{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LZZVK5BOULUJXHYCM5PPAARMQY","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":"90fecc497fccccf627637822bb000242fe05e3680ea9d1fa2c4d1a7d0f175ba6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T17:03:07Z","title_canon_sha256":"9dced5f5ef010770f12b1b9e983309e5d725a055be0e1a98528c1b363ba876c3"},"schema_version":"1.0","source":{"id":"2209.00588","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.00588","created_at":"2026-07-05T05:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"2209.00588v2","created_at":"2026-07-05T05:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00588","created_at":"2026-07-05T05:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"LZZVK5BOULUJ","created_at":"2026-07-05T05:47:03Z"},{"alias_kind":"pith_short_16","alias_value":"LZZVK5BOULUJXHYC","created_at":"2026-07-05T05:47:03Z"},{"alias_kind":"pith_short_8","alias_value":"LZZVK5BO","created_at":"2026-07-05T05:47:03Z"}],"graph_snapshots":[{"event_id":"sha256:e465bade35121479e3e58bcd0be2357fb1ba1da4635255e590550d1fd85f581a","target":"graph","created_at":"2026-07-05T05:47:03Z","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/2209.00588/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning agents are notoriously sample inefficient, which considerably limits their application to real-world problems. Recently, many model-based methods have been designed to address this issue, with learning in the imagination of a world model being one of the most prominent approaches. However, while virtually unlimited interaction with a simulated environment sounds appealing, the world model has to be accurate over extended periods of time. Motivated by the success of Transformers in sequence modeling tasks, we introduce IRIS, a data-efficient agent that learns in a wo","authors_text":"Eloi Alonso, Fran\\c{c}ois Fleuret, Vincent Micheli","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T17:03:07Z","title":"Transformers are Sample-Efficient World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00588","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:ef34eb3c3ee802a4d605682224f7d6b0687a7151c73f60d11d36721417fd4d84","target":"record","created_at":"2026-07-05T05:47:03Z","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":"90fecc497fccccf627637822bb000242fe05e3680ea9d1fa2c4d1a7d0f175ba6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-01T17:03:07Z","title_canon_sha256":"9dced5f5ef010770f12b1b9e983309e5d725a055be0e1a98528c1b363ba876c3"},"schema_version":"1.0","source":{"id":"2209.00588","kind":"arxiv","version":2}},"canonical_sha256":"5e7355742ea2e89b9f02675ef0022c860b931c751a25ccb64cf4c15a3fb9780d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e7355742ea2e89b9f02675ef0022c860b931c751a25ccb64cf4c15a3fb9780d","first_computed_at":"2026-07-05T05:47:03.534188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:03.534188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oxslj6Mtpjout8MmjBzLIRL8Af7wq+Rmm/08wMGPHOZcGJYYh9Qufe3D/pNqYDP3wr+dj69jn9R29ttk5VZ9DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:03.534587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.00588","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef34eb3c3ee802a4d605682224f7d6b0687a7151c73f60d11d36721417fd4d84","sha256:e465bade35121479e3e58bcd0be2357fb1ba1da4635255e590550d1fd85f581a"],"state_sha256":"8defbad9780dfb4f939bc97c559af3ddcd8185d7df249aad8d726f3d1c1f301b"}