{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D55O2SY2TCSB5H2XUIHELH2W5S","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":"f44383a4e7225ab1ef3be518bb1343c56cdbd90da025a17e7491cfbbcec3c24d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:25:17Z","title_canon_sha256":"3eb643c6661d2939d61a50c71cd83fd76afaa0b5f0f62b9698102235740134aa"},"schema_version":"1.0","source":{"id":"2502.01591","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01591","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01591v3","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01591","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_12","alias_value":"D55O2SY2TCSB","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_16","alias_value":"D55O2SY2TCSB5H2X","created_at":"2026-07-05T11:38:26Z"},{"alias_kind":"pith_short_8","alias_value":"D55O2SY2","created_at":"2026-07-05T11:38:26Z"}],"graph_snapshots":[{"event_id":"sha256:112f1bfb2040002d164f45ad36b56dda2d02cfad45d030bc7a1d633372deb244","target":"graph","created_at":"2026-07-05T11:38:26Z","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/2502.01591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present three improvements to the standard model-based RL paradigm based on transformers: (a) \"Dyna with warmup\", which trains the policy on real and imaginary data, but only starts using imaginary data after the world model has been sufficiently trained; (b) \"nearest neighbor tokenizer\" for image patches, which improves upon previous tokenization schemes, which are needed when using a transformer world model (TWM), by ensuring the code words are static after creation, thus providing a constant target for TWM learning; and (c) \"block teacher forcing\", which allows the TWM to reason jointly ","authors_text":"Antoine Dedieu, Carter Wendelken, Joseph Ortiz, J Swaroop Guntupalli, Kevin Patrick Murphy, Miguel Lazaro-Gredilla, Wolfgang Lehrach, Xinghua Lou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:25:17Z","title":"Improving Transformer World Models for Data-Efficient RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01591","kind":"arxiv","version":3},"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":"sha256:169bbf6682de8d5fe5218dfb1daac1b4804d2b6afd12a61e346b38351e6d4039","target":"record","created_at":"2026-07-05T11:38:26Z","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":"f44383a4e7225ab1ef3be518bb1343c56cdbd90da025a17e7491cfbbcec3c24d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:25:17Z","title_canon_sha256":"3eb643c6661d2939d61a50c71cd83fd76afaa0b5f0f62b9698102235740134aa"},"schema_version":"1.0","source":{"id":"2502.01591","kind":"arxiv","version":3}},"canonical_sha256":"1f7aed4b1a98a41e9f57a20e459f56eca47ed3adf8a379fe2949d101272f6dfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f7aed4b1a98a41e9f57a20e459f56eca47ed3adf8a379fe2949d101272f6dfb","first_computed_at":"2026-07-05T11:38:26.749849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:26.749849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OuIDudP6JuHHnpNI0VlgMaea57a62vjSKL+sMKhZoISSdglBYwRjf/rDux20rVkZ+olqT4YkcOMok8uBkuw2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:26.750416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01591","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:169bbf6682de8d5fe5218dfb1daac1b4804d2b6afd12a61e346b38351e6d4039","sha256:112f1bfb2040002d164f45ad36b56dda2d02cfad45d030bc7a1d633372deb244"],"state_sha256":"984a871a283994513dcef3b1468b5042333e9c4ca3d4a71ec98b9ba102730d5b"}