{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5T7GMWU2ZX7RUTGRQNJ6HMGF7E","short_pith_number":"pith:5T7GMWU2","canonical_record":{"source":{"id":"2306.00840","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:01:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d173bc0251dd22c8f96f77949b21eb0070c11e7d1dc0f760780a37e268d4859c","abstract_canon_sha256":"4587bf832995ba496265112fe545421eb0de5b387fd5121cf8ed462a4b54b400"},"schema_version":"1.0"},"canonical_sha256":"ecfe665a9acdff1a4cd18353e3b0c5f938837dd91e78fa7b954eaf527e1769ca","source":{"kind":"arxiv","id":"2306.00840","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00840","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00840v4","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00840","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"5T7GMWU2ZX7R","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"pith_short_16","alias_value":"5T7GMWU2ZX7RUTGR","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"pith_short_8","alias_value":"5T7GMWU2","created_at":"2026-07-05T09:19:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5T7GMWU2ZX7RUTGRQNJ6HMGF7E","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00840","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:01:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d173bc0251dd22c8f96f77949b21eb0070c11e7d1dc0f760780a37e268d4859c","abstract_canon_sha256":"4587bf832995ba496265112fe545421eb0de5b387fd5121cf8ed462a4b54b400"},"schema_version":"1.0"},"canonical_sha256":"ecfe665a9acdff1a4cd18353e3b0c5f938837dd91e78fa7b954eaf527e1769ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:23.386350Z","signature_b64":"pCDOWjFIY2j5yvB6xrxj3D4e70BxPeIXgYcgiT7kKqbjiaNm3tbkjQZ2FqODD+ZlPdOU+3T5qrImAJB/r80qDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecfe665a9acdff1a4cd18353e3b0c5f938837dd91e78fa7b954eaf527e1769ca","last_reissued_at":"2026-07-05T09:19:23.385812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:23.385812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00840","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":"2026-07-05T09:19:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V90saMWG/kT0AxBGe7oj0GUiWxndT/pth2N1k+mXn5NpDHenVE8Tk4c8/RO9Cq9zJZWuE0qG3hWhrsFbsaVHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:21:24.242095Z"},"content_sha256":"1e607d46a0b534ff058351dc1a745a3a845395ea37583ed648f58b25f65023a9","schema_version":"1.0","event_id":"sha256:1e607d46a0b534ff058351dc1a745a3a845395ea37583ed648f58b25f65023a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5T7GMWU2ZX7RUTGRQNJ6HMGF7E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What model does MuZero learn?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Frans A. Oliehoek, Jinke He, Joery A. de Vries, Thomas M. Moerland","submitted_at":"2023-06-01T16:01:23Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) has drawn considerable interest in recent years, given its promise to improve sample efficiency. Moreover, when using deep-learned models, it is possible to learn compact and generalizable models from data. In this work, we study MuZero, a state-of-the-art deep model-based reinforcement learning algorithm that distinguishes itself from existing algorithms by learning a value-equivalent model. Despite MuZero's success and impact in the field of MBRL, existing literature has not thoroughly addressed why MuZero performs so well in practice. Specifically, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00840","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/2306.00840/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":"2026-07-05T09:19:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4n4izIgasB1kZEcV3z6M19E1soM3Hlf1UK8x9QfTjkuRzpVU2csA7N1R1VCquDwD1F3uoJRkc+6BasfP6gjwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:21:24.242544Z"},"content_sha256":"60ae6d2cbf32fb076c1d9a6bbcb2782840a49df47972ae7baf42cd9abef00c8d","schema_version":"1.0","event_id":"sha256:60ae6d2cbf32fb076c1d9a6bbcb2782840a49df47972ae7baf42cd9abef00c8d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5T7GMWU2ZX7RUTGRQNJ6HMGF7E/bundle.json","state_url":"https://pith.science/pith/5T7GMWU2ZX7RUTGRQNJ6HMGF7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5T7GMWU2ZX7RUTGRQNJ6HMGF7E/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":"2026-07-31T17:21:24Z","links":{"resolver":"https://pith.science/pith/5T7GMWU2ZX7RUTGRQNJ6HMGF7E","bundle":"https://pith.science/pith/5T7GMWU2ZX7RUTGRQNJ6HMGF7E/bundle.json","state":"https://pith.science/pith/5T7GMWU2ZX7RUTGRQNJ6HMGF7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5T7GMWU2ZX7RUTGRQNJ6HMGF7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5T7GMWU2ZX7RUTGRQNJ6HMGF7E","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":"4587bf832995ba496265112fe545421eb0de5b387fd5121cf8ed462a4b54b400","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:01:23Z","title_canon_sha256":"d173bc0251dd22c8f96f77949b21eb0070c11e7d1dc0f760780a37e268d4859c"},"schema_version":"1.0","source":{"id":"2306.00840","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00840","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00840v4","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00840","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"pith_short_12","alias_value":"5T7GMWU2ZX7R","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"pith_short_16","alias_value":"5T7GMWU2ZX7RUTGR","created_at":"2026-07-05T09:19:23Z"},{"alias_kind":"pith_short_8","alias_value":"5T7GMWU2","created_at":"2026-07-05T09:19:23Z"}],"graph_snapshots":[{"event_id":"sha256:60ae6d2cbf32fb076c1d9a6bbcb2782840a49df47972ae7baf42cd9abef00c8d","target":"graph","created_at":"2026-07-05T09:19:23Z","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/2306.00840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (MBRL) has drawn considerable interest in recent years, given its promise to improve sample efficiency. Moreover, when using deep-learned models, it is possible to learn compact and generalizable models from data. In this work, we study MuZero, a state-of-the-art deep model-based reinforcement learning algorithm that distinguishes itself from existing algorithms by learning a value-equivalent model. Despite MuZero's success and impact in the field of MBRL, existing literature has not thoroughly addressed why MuZero performs so well in practice. Specifically, ","authors_text":"Frans A. Oliehoek, Jinke He, Joery A. de Vries, Thomas M. Moerland","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:01:23Z","title":"What model does MuZero learn?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00840","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":"sha256:1e607d46a0b534ff058351dc1a745a3a845395ea37583ed648f58b25f65023a9","target":"record","created_at":"2026-07-05T09:19:23Z","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":"4587bf832995ba496265112fe545421eb0de5b387fd5121cf8ed462a4b54b400","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T16:01:23Z","title_canon_sha256":"d173bc0251dd22c8f96f77949b21eb0070c11e7d1dc0f760780a37e268d4859c"},"schema_version":"1.0","source":{"id":"2306.00840","kind":"arxiv","version":4}},"canonical_sha256":"ecfe665a9acdff1a4cd18353e3b0c5f938837dd91e78fa7b954eaf527e1769ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecfe665a9acdff1a4cd18353e3b0c5f938837dd91e78fa7b954eaf527e1769ca","first_computed_at":"2026-07-05T09:19:23.385812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:23.385812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pCDOWjFIY2j5yvB6xrxj3D4e70BxPeIXgYcgiT7kKqbjiaNm3tbkjQZ2FqODD+ZlPdOU+3T5qrImAJB/r80qDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:23.386350Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00840","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e607d46a0b534ff058351dc1a745a3a845395ea37583ed648f58b25f65023a9","sha256:60ae6d2cbf32fb076c1d9a6bbcb2782840a49df47972ae7baf42cd9abef00c8d"],"state_sha256":"04da4f11872c79e44a5e10c6d234380eb574ab0aa2c1daa33b897df24f15bbe3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oaSBRbtIXyNnUBd6iJHBNzGiRSJ8SPylz6Nx470qbX2x9YOee/j0sLqRchOqSdY+/HYrnS+E3whInJBhR8ZABg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:21:24.246798Z","bundle_sha256":"045ded894a2645e895ef374da6d599d560756f61bd7261fcf94289d22ea7787c"}}