{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RLZUH3FVHNW2VHUD6LYMXIBEJJ","short_pith_number":"pith:RLZUH3FV","canonical_record":{"source":{"id":"2109.14311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-29T09:50:25Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"74bf6319dbe58e371289f3a4c8747e81eb680865dded0f31978588ace99604d3","abstract_canon_sha256":"883a49ad4704c0d7f5dde59fa9fc57c83959e6ef3ef3e994401be8eeae4e137f"},"schema_version":"1.0"},"canonical_sha256":"8af343ecb53b6daa9e83f2f0cba0244a7dbb96a4105515f54522698c58f3f2d9","source":{"kind":"arxiv","id":"2109.14311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.14311","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.14311v1","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14311","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"RLZUH3FVHNW2","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"RLZUH3FVHNW2VHUD","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"RLZUH3FV","created_at":"2026-07-05T03:18:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RLZUH3FVHNW2VHUD6LYMXIBEJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2109.14311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-29T09:50:25Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"74bf6319dbe58e371289f3a4c8747e81eb680865dded0f31978588ace99604d3","abstract_canon_sha256":"883a49ad4704c0d7f5dde59fa9fc57c83959e6ef3ef3e994401be8eeae4e137f"},"schema_version":"1.0"},"canonical_sha256":"8af343ecb53b6daa9e83f2f0cba0244a7dbb96a4105515f54522698c58f3f2d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:34.028268Z","signature_b64":"3+kgXaUOKvOvMu4oCboRwujHf69zaDQ80UgS3nwQNGLfff24Vuco/YNM+V5TknuUC/lovK019yay80gC9xkNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8af343ecb53b6daa9e83f2f0cba0244a7dbb96a4105515f54522698c58f3f2d9","last_reissued_at":"2026-07-05T03:18:34.027800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:34.027800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.14311","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":"2026-07-05T03:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jlz1+DLd5KnqdZfZY5pFloWPM4zoGzJYKdRwI6GnkOEnl1JkhKJBpxeO0yQl0sp36t2sASTAxKcfdMGvcT+EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:08:58.904893Z"},"content_sha256":"0618fa1244009dfa0720bc99c2fbfd56187c0b4132afc476e812093484d950e1","schema_version":"1.0","event_id":"sha256:0618fa1244009dfa0720bc99c2fbfd56187c0b4132afc476e812093484d950e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RLZUH3FVHNW2VHUD6LYMXIBEJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Dynamics Models for Model Predictive Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Arunkumar Byravan, Gabriel Dulac-Arnold, Josh Merel, Leonard Hasenclever, Michael Lutter, Nicolas Heess, Piotr Trochim, Yuval Tassa","submitted_at":"2021-09-29T09:50:25Z","abstract_excerpt":"Model-Based Reinforcement Learning involves learning a \\textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \\textit{planner}. Much of the recent research along these lines presents a particular set of design choices, involving problem definition, model learning and planning. Given the multiple contributions, it is difficult to evaluate the effects of each. This paper sets out to disambiguate the role of different design choices for learning dynamics models, by comparing their performance to planning with a ground-truth model -- the simul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14311","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/2109.14311/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":"2026-07-05T03:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjP+iWpNp6uJCmAQ2Nv9tuaXJHJsNj2n9NWAG5H4RKCklpjxNtys3MsUWWRmurSM3jFFL8VREv5atp593dAaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T11:08:58.905274Z"},"content_sha256":"acd167fa0ddd07d5a3600060fb415fd5631fab9452c5d9892eda77b79b998984","schema_version":"1.0","event_id":"sha256:acd167fa0ddd07d5a3600060fb415fd5631fab9452c5d9892eda77b79b998984"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLZUH3FVHNW2VHUD6LYMXIBEJJ/bundle.json","state_url":"https://pith.science/pith/RLZUH3FVHNW2VHUD6LYMXIBEJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLZUH3FVHNW2VHUD6LYMXIBEJJ/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":"2026-07-05T11:08:58Z","links":{"resolver":"https://pith.science/pith/RLZUH3FVHNW2VHUD6LYMXIBEJJ","bundle":"https://pith.science/pith/RLZUH3FVHNW2VHUD6LYMXIBEJJ/bundle.json","state":"https://pith.science/pith/RLZUH3FVHNW2VHUD6LYMXIBEJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLZUH3FVHNW2VHUD6LYMXIBEJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RLZUH3FVHNW2VHUD6LYMXIBEJJ","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":"883a49ad4704c0d7f5dde59fa9fc57c83959e6ef3ef3e994401be8eeae4e137f","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-29T09:50:25Z","title_canon_sha256":"74bf6319dbe58e371289f3a4c8747e81eb680865dded0f31978588ace99604d3"},"schema_version":"1.0","source":{"id":"2109.14311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.14311","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.14311v1","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14311","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"RLZUH3FVHNW2","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"RLZUH3FVHNW2VHUD","created_at":"2026-07-05T03:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"RLZUH3FV","created_at":"2026-07-05T03:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:acd167fa0ddd07d5a3600060fb415fd5631fab9452c5d9892eda77b79b998984","target":"graph","created_at":"2026-07-05T03:18:34Z","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/2109.14311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-Based Reinforcement Learning involves learning a \\textit{dynamics model} from data, and then using this model to optimise behaviour, most often with an online \\textit{planner}. Much of the recent research along these lines presents a particular set of design choices, involving problem definition, model learning and planning. Given the multiple contributions, it is difficult to evaluate the effects of each. This paper sets out to disambiguate the role of different design choices for learning dynamics models, by comparing their performance to planning with a ground-truth model -- the simul","authors_text":"Arunkumar Byravan, Gabriel Dulac-Arnold, Josh Merel, Leonard Hasenclever, Michael Lutter, Nicolas Heess, Piotr Trochim, Yuval Tassa","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-29T09:50:25Z","title":"Learning Dynamics Models for Model Predictive Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14311","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":"sha256:0618fa1244009dfa0720bc99c2fbfd56187c0b4132afc476e812093484d950e1","target":"record","created_at":"2026-07-05T03:18:34Z","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":"883a49ad4704c0d7f5dde59fa9fc57c83959e6ef3ef3e994401be8eeae4e137f","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-29T09:50:25Z","title_canon_sha256":"74bf6319dbe58e371289f3a4c8747e81eb680865dded0f31978588ace99604d3"},"schema_version":"1.0","source":{"id":"2109.14311","kind":"arxiv","version":1}},"canonical_sha256":"8af343ecb53b6daa9e83f2f0cba0244a7dbb96a4105515f54522698c58f3f2d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8af343ecb53b6daa9e83f2f0cba0244a7dbb96a4105515f54522698c58f3f2d9","first_computed_at":"2026-07-05T03:18:34.027800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:18:34.027800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3+kgXaUOKvOvMu4oCboRwujHf69zaDQ80UgS3nwQNGLfff24Vuco/YNM+V5TknuUC/lovK019yay80gC9xkNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:18:34.028268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.14311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0618fa1244009dfa0720bc99c2fbfd56187c0b4132afc476e812093484d950e1","sha256:acd167fa0ddd07d5a3600060fb415fd5631fab9452c5d9892eda77b79b998984"],"state_sha256":"9396a73455c0dfb3972a90a9885d391c2ecdafaf557197c53769c3fcec867ea7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wRKY++Wvsw47kFHypGCbWRiAw+xa9Q1bSt2S9XIZE53fU7wphPd9XbDJO31IBwRWRoMOXnV4x1FxK4ZePpysBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T11:08:58.907263Z","bundle_sha256":"eb1a5bacfca16f41463caa6d29217ecf9903437f19ccaee84ff4346b27e907a3"}}