{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BOXZES2IUJO6M2D3ZJ2V7L2TJD","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":"4b59d29c5076b42c6c37a85dc96c337c8730bf3be3b0297aa2e051b899671712","cross_cats_sorted":["cs.LG","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-29T09:42:27Z","title_canon_sha256":"ca412486a9c960ce665f45febfd51c94c7d589cdfd63db76b8163230d2325929"},"schema_version":"1.0","source":{"id":"2509.24527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.24527","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2509.24527v1","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24527","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"BOXZES2IUJO6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BOXZES2IUJO6M2D3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BOXZES2I","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:afcaa41cdf0c8215efb91d7ff7cdaa3f642d427029fc926eb479acd4c33004ed","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By learning behaviors in imagination, Dreamer 4 is the first agent to obtain diamonds in Minecraft purely from offline data, without environment interaction."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The world model accurately predicts object interactions and game mechanics over the long action sequences required for the diamond task."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Dreamer 4 obtains diamonds in Minecraft by training reinforcement learning behaviors inside a world model learned from offline videos."}],"snapshot_sha256":"a5ed48d9d4e669289a408a2581c8da8d60ebc3bf363b27c85e57f8d791f7fd02"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"cfb102cd8a5c161d63ae1f4f8b90da852ce445831b12a5650c28aff7edf83ea3"},"paper":{"abstract_excerpt":"World models learn general knowledge from videos and simulate experience for training behaviors in imagination, offering a path towards intelligent agents. However, previous world models have been unable to accurately predict object interactions in complex environments. We introduce Dreamer 4, a scalable agent that learns to solve control tasks by reinforcement learning inside of a fast and accurate world model. In the complex video game Minecraft, the world model accurately predicts object interactions and game mechanics, outperforming previous world models by a large margin. The world model ","authors_text":"Danijar Hafner, Timothy Lillicrap, Wilson Yan","cross_cats":["cs.LG","cs.RO","stat.ML"],"headline":"Dreamer 4 obtains diamonds in Minecraft by training reinforcement learning behaviors inside a world model learned from offline videos.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-29T09:42:27Z","title":"Training Agents Inside of Scalable World Models"},"references":{"count":84,"internal_anchors":26,"resolved_work":84,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Mastering diverse control tasks through world models.Nature, pages 1–7, 2025","work_id":"11501645-f4f6-4b70-a15e-9da63b320e73","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Daydreamer: World models for physical robot learning","work_id":"3be0bb29-cef0-4cd3-90da-1ffb544f0046","year":2023},{"cited_arxiv_id":"2310.16828","doi":"","is_internal_anchor":true,"ref_index":3,"title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","work_id":"360ec5fb-79fd-4490-bc73-3d161609c42d","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Diffusion for world modeling: Visual details matter in atari.Advances in Neural Information Processing Systems, 37:58757–58791, 2024","work_id":"38bbb70f-29a1-4c4c-9a5b-f24d6be2e431","year":2024},{"cited_arxiv_id":"1911.08265","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","work_id":"964ed935-1570-495e-a162-9182456934cc","year":1911}],"snapshot_sha256":"23340cba0440dd8752f3268d74a4c14f9e42192b4a5ff5b96a8f6fe37b8ef1b4"},"source":{"id":"2509.24527","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:01:18.530066Z","id":"e70fdf4a-fa31-411b-a985-eb38cd501cd6","model_set":{"reader":"grok-4.3"},"one_line_summary":"Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Dreamer 4 obtains diamonds in Minecraft by training reinforcement learning behaviors inside a world model learned from offline videos.","strongest_claim":"By learning behaviors in imagination, Dreamer 4 is the first agent to obtain diamonds in Minecraft purely from offline data, without environment interaction.","weakest_assumption":"The world model accurately predicts object interactions and game mechanics over the long action sequences required for the diamond task."}},"verdict_id":"e70fdf4a-fa31-411b-a985-eb38cd501cd6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d254d9a3b726646ec3bb8ca588fabb21aa25ddbf1656c3ca9190a988df74d466","target":"record","created_at":"2026-05-17T23:38:53Z","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":"4b59d29c5076b42c6c37a85dc96c337c8730bf3be3b0297aa2e051b899671712","cross_cats_sorted":["cs.LG","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-29T09:42:27Z","title_canon_sha256":"ca412486a9c960ce665f45febfd51c94c7d589cdfd63db76b8163230d2325929"},"schema_version":"1.0","source":{"id":"2509.24527","kind":"arxiv","version":1}},"canonical_sha256":"0baf924b48a25de6687bca755faf5348ee903c9ac35a648ddda7a30a201094cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0baf924b48a25de6687bca755faf5348ee903c9ac35a648ddda7a30a201094cb","first_computed_at":"2026-05-17T23:38:53.862693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.862693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZyxdlVDCfM305rJfTJxnvFGNMlQ5zksZ6kv7NIJbf6X40GLezDXnj1Th9qGgtqiIL/Uioxem4Gceet1wc94zBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.863342Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.24527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d254d9a3b726646ec3bb8ca588fabb21aa25ddbf1656c3ca9190a988df74d466","sha256:afcaa41cdf0c8215efb91d7ff7cdaa3f642d427029fc926eb479acd4c33004ed"],"state_sha256":"1e779a5daf7b610ec531707680c0a52875ba582f44053d38a7bac09d61230466"}