{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:U73NBYEYH6XZCQH5CFHIZCZTWR","short_pith_number":"pith:U73NBYEY","canonical_record":{"source":{"id":"2210.08349","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T17:57:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebb96d36e1ddf1b5e2d0270590fdf25d517a1b8c7a7ff02df2a434d5ce4579f0","abstract_canon_sha256":"9b102f0697cc86f001c28d185dcc657c58d556b7178c0beeee40e0e2a921f0a2"},"schema_version":"1.0"},"canonical_sha256":"a7f6d0e0983faf9140fd114e8c8b33b476eab31b3851c79a048151ab8014bb7a","source":{"kind":"arxiv","id":"2210.08349","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.08349","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2210.08349v4","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08349","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"U73NBYEYH6XZ","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"U73NBYEYH6XZCQH5","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"U73NBYEY","created_at":"2026-07-05T07:10:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:U73NBYEYH6XZCQH5CFHIZCZTWR","target":"record","payload":{"canonical_record":{"source":{"id":"2210.08349","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T17:57:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebb96d36e1ddf1b5e2d0270590fdf25d517a1b8c7a7ff02df2a434d5ce4579f0","abstract_canon_sha256":"9b102f0697cc86f001c28d185dcc657c58d556b7178c0beeee40e0e2a921f0a2"},"schema_version":"1.0"},"canonical_sha256":"a7f6d0e0983faf9140fd114e8c8b33b476eab31b3851c79a048151ab8014bb7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:21.234645Z","signature_b64":"ParQMseeysDMTnozegHRXqba0qcJgrqPv/zKYr3nvl+4gGtj+gPAvKZWFDceg7SozhQYcXMYQxFi96GghJfgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7f6d0e0983faf9140fd114e8c8b33b476eab31b3851c79a048151ab8014bb7a","last_reissued_at":"2026-07-05T07:10:21.234132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:21.234132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.08349","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HaPv8XU/Fl1bdzcfNPpW3hvvW+hIJoa6B1OYElLpWn0dnJmbtK/o5+m4CgSn63qUC/hOrteXiXGzIJHmLjciCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:36:31.315807Z"},"content_sha256":"28518c3ad143d8267e97d1c2e17463f956c261df53c48e53a46804d8ccd2296b","schema_version":"1.0","event_id":"sha256:28518c3ad143d8267e97d1c2e17463f956c261df53c48e53a46804d8ccd2296b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:U73NBYEYH6XZCQH5CFHIZCZTWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When to Update Your Model: Constrained Model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fengxiang He, Fuchun Sun, Mingxuan Jing, Tianying Ji, Wenbing Huang, Yu Luo","submitted_at":"2022-10-15T17:57:43Z","abstract_excerpt":"Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08349","kind":"arxiv","version":4},"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/2210.08349/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":"2026-07-05T07:10:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FY6gGF7zAswr68uM7Yjo/KVItBW9tv9ku8i7NqDmCaMQYfcJ8/4rvZA6lvbaaO6WEt4FOvRwLgMxWp2eHrQOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:36:31.317425Z"},"content_sha256":"8575e11b56e6243a05d3b1e5c14bbc5092bbe9331884958c543f82b385f9cc8a","schema_version":"1.0","event_id":"sha256:8575e11b56e6243a05d3b1e5c14bbc5092bbe9331884958c543f82b385f9cc8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U73NBYEYH6XZCQH5CFHIZCZTWR/bundle.json","state_url":"https://pith.science/pith/U73NBYEYH6XZCQH5CFHIZCZTWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U73NBYEYH6XZCQH5CFHIZCZTWR/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":"2026-08-01T11:36:31Z","links":{"resolver":"https://pith.science/pith/U73NBYEYH6XZCQH5CFHIZCZTWR","bundle":"https://pith.science/pith/U73NBYEYH6XZCQH5CFHIZCZTWR/bundle.json","state":"https://pith.science/pith/U73NBYEYH6XZCQH5CFHIZCZTWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U73NBYEYH6XZCQH5CFHIZCZTWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:U73NBYEYH6XZCQH5CFHIZCZTWR","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":"9b102f0697cc86f001c28d185dcc657c58d556b7178c0beeee40e0e2a921f0a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T17:57:43Z","title_canon_sha256":"ebb96d36e1ddf1b5e2d0270590fdf25d517a1b8c7a7ff02df2a434d5ce4579f0"},"schema_version":"1.0","source":{"id":"2210.08349","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.08349","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"arxiv_version","alias_value":"2210.08349v4","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08349","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"pith_short_12","alias_value":"U73NBYEYH6XZ","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"pith_short_16","alias_value":"U73NBYEYH6XZCQH5","created_at":"2026-07-05T07:10:21Z"},{"alias_kind":"pith_short_8","alias_value":"U73NBYEY","created_at":"2026-07-05T07:10:21Z"}],"graph_snapshots":[{"event_id":"sha256:8575e11b56e6243a05d3b1e5c14bbc5092bbe9331884958c543f82b385f9cc8a","target":"graph","created_at":"2026-07-05T07:10:21Z","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/2210.08349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These d","authors_text":"Fengxiang He, Fuchun Sun, Mingxuan Jing, Tianying Ji, Wenbing Huang, Yu Luo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T17:57:43Z","title":"When to Update Your Model: Constrained Model-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08349","kind":"arxiv","version":4},"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":"sha256:28518c3ad143d8267e97d1c2e17463f956c261df53c48e53a46804d8ccd2296b","target":"record","created_at":"2026-07-05T07:10:21Z","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":"9b102f0697cc86f001c28d185dcc657c58d556b7178c0beeee40e0e2a921f0a2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-15T17:57:43Z","title_canon_sha256":"ebb96d36e1ddf1b5e2d0270590fdf25d517a1b8c7a7ff02df2a434d5ce4579f0"},"schema_version":"1.0","source":{"id":"2210.08349","kind":"arxiv","version":4}},"canonical_sha256":"a7f6d0e0983faf9140fd114e8c8b33b476eab31b3851c79a048151ab8014bb7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7f6d0e0983faf9140fd114e8c8b33b476eab31b3851c79a048151ab8014bb7a","first_computed_at":"2026-07-05T07:10:21.234132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:21.234132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ParQMseeysDMTnozegHRXqba0qcJgrqPv/zKYr3nvl+4gGtj+gPAvKZWFDceg7SozhQYcXMYQxFi96GghJfgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:21.234645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.08349","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28518c3ad143d8267e97d1c2e17463f956c261df53c48e53a46804d8ccd2296b","sha256:8575e11b56e6243a05d3b1e5c14bbc5092bbe9331884958c543f82b385f9cc8a"],"state_sha256":"f332bee339ecc48091128d4d391a70712b64a54089aaeb4072c694f905fba4f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+As4qICxRZVIRA2piwBmcfzt4dXGMQRye02YIszPcT+XfDoeIaT8jZafETYHW0cPSM01I12hCrAyy47EjuOfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T11:36:31.324114Z","bundle_sha256":"ce5fca0245c057e57682d961400874dc1971ef47cf1b598f6b03102fb30836a6"}}