{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CCR34REEFJHFSQ7YVEFMVFRSFC","short_pith_number":"pith:CCR34REE","canonical_record":{"source":{"id":"2301.08502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-20T10:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"fc86481051c0797c1832a92a6e40b9e52c8c4f8cf950e02ec2683e7a7dc0e230","abstract_canon_sha256":"3dee6fcc1a97293c5014c04612b98133224fc990c09896dbfb88c0f638316dc7"},"schema_version":"1.0"},"canonical_sha256":"10a3be44842a4e5943f8a90aca963228a4e29f61de56d34748a228e2e1057095","source":{"kind":"arxiv","id":"2301.08502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08502","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08502v1","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08502","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"pith_short_12","alias_value":"CCR34REEFJHF","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"pith_short_16","alias_value":"CCR34REEFJHFSQ7Y","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"pith_short_8","alias_value":"CCR34REE","created_at":"2026-07-05T05:34:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CCR34REEFJHFSQ7YVEFMVFRSFC","target":"record","payload":{"canonical_record":{"source":{"id":"2301.08502","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-20T10:17:22Z","cross_cats_sorted":[],"title_canon_sha256":"fc86481051c0797c1832a92a6e40b9e52c8c4f8cf950e02ec2683e7a7dc0e230","abstract_canon_sha256":"3dee6fcc1a97293c5014c04612b98133224fc990c09896dbfb88c0f638316dc7"},"schema_version":"1.0"},"canonical_sha256":"10a3be44842a4e5943f8a90aca963228a4e29f61de56d34748a228e2e1057095","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:36.786396Z","signature_b64":"m63bTHNbVlbWg9+W+lZfnyRK8fw816c93qIUxAk5rwerngGgSxyo+rqsOh0OiFjQHtaiBYeQT/wIr40ppnDaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10a3be44842a4e5943f8a90aca963228a4e29f61de56d34748a228e2e1057095","last_reissued_at":"2026-07-05T05:34:36.785948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:36.785948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.08502","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":"2026-07-05T05:34:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YgmHBj6zXk5UEJRiynGVW6yJmXYzJkKIW2FuG6qPO98ixW9xt0uHdwvkpMomVog24T02vJq+IHOxbsH0U23lAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:11:07.225911Z"},"content_sha256":"9907569182b5963f0a8e9f65558de5df49a0099cb57daffdd27afad8ded344a9","schema_version":"1.0","event_id":"sha256:9907569182b5963f0a8e9f65558de5df49a0099cb57daffdd27afad8ded344a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CCR34REEFJHFSQ7YVEFMVFRSFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Yu, Chen Chen, Hankz Hankui Zhuo, Jianye Hao, Zifan Wu","submitted_at":"2023-01-20T10:17:22Z","abstract_excerpt":"In Model-based Reinforcement Learning (MBRL), model learning is critical since an inaccurate model can bias policy learning via generating misleading samples. However, learning an accurate model can be difficult since the policy is continually updated and the induced distribution over visited states used for model learning shifts accordingly. Prior methods alleviate this issue by quantifying the uncertainty of model-generated samples. However, these methods only quantify the uncertainty passively after the samples were generated, rather than foreseeing the uncertainty before model trajectories"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08502","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/2301.08502/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":"2026-07-05T05:34:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UU/suhzH8s7eYrysuqH1Wfqb3SQ68tL1InS3SLKR9UwklT9czL7k1ubdRvEfRqpuan8gKg3H0baP+6Z9esgjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T15:11:07.226292Z"},"content_sha256":"72cd4acf2786b91ef52d0c884b90e78a0d3169579705873bfaaf7b7da47dc39f","schema_version":"1.0","event_id":"sha256:72cd4acf2786b91ef52d0c884b90e78a0d3169579705873bfaaf7b7da47dc39f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCR34REEFJHFSQ7YVEFMVFRSFC/bundle.json","state_url":"https://pith.science/pith/CCR34REEFJHFSQ7YVEFMVFRSFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCR34REEFJHFSQ7YVEFMVFRSFC/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":"2026-07-11T15:11:07Z","links":{"resolver":"https://pith.science/pith/CCR34REEFJHFSQ7YVEFMVFRSFC","bundle":"https://pith.science/pith/CCR34REEFJHFSQ7YVEFMVFRSFC/bundle.json","state":"https://pith.science/pith/CCR34REEFJHFSQ7YVEFMVFRSFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCR34REEFJHFSQ7YVEFMVFRSFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CCR34REEFJHFSQ7YVEFMVFRSFC","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":"3dee6fcc1a97293c5014c04612b98133224fc990c09896dbfb88c0f638316dc7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-20T10:17:22Z","title_canon_sha256":"fc86481051c0797c1832a92a6e40b9e52c8c4f8cf950e02ec2683e7a7dc0e230"},"schema_version":"1.0","source":{"id":"2301.08502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08502","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08502v1","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08502","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"pith_short_12","alias_value":"CCR34REEFJHF","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"pith_short_16","alias_value":"CCR34REEFJHFSQ7Y","created_at":"2026-07-05T05:34:36Z"},{"alias_kind":"pith_short_8","alias_value":"CCR34REE","created_at":"2026-07-05T05:34:36Z"}],"graph_snapshots":[{"event_id":"sha256:72cd4acf2786b91ef52d0c884b90e78a0d3169579705873bfaaf7b7da47dc39f","target":"graph","created_at":"2026-07-05T05:34:36Z","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/2301.08502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Model-based Reinforcement Learning (MBRL), model learning is critical since an inaccurate model can bias policy learning via generating misleading samples. However, learning an accurate model can be difficult since the policy is continually updated and the induced distribution over visited states used for model learning shifts accordingly. Prior methods alleviate this issue by quantifying the uncertainty of model-generated samples. However, these methods only quantify the uncertainty passively after the samples were generated, rather than foreseeing the uncertainty before model trajectories","authors_text":"Chao Yu, Chen Chen, Hankz Hankui Zhuo, Jianye Hao, Zifan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-20T10:17:22Z","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08502","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":"sha256:9907569182b5963f0a8e9f65558de5df49a0099cb57daffdd27afad8ded344a9","target":"record","created_at":"2026-07-05T05:34:36Z","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":"3dee6fcc1a97293c5014c04612b98133224fc990c09896dbfb88c0f638316dc7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-20T10:17:22Z","title_canon_sha256":"fc86481051c0797c1832a92a6e40b9e52c8c4f8cf950e02ec2683e7a7dc0e230"},"schema_version":"1.0","source":{"id":"2301.08502","kind":"arxiv","version":1}},"canonical_sha256":"10a3be44842a4e5943f8a90aca963228a4e29f61de56d34748a228e2e1057095","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10a3be44842a4e5943f8a90aca963228a4e29f61de56d34748a228e2e1057095","first_computed_at":"2026-07-05T05:34:36.785948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:34:36.785948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m63bTHNbVlbWg9+W+lZfnyRK8fw816c93qIUxAk5rwerngGgSxyo+rqsOh0OiFjQHtaiBYeQT/wIr40ppnDaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:34:36.786396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.08502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9907569182b5963f0a8e9f65558de5df49a0099cb57daffdd27afad8ded344a9","sha256:72cd4acf2786b91ef52d0c884b90e78a0d3169579705873bfaaf7b7da47dc39f"],"state_sha256":"8de33cdef3fe0c13bba1721cfe53f0288246bf00b37add6ded03fc7b9c39e9b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oKAR1DSwMP3P71aEtjcU0kbh3JWCA0M6sP160a67F8+se5f08niLYZHxv/Ks+8Uq/ZNqsHpaD3skS5iimwtGDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T15:11:07.228737Z","bundle_sha256":"0aa0e430585740d883595ff8cd65209a981a1e567d579b1e7965553c9dd061b6"}}