{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HR2GACLMBMISTQYCVISQ4XN76U","short_pith_number":"pith:HR2GACLM","canonical_record":{"source":{"id":"2110.02758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:43:27Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"422878dbe3f772bc90a5437d106607129e8ee2bee62f12ac018b50dabebe31f1","abstract_canon_sha256":"5be0e33474d3d63221975caf6e4c27cd05b2c36a6458d54a07770c00bf5b2c35"},"schema_version":"1.0"},"canonical_sha256":"3c7460096c0b1129c302aa250e5dbff534ee30c0120b3836c23e6d77bb728707","source":{"kind":"arxiv","id":"2110.02758","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02758","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02758v2","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02758","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"HR2GACLMBMIS","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"HR2GACLMBMISTQYC","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"HR2GACLM","created_at":"2026-07-05T05:43:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HR2GACLMBMISTQYCVISQ4XN76U","target":"record","payload":{"canonical_record":{"source":{"id":"2110.02758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:43:27Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"422878dbe3f772bc90a5437d106607129e8ee2bee62f12ac018b50dabebe31f1","abstract_canon_sha256":"5be0e33474d3d63221975caf6e4c27cd05b2c36a6458d54a07770c00bf5b2c35"},"schema_version":"1.0"},"canonical_sha256":"3c7460096c0b1129c302aa250e5dbff534ee30c0120b3836c23e6d77bb728707","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:08.541733Z","signature_b64":"fFPsej5QAJOLyVdx8v+PZ5euIPig7QLlW0DtGqrUYyQ83BEEmRY50BwbdaGT0KbGjJ3VAmRR20DrwEOgcJc+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c7460096c0b1129c302aa250e5dbff534ee30c0120b3836c23e6d77bb728707","last_reissued_at":"2026-07-05T05:43:08.541299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:08.541299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.02758","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7GnwrMFXc74ePrV4GcJ3tLjNHBdZLIFUhHXSkJqyeZpbgkzqeHfO+J9a7IY68qqpgMSMtZe/K8z29TcfkpeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:00:22.527593Z"},"content_sha256":"9dc8ddc9ea785f0f361923fdb1ac1beda4e33779cef1e51eae5bffeeefd7da3c","schema_version":"1.0","event_id":"sha256:9dc8ddc9ea785f0f361923fdb1ac1beda4e33779cef1e51eae5bffeeefd7da3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HR2GACLMBMISTQYCVISQ4XN76U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Alexander Khazatsky, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","submitted_at":"2021-10-06T13:43:27Z","abstract_excerpt":"Many model-based reinforcement learning (RL) methods follow a similar template: fit a model to previously observed data, and then use data from that model for RL or planning. However, models that achieve better training performance (e.g., lower MSE) are not necessarily better for control: an RL agent may seek out the small fraction of states where an accurate model makes mistakes, or it might act in ways that do not expose the errors of an inaccurate model. As noted in prior work, there is an objective mismatch: models are useful if they yield good policies, but they are trained to maximize th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02758","kind":"arxiv","version":2},"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/2110.02758/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":"2026-07-05T05:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tV7giMUaRH8J2FWVKvp/GmPnTbcT4asFTboE+FHFsrBumFCv/dfn+6q77MHQkT74O0fd2QxcD5fimsNhsSX7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:00:22.528751Z"},"content_sha256":"19254b916d34cfc72c26cc497ae538a86f0eaa77aaca20f50c4b9204c6200261","schema_version":"1.0","event_id":"sha256:19254b916d34cfc72c26cc497ae538a86f0eaa77aaca20f50c4b9204c6200261"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HR2GACLMBMISTQYCVISQ4XN76U/bundle.json","state_url":"https://pith.science/pith/HR2GACLMBMISTQYCVISQ4XN76U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HR2GACLMBMISTQYCVISQ4XN76U/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":"2026-08-13T04:00:22Z","links":{"resolver":"https://pith.science/pith/HR2GACLMBMISTQYCVISQ4XN76U","bundle":"https://pith.science/pith/HR2GACLMBMISTQYCVISQ4XN76U/bundle.json","state":"https://pith.science/pith/HR2GACLMBMISTQYCVISQ4XN76U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HR2GACLMBMISTQYCVISQ4XN76U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HR2GACLMBMISTQYCVISQ4XN76U","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":"5be0e33474d3d63221975caf6e4c27cd05b2c36a6458d54a07770c00bf5b2c35","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:43:27Z","title_canon_sha256":"422878dbe3f772bc90a5437d106607129e8ee2bee62f12ac018b50dabebe31f1"},"schema_version":"1.0","source":{"id":"2110.02758","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02758","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02758v2","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02758","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"HR2GACLMBMIS","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"HR2GACLMBMISTQYC","created_at":"2026-07-05T05:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"HR2GACLM","created_at":"2026-07-05T05:43:08Z"}],"graph_snapshots":[{"event_id":"sha256:19254b916d34cfc72c26cc497ae538a86f0eaa77aaca20f50c4b9204c6200261","target":"graph","created_at":"2026-07-05T05:43:08Z","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/2110.02758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many model-based reinforcement learning (RL) methods follow a similar template: fit a model to previously observed data, and then use data from that model for RL or planning. However, models that achieve better training performance (e.g., lower MSE) are not necessarily better for control: an RL agent may seek out the small fraction of states where an accurate model makes mistakes, or it might act in ways that do not expose the errors of an inaccurate model. As noted in prior work, there is an objective mismatch: models are useful if they yield good policies, but they are trained to maximize th","authors_text":"Alexander Khazatsky, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:43:27Z","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02758","kind":"arxiv","version":2},"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":"sha256:9dc8ddc9ea785f0f361923fdb1ac1beda4e33779cef1e51eae5bffeeefd7da3c","target":"record","created_at":"2026-07-05T05:43:08Z","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":"5be0e33474d3d63221975caf6e4c27cd05b2c36a6458d54a07770c00bf5b2c35","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:43:27Z","title_canon_sha256":"422878dbe3f772bc90a5437d106607129e8ee2bee62f12ac018b50dabebe31f1"},"schema_version":"1.0","source":{"id":"2110.02758","kind":"arxiv","version":2}},"canonical_sha256":"3c7460096c0b1129c302aa250e5dbff534ee30c0120b3836c23e6d77bb728707","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c7460096c0b1129c302aa250e5dbff534ee30c0120b3836c23e6d77bb728707","first_computed_at":"2026-07-05T05:43:08.541299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:08.541299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fFPsej5QAJOLyVdx8v+PZ5euIPig7QLlW0DtGqrUYyQ83BEEmRY50BwbdaGT0KbGjJ3VAmRR20DrwEOgcJc+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:08.541733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02758","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dc8ddc9ea785f0f361923fdb1ac1beda4e33779cef1e51eae5bffeeefd7da3c","sha256:19254b916d34cfc72c26cc497ae538a86f0eaa77aaca20f50c4b9204c6200261"],"state_sha256":"794638d9bcdb942b0c1f6d4aee9e05925910003059a8499b48775c2a681f9b8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CQ7Cv+YzvpEd+1tokN4kCz8pXYjLdu/gP8YtlRyX9K2RI5hlo/CUW1KBbR8IYfptqY7mjTlLnTSLagfHo/gpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:00:22.538035Z","bundle_sha256":"7ee542ea79350956db35d86b87b55e407b7cc94ad72bb31d75972083ccd82990"}}