{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RY3RMCDYBQAN6U2ORD42AYWG5E","short_pith_number":"pith:RY3RMCDY","canonical_record":{"source":{"id":"2303.07109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T13:43:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d5df4af1476f67b707e18c84b2ceda8092a544199933d7634a17864c269ba397","abstract_canon_sha256":"1b2c42e6668b2d464b641f1c035c28ae7c7feefbfcfd8060a9a8bf27b9352c61"},"schema_version":"1.0"},"canonical_sha256":"8e371608780c00df534e88f9a062c6e906f48c195d073373accb44e9bbafacd9","source":{"kind":"arxiv","id":"2303.07109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07109","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07109v1","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07109","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"pith_short_12","alias_value":"RY3RMCDYBQAN","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"pith_short_16","alias_value":"RY3RMCDYBQAN6U2O","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"pith_short_8","alias_value":"RY3RMCDY","created_at":"2026-07-05T05:50:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RY3RMCDYBQAN6U2ORD42AYWG5E","target":"record","payload":{"canonical_record":{"source":{"id":"2303.07109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T13:43:59Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d5df4af1476f67b707e18c84b2ceda8092a544199933d7634a17864c269ba397","abstract_canon_sha256":"1b2c42e6668b2d464b641f1c035c28ae7c7feefbfcfd8060a9a8bf27b9352c61"},"schema_version":"1.0"},"canonical_sha256":"8e371608780c00df534e88f9a062c6e906f48c195d073373accb44e9bbafacd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:26.837125Z","signature_b64":"qLPGzCOtWfeEXmqtZBrGEUykbujc6zEfdYnuhxINg+daJ8SJs0bEhJv2z4giadRDjjkBZcGIYOc7SfRpXBF0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e371608780c00df534e88f9a062c6e906f48c195d073373accb44e9bbafacd9","last_reissued_at":"2026-07-05T05:50:26.836776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:26.836776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.07109","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:50:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ssuwNqPFOwQKG0YIBhwEyEqTAtFc/4fqHLaqtRzkpRnRFOxG3TYN01zTyo0Ip+lw8Nb16gcFUUpB2X5gg5mBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:43:58.992213Z"},"content_sha256":"ecfb48e9167a5043feeee57e60ad3c75f5743f0acfa0054b11bf6e114f1655b1","schema_version":"1.0","event_id":"sha256:ecfb48e9167a5043feeee57e60ad3c75f5743f0acfa0054b11bf6e114f1655b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RY3RMCDYBQAN6U2ORD42AYWG5E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformer-based World Models Are Happy With 100k Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jan Robine, Marc H\\\"oftmann, Stefan Harmeling, Tobias Uelwer","submitted_at":"2023-03-13T13:43:59Z","abstract_excerpt":"Deep neural networks have been successful in many reinforcement learning settings. However, compared to human learners they are overly data hungry. To build a sample-efficient world model, we apply a transformer to real-world episodes in an autoregressive manner: not only the compact latent states and the taken actions but also the experienced or predicted rewards are fed into the transformer, so that it can attend flexibly to all three modalities at different time steps. The transformer allows our world model to access previous states directly, instead of viewing them through a compressed rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07109","kind":"arxiv","version":1},"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/2303.07109/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":"2026-07-05T05:50:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3tjtljV5/T4IUzo1EzUe3RQaUwETZIEk7k93R+XbapPx4uO1Ehnglkkd6jVio0EBNkuLuu2CdA6ybM7MqZsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T00:43:58.992858Z"},"content_sha256":"c63c09154a746759f1062bc88f5b8da064878265376bfab3e45a7e90778ecb24","schema_version":"1.0","event_id":"sha256:c63c09154a746759f1062bc88f5b8da064878265376bfab3e45a7e90778ecb24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RY3RMCDYBQAN6U2ORD42AYWG5E/bundle.json","state_url":"https://pith.science/pith/RY3RMCDYBQAN6U2ORD42AYWG5E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RY3RMCDYBQAN6U2ORD42AYWG5E/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":"2026-08-22T00:43:58Z","links":{"resolver":"https://pith.science/pith/RY3RMCDYBQAN6U2ORD42AYWG5E","bundle":"https://pith.science/pith/RY3RMCDYBQAN6U2ORD42AYWG5E/bundle.json","state":"https://pith.science/pith/RY3RMCDYBQAN6U2ORD42AYWG5E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RY3RMCDYBQAN6U2ORD42AYWG5E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RY3RMCDYBQAN6U2ORD42AYWG5E","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":"1b2c42e6668b2d464b641f1c035c28ae7c7feefbfcfd8060a9a8bf27b9352c61","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T13:43:59Z","title_canon_sha256":"d5df4af1476f67b707e18c84b2ceda8092a544199933d7634a17864c269ba397"},"schema_version":"1.0","source":{"id":"2303.07109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07109","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07109v1","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07109","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"pith_short_12","alias_value":"RY3RMCDYBQAN","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"pith_short_16","alias_value":"RY3RMCDYBQAN6U2O","created_at":"2026-07-05T05:50:26Z"},{"alias_kind":"pith_short_8","alias_value":"RY3RMCDY","created_at":"2026-07-05T05:50:26Z"}],"graph_snapshots":[{"event_id":"sha256:c63c09154a746759f1062bc88f5b8da064878265376bfab3e45a7e90778ecb24","target":"graph","created_at":"2026-07-05T05:50:26Z","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/2303.07109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks have been successful in many reinforcement learning settings. However, compared to human learners they are overly data hungry. To build a sample-efficient world model, we apply a transformer to real-world episodes in an autoregressive manner: not only the compact latent states and the taken actions but also the experienced or predicted rewards are fed into the transformer, so that it can attend flexibly to all three modalities at different time steps. The transformer allows our world model to access previous states directly, instead of viewing them through a compressed rec","authors_text":"Jan Robine, Marc H\\\"oftmann, Stefan Harmeling, Tobias Uelwer","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T13:43:59Z","title":"Transformer-based World Models Are Happy With 100k Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07109","kind":"arxiv","version":1},"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:ecfb48e9167a5043feeee57e60ad3c75f5743f0acfa0054b11bf6e114f1655b1","target":"record","created_at":"2026-07-05T05:50:26Z","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":"1b2c42e6668b2d464b641f1c035c28ae7c7feefbfcfd8060a9a8bf27b9352c61","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-13T13:43:59Z","title_canon_sha256":"d5df4af1476f67b707e18c84b2ceda8092a544199933d7634a17864c269ba397"},"schema_version":"1.0","source":{"id":"2303.07109","kind":"arxiv","version":1}},"canonical_sha256":"8e371608780c00df534e88f9a062c6e906f48c195d073373accb44e9bbafacd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e371608780c00df534e88f9a062c6e906f48c195d073373accb44e9bbafacd9","first_computed_at":"2026-07-05T05:50:26.836776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:50:26.836776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qLPGzCOtWfeEXmqtZBrGEUykbujc6zEfdYnuhxINg+daJ8SJs0bEhJv2z4giadRDjjkBZcGIYOc7SfRpXBF0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:50:26.837125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecfb48e9167a5043feeee57e60ad3c75f5743f0acfa0054b11bf6e114f1655b1","sha256:c63c09154a746759f1062bc88f5b8da064878265376bfab3e45a7e90778ecb24"],"state_sha256":"24adad7279d6fcf3554da64101e48ee59cefc409314dc77c9de83be7dba81b47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uAKoIuh1mLt35mJD8BWeYXkOHhvu+JmPZCLUWHjxMYUaP6yC5oXPfU5SLU1SEdvw6sm/hYzW16c6YLhM9d9qDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T00:43:58.998162Z","bundle_sha256":"9632c6bf0994ef64628179a0e82055e586aa4297d6c3fb3e9fc5ea7aae22bce6"}}