{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BTO4NYZ7UITRM3R632G5RVVLFY","short_pith_number":"pith:BTO4NYZ7","canonical_record":{"source":{"id":"2406.10667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-15T15:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"c7301e2ef15a4aca7f01b8fd22f9f20e17832a64ef713cafffd63a7d117d3679","abstract_canon_sha256":"4d806832798b94dc036e8190742440060752236d6a317b735469b31fe8ba40b4"},"schema_version":"1.0"},"canonical_sha256":"0cddc6e33fa227166e3ede8dd8d6ab2e3525ae170d128c20896faf776b340d29","source":{"kind":"arxiv","id":"2406.10667","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10667","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10667v2","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10667","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"pith_short_12","alias_value":"BTO4NYZ7UITR","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"pith_short_16","alias_value":"BTO4NYZ7UITRM3R6","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"pith_short_8","alias_value":"BTO4NYZ7","created_at":"2026-07-05T09:56:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BTO4NYZ7UITRM3R632G5RVVLFY","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-15T15:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"c7301e2ef15a4aca7f01b8fd22f9f20e17832a64ef713cafffd63a7d117d3679","abstract_canon_sha256":"4d806832798b94dc036e8190742440060752236d6a317b735469b31fe8ba40b4"},"schema_version":"1.0"},"canonical_sha256":"0cddc6e33fa227166e3ede8dd8d6ab2e3525ae170d128c20896faf776b340d29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:36.305482Z","signature_b64":"tmKSbiCvg14fng7YUrZ/XyIFCdYCqvDlf1okU+VZ7Z7BBgCPh7SXP+J6i3vsMnVULQCbnCkBYLJNkYf8ANCaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cddc6e33fa227166e3ede8dd8d6ab2e3525ae170d128c20896faf776b340d29","last_reissued_at":"2026-07-05T09:56:36.304941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:36.304941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10667","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":"2026-07-05T09:56:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+/+bvGy7pMXkk0d+Ij7LgZ3M1nDdRsGUVGSXpYmTydVdVk7z/1sT9QNWr+H5EUVYjobpyQ1pTGmC3uCkigLIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:23:02.070672Z"},"content_sha256":"5dfda27eeca83962be03e013c398f8d86550133abad8a23ff5f3208cec48a976","schema_version":"1.0","event_id":"sha256:5dfda27eeca83962be03e013c398f8d86550133abad8a23ff5f3208cec48a976"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BTO4NYZ7UITRM3R632G5RVVLFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongsheng Li, Jiyuan Ren, Yazhe Niu, Yuan Pu, Yu Liu, Zhenjie Yang","submitted_at":"2024-06-15T15:24:15Z","abstract_excerpt":"Learning predictive world models is crucial for enhancing the planning capabilities of reinforcement learning (RL) agents. Recently, MuZero-style algorithms, leveraging the value equivalence principle and Monte Carlo Tree Search (MCTS), have achieved superhuman performance in various domains. However, these methods struggle to scale in heterogeneous scenarios with diverse dependencies and task variability. To overcome these limitations, we introduce UniZero, a novel approach that employs a modular transformer-based world model to effectively learn a shared latent space. By concurrently predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10667","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/2406.10667/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":"2026-07-05T09:56:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WztzZxEI2btFGZySuHS+VRbFzyXQmDRYXZkTwLxSKVHtPpyPjUJWWRuVw+kuMFYwdejJaIbi/0ec+E9AQ2P8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:23:02.071300Z"},"content_sha256":"2ab757893513c877ef9c02cca238211cd078a50713a3600a4ab25ea1e2905da6","schema_version":"1.0","event_id":"sha256:2ab757893513c877ef9c02cca238211cd078a50713a3600a4ab25ea1e2905da6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BTO4NYZ7UITRM3R632G5RVVLFY/bundle.json","state_url":"https://pith.science/pith/BTO4NYZ7UITRM3R632G5RVVLFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BTO4NYZ7UITRM3R632G5RVVLFY/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":"2026-08-04T20:23:02Z","links":{"resolver":"https://pith.science/pith/BTO4NYZ7UITRM3R632G5RVVLFY","bundle":"https://pith.science/pith/BTO4NYZ7UITRM3R632G5RVVLFY/bundle.json","state":"https://pith.science/pith/BTO4NYZ7UITRM3R632G5RVVLFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BTO4NYZ7UITRM3R632G5RVVLFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BTO4NYZ7UITRM3R632G5RVVLFY","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":"4d806832798b94dc036e8190742440060752236d6a317b735469b31fe8ba40b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-15T15:24:15Z","title_canon_sha256":"c7301e2ef15a4aca7f01b8fd22f9f20e17832a64ef713cafffd63a7d117d3679"},"schema_version":"1.0","source":{"id":"2406.10667","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10667","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10667v2","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10667","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"pith_short_12","alias_value":"BTO4NYZ7UITR","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"pith_short_16","alias_value":"BTO4NYZ7UITRM3R6","created_at":"2026-07-05T09:56:36Z"},{"alias_kind":"pith_short_8","alias_value":"BTO4NYZ7","created_at":"2026-07-05T09:56:36Z"}],"graph_snapshots":[{"event_id":"sha256:2ab757893513c877ef9c02cca238211cd078a50713a3600a4ab25ea1e2905da6","target":"graph","created_at":"2026-07-05T09:56:36Z","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/2406.10667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning predictive world models is crucial for enhancing the planning capabilities of reinforcement learning (RL) agents. Recently, MuZero-style algorithms, leveraging the value equivalence principle and Monte Carlo Tree Search (MCTS), have achieved superhuman performance in various domains. However, these methods struggle to scale in heterogeneous scenarios with diverse dependencies and task variability. To overcome these limitations, we introduce UniZero, a novel approach that employs a modular transformer-based world model to effectively learn a shared latent space. By concurrently predict","authors_text":"Hongsheng Li, Jiyuan Ren, Yazhe Niu, Yuan Pu, Yu Liu, Zhenjie Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-15T15:24:15Z","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10667","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":"sha256:5dfda27eeca83962be03e013c398f8d86550133abad8a23ff5f3208cec48a976","target":"record","created_at":"2026-07-05T09:56:36Z","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":"4d806832798b94dc036e8190742440060752236d6a317b735469b31fe8ba40b4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-15T15:24:15Z","title_canon_sha256":"c7301e2ef15a4aca7f01b8fd22f9f20e17832a64ef713cafffd63a7d117d3679"},"schema_version":"1.0","source":{"id":"2406.10667","kind":"arxiv","version":2}},"canonical_sha256":"0cddc6e33fa227166e3ede8dd8d6ab2e3525ae170d128c20896faf776b340d29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cddc6e33fa227166e3ede8dd8d6ab2e3525ae170d128c20896faf776b340d29","first_computed_at":"2026-07-05T09:56:36.304941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:36.304941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tmKSbiCvg14fng7YUrZ/XyIFCdYCqvDlf1okU+VZ7Z7BBgCPh7SXP+J6i3vsMnVULQCbnCkBYLJNkYf8ANCaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:36.305482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10667","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dfda27eeca83962be03e013c398f8d86550133abad8a23ff5f3208cec48a976","sha256:2ab757893513c877ef9c02cca238211cd078a50713a3600a4ab25ea1e2905da6"],"state_sha256":"b8e6e290cb7ea2be67bd1dd1ec3cb431501e96f612e36b35067cb5bc3fd071f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8V8dfMLOVD4CmaZ6COa+zjQGn/2q5aRrKGTetSWeXVrJ7fAKWX7r6XdUNOOeC3flyv++CNjW6LNS74WqRW7aBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:23:02.076550Z","bundle_sha256":"f81749cc45bd53737ea180ebf90e86c8cf019001d6f5b9021ed58369ef94a602"}}