{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:EV73GGKDSS7Q7G34BDZSFHXBFC","short_pith_number":"pith:EV73GGKD","canonical_record":{"source":{"id":"2008.12775","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-28T17:58:29Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"b3ec6225e007994ed4da0cb5bdacd3e2d9af32cf7575201698ed40eb2167b4a8","abstract_canon_sha256":"13637f5af0dfc1228aa2f0b7e65839cb0cfc0098782c5c47249d0b53b345bb14"},"schema_version":"1.0"},"canonical_sha256":"257fb3194394bf0f9b7c08f3229ee12890c8fff4ef928d2a0527e393cc26c93d","source":{"kind":"arxiv","id":"2008.12775","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.12775","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"arxiv_version","alias_value":"2008.12775v3","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.12775","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"pith_short_12","alias_value":"EV73GGKDSS7Q","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"pith_short_16","alias_value":"EV73GGKDSS7Q7G34","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"pith_short_8","alias_value":"EV73GGKD","created_at":"2026-07-05T02:43:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:EV73GGKDSS7Q7G34BDZSFHXBFC","target":"record","payload":{"canonical_record":{"source":{"id":"2008.12775","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-28T17:58:29Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"b3ec6225e007994ed4da0cb5bdacd3e2d9af32cf7575201698ed40eb2167b4a8","abstract_canon_sha256":"13637f5af0dfc1228aa2f0b7e65839cb0cfc0098782c5c47249d0b53b345bb14"},"schema_version":"1.0"},"canonical_sha256":"257fb3194394bf0f9b7c08f3229ee12890c8fff4ef928d2a0527e393cc26c93d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:43:51.986208Z","signature_b64":"W/pfQUsllYpP7OwjHHEEAb9oWNUYKJABVkyFHiJa71qlzS0hfK+zF/Sm2x9G44XgdwDkaKFajRST/KgqoC6qBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"257fb3194394bf0f9b7c08f3229ee12890c8fff4ef928d2a0527e393cc26c93d","last_reissued_at":"2026-07-05T02:43:51.985600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:43:51.985600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.12775","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":"2026-07-05T02:43:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ot0+lD/E/E7DOrBGG0DFnJdiN+9Oqe5ZcQeMCeMVqhR6mY6LyJoLbfqAfPIY51rxjggiSROI810DXnu5MeIjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:06:27.061360Z"},"content_sha256":"4fd9eb4cc3d4f6e5d2b46c10b57abf2f84bc4f44dfd3a94d8e68ae41bf620ab4","schema_version":"1.0","event_id":"sha256:4fd9eb4cc3d4f6e5d2b46c10b57abf2f84bc4f44dfd3a94d8e68ae41bf620ab4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:EV73GGKDSS7Q7G34BDZSFHXBFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the model-based stochastic value gradient for continuous reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson, Brandon Amos, Denis Yarats, Samuel Stanton","submitted_at":"2020-08-28T17:58:29Z","abstract_excerpt":"For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning agents. While model-based agents are conceptually appealing, their policies tend to lag behind those of model-free agents in terms of final reward, especially in non-trivial environments. In response, researchers have proposed model-based agents with increasingly complex components, from ensembles of probabilistic dynamics models, to heuristics for mitigating model error. In a reversal of this trend, we show that simp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.12775","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/2008.12775/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":"2026-07-05T02:43:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJuFrAmMZ7WDgqsXSKROGMN9Ej1IdubMREE4WgMCleaBzN34XfbAnv3bt2UydUS11oN6Nzc3H9fD5ch7RBPlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:06:27.061874Z"},"content_sha256":"527103e2d887b9fc9f073f5f892e0ff157d0d0dd2eb561da0b31529d6be20748","schema_version":"1.0","event_id":"sha256:527103e2d887b9fc9f073f5f892e0ff157d0d0dd2eb561da0b31529d6be20748"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EV73GGKDSS7Q7G34BDZSFHXBFC/bundle.json","state_url":"https://pith.science/pith/EV73GGKDSS7Q7G34BDZSFHXBFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EV73GGKDSS7Q7G34BDZSFHXBFC/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":"2026-08-03T21:06:27Z","links":{"resolver":"https://pith.science/pith/EV73GGKDSS7Q7G34BDZSFHXBFC","bundle":"https://pith.science/pith/EV73GGKDSS7Q7G34BDZSFHXBFC/bundle.json","state":"https://pith.science/pith/EV73GGKDSS7Q7G34BDZSFHXBFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EV73GGKDSS7Q7G34BDZSFHXBFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:EV73GGKDSS7Q7G34BDZSFHXBFC","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":"13637f5af0dfc1228aa2f0b7e65839cb0cfc0098782c5c47249d0b53b345bb14","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-28T17:58:29Z","title_canon_sha256":"b3ec6225e007994ed4da0cb5bdacd3e2d9af32cf7575201698ed40eb2167b4a8"},"schema_version":"1.0","source":{"id":"2008.12775","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.12775","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"arxiv_version","alias_value":"2008.12775v3","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.12775","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"pith_short_12","alias_value":"EV73GGKDSS7Q","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"pith_short_16","alias_value":"EV73GGKDSS7Q7G34","created_at":"2026-07-05T02:43:51Z"},{"alias_kind":"pith_short_8","alias_value":"EV73GGKD","created_at":"2026-07-05T02:43:51Z"}],"graph_snapshots":[{"event_id":"sha256:527103e2d887b9fc9f073f5f892e0ff157d0d0dd2eb561da0b31529d6be20748","target":"graph","created_at":"2026-07-05T02:43:51Z","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/2008.12775/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For over a decade, model-based reinforcement learning has been seen as a way to leverage control-based domain knowledge to improve the sample-efficiency of reinforcement learning agents. While model-based agents are conceptually appealing, their policies tend to lag behind those of model-free agents in terms of final reward, especially in non-trivial environments. In response, researchers have proposed model-based agents with increasingly complex components, from ensembles of probabilistic dynamics models, to heuristics for mitigating model error. In a reversal of this trend, we show that simp","authors_text":"Andrew Gordon Wilson, Brandon Amos, Denis Yarats, Samuel Stanton","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-28T17:58:29Z","title":"On the model-based stochastic value gradient for continuous reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.12775","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":"sha256:4fd9eb4cc3d4f6e5d2b46c10b57abf2f84bc4f44dfd3a94d8e68ae41bf620ab4","target":"record","created_at":"2026-07-05T02:43:51Z","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":"13637f5af0dfc1228aa2f0b7e65839cb0cfc0098782c5c47249d0b53b345bb14","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-28T17:58:29Z","title_canon_sha256":"b3ec6225e007994ed4da0cb5bdacd3e2d9af32cf7575201698ed40eb2167b4a8"},"schema_version":"1.0","source":{"id":"2008.12775","kind":"arxiv","version":3}},"canonical_sha256":"257fb3194394bf0f9b7c08f3229ee12890c8fff4ef928d2a0527e393cc26c93d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"257fb3194394bf0f9b7c08f3229ee12890c8fff4ef928d2a0527e393cc26c93d","first_computed_at":"2026-07-05T02:43:51.985600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:43:51.985600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W/pfQUsllYpP7OwjHHEEAb9oWNUYKJABVkyFHiJa71qlzS0hfK+zF/Sm2x9G44XgdwDkaKFajRST/KgqoC6qBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:43:51.986208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.12775","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd9eb4cc3d4f6e5d2b46c10b57abf2f84bc4f44dfd3a94d8e68ae41bf620ab4","sha256:527103e2d887b9fc9f073f5f892e0ff157d0d0dd2eb561da0b31529d6be20748"],"state_sha256":"0bb6bb37d7987613e617743436dadb20dd37bd5ed0bfb30c21981ae11fb01de6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGiEjVqvJoz2fTWENX7TIxw30X/56VHQJbhUJCMY9iWeh9mc92XjrbWVBzcpbIge2EW+xORCyZfBRMJZSwozBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:06:27.067341Z","bundle_sha256":"c5ee0980f641931276dd70b95ef382992eccc523b591c7342d60f2b024bdaedd"}}