99Kk08JA49RIsiOdk9QvuQQyO1sTGewCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:16:53.923944Z"},"content_sha256":"6bd84a95fb71a9649a610a0498420f36398e604c6df7b7135721ef29217311b4","schema_version":"1.0","event_id":"sha256:6bd84a95fb71a9649a610a0498420f36398e604c6df7b7135721ef29217311b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:A2EZBORBEINK4QFRUKGSMEJAGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Making Sense of Reinforcement Learning and Probabilistic Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brendan O'Donoghue, Catalin Ionescu, Ian Osband","submitted_at":"2020-01-03T12:50:42Z","abstract_excerpt":"Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts `RL as inference' and suggests a particular framework to generalize the RL problem as probabilistic inference. Our paper surfaces a key shortcoming in that approach, and clarifies the sense in which RL can be coherently cast as an inference problem. In particular, an RL agent must consider the effects of its actions upon future rewards and observations: The exploration-exploitation tradeoff. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00805","kind":"arxiv","version":3},"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/2001.00805/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":"2026-07-05T01:49:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jb7IxM3YHxpbG7OcnPBwviQm/GLoqL1u3Vg9kEgGzAcU3qrRNIbVpuqcqBZCEM/IsfcsmEZmtmeyMCiYpE3IBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T22:16:53.924447Z"},"content_sha256":"799dd734ac24cfdc52c7eb759bfd6ef12f54112a94482c02ac058c50a31a8efb","schema_version":"1.0","event_id":"sha256:799dd734ac24cfdc52c7eb759bfd6ef12f54112a94482c02ac058c50a31a8efb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A2EZBORBEINK4QFRUKGSMEJAGF/bundle.json","state_url":"https://pith.science/pith/A2EZBORBEINK4QFRUKGSMEJAGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A2EZBORBEINK4QFRUKGSMEJAGF/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":"2026-08-10T22:16:53Z","links":{"resolver":"https://pith.science/pith/A2EZBORBEINK4QFRUKGSMEJAGF","bundle":"https://pith.science/pith/A2EZBORBEINK4QFRUKGSMEJAGF/bundle.json","state":"https://pith.science/pith/A2EZBORBEINK4QFRUKGSMEJAGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A2EZBORBEINK4QFRUKGSMEJAGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:A2EZBORBEINK4QFRUKGSMEJAGF","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":"e2ef4095e72db85bc697bc92eb17c1d2fc61a074cddbd0e23a8072854e954083","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-03T12:50:42Z","title_canon_sha256":"ac3b840d73eac0455de4bc6626dfa0d3e0e92c6aaca933cdf746729f56b3b432"},"schema_version":"1.0","source":{"id":"2001.00805","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.00805","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"arxiv_version","alias_value":"2001.00805v3","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00805","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"pith_short_12","alias_value":"A2EZBORBEINK","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"pith_short_16","alias_value":"A2EZBORBEINK4QFR","created_at":"2026-07-05T01:49:01Z"},{"alias_kind":"pith_short_8","alias_value":"A2EZBORB","created_at":"2026-07-05T01:49:01Z"}],"graph_snapshots":[{"event_id":"sha256:799dd734ac24cfdc52c7eb759bfd6ef12f54112a94482c02ac058c50a31a8efb","target":"graph","created_at":"2026-07-05T01:49:01Z","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/2001.00805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts `RL as inference' and suggests a particular framework to generalize the RL problem as probabilistic inference. Our paper surfaces a key shortcoming in that approach, and clarifies the sense in which RL can be coherently cast as an inference problem. In particular, an RL agent must consider the effects of its actions upon future rewards and observations: The exploration-exploitation tradeoff. In","authors_text":"Brendan O'Donoghue, Catalin Ionescu, Ian Osband","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-03T12:50:42Z","title":"Making Sense of Reinforcement Learning and Probabilistic Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00805","kind":"arxiv","version":3},"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":"sha256:6bd84a95fb71a9649a610a0498420f36398e604c6df7b7135721ef29217311b4","target":"record","created_at":"2026-07-05T01:49:01Z","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":"e2ef4095e72db85bc697bc92eb17c1d2fc61a074cddbd0e23a8072854e954083","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-03T12:50:42Z","title_canon_sha256":"ac3b840d73eac0455de4bc6626dfa0d3e0e92c6aaca933cdf746729f56b3b432"},"schema_version":"1.0","source":{"id":"2001.00805","kind":"arxiv","version":3}},"canonical_sha256":"068990ba21221aae40b1a28d2611203153e99e023d662455a9952b75eb49a197","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"068990ba21221aae40b1a28d2611203153e99e023d662455a9952b75eb49a197","first_computed_at":"2026-07-05T01:49:01.268943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:01.268943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D1wZeahiD2q6+sOtNAxdSqhtrRb9/iZnyQg53AxDqOSpKWZ3FLYwFQ/z1jpc0Gzjn673WJbAIPLY8voTggSvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:01.269292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.00805","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bd84a95fb71a9649a610a0498420f36398e604c6df7b7135721ef29217311b4","sha256:799dd734ac24cfdc52c7eb759bfd6ef12f54112a94482c02ac058c50a31a8efb"],"state_sha256":"0a5a07ff6d1fb1b7e579575d72322b2ccd6efe082471e637412edefd9226ce25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U7leH7Hqnt64AnE7+OPrTE6weXNCnz1ApildWhJYWW/HsWfKNLqdl0JvxBdwNVlolLfORxPos1BGvKPSzG+CDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T22:16:53.928147Z","bundle_sha256":"30a328325c818fd50dcb83672dafe70544b89463a0db29b3c42efe1b52d41925"}}