{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HRX7JTX5OX2QTB6JUGL5TZUV3F","short_pith_number":"pith:HRX7JTX5","canonical_record":{"source":{"id":"2509.05735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T14:52:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4448a2bfb7360af35d3dd8b7494e1a50bb9a8823d1f68b00ac511d0ac8268bb","abstract_canon_sha256":"9164ee157ac61e1af09ccc6fec8ebe89e10089946277212794c21bde3f176c4a"},"schema_version":"1.0"},"canonical_sha256":"3c6ff4cefd75f50987c9a197d9e695d974ad0847750c57ce2afdcbaa5e778658","source":{"kind":"arxiv","id":"2509.05735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05735","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05735v1","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05735","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"pith_short_12","alias_value":"HRX7JTX5OX2Q","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"pith_short_16","alias_value":"HRX7JTX5OX2QTB6J","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"pith_short_8","alias_value":"HRX7JTX5","created_at":"2026-07-05T12:06:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HRX7JTX5OX2QTB6JUGL5TZUV3F","target":"record","payload":{"canonical_record":{"source":{"id":"2509.05735","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T14:52:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4448a2bfb7360af35d3dd8b7494e1a50bb9a8823d1f68b00ac511d0ac8268bb","abstract_canon_sha256":"9164ee157ac61e1af09ccc6fec8ebe89e10089946277212794c21bde3f176c4a"},"schema_version":"1.0"},"canonical_sha256":"3c6ff4cefd75f50987c9a197d9e695d974ad0847750c57ce2afdcbaa5e778658","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:23.203020Z","signature_b64":"jFu//EsiZTgiKfKrZVqVPGkoTZTMC/b4KTUvI3wbhPjN51DlfVXTR2Uvufw7+RxA68iIB8E/0CtfjAbc5JWEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c6ff4cefd75f50987c9a197d9e695d974ad0847750c57ce2afdcbaa5e778658","last_reissued_at":"2026-07-05T12:06:23.202513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:23.202513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.05735","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":"2026-07-05T12:06:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbcSh8bZc9Ckg6AuuyOnIK2NfzwgCqSbeKXISyGcDB7YEke2Wimt4l4Q87HVkeTqvjeNU+TVwt2KAbWhaDFcAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:09:03.510115Z"},"content_sha256":"19765740c46b902ec8a844836b2d491d1ca9c64c816ed09d359956d9fcc3dcd8","schema_version":"1.0","event_id":"sha256:19765740c46b902ec8a844836b2d491d1ca9c64c816ed09d359956d9fcc3dcd8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HRX7JTX5OX2QTB6JUGL5TZUV3F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cansu Sancaktar, Georg Martius, Jiaqi Chen, Ji Shi, Jonas Frey","submitted_at":"2025-09-06T14:52:33Z","abstract_excerpt":"Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting with the environment during online training or training on offline datasets. At first glance, the nature of learning task-agnostic environment dynamics makes world models a good candidate for effective offline training. However, the effects of online vs. offline data on world models and thus on the resulting task performance have not been thoroughly studied in the literature. In this work, we investigate both paradi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05735","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/2509.05735/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":"2026-07-05T12:06:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k92/uxIEJT7ZkPkj3hJIFwvm+dbjLssY1UxVbIcmpHDnIW6QEGVQtEkPvFLdeqkpvZOAgYH/XOSZm7bXRs0dCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:09:03.510837Z"},"content_sha256":"6536aaac173546c9792b1eda9fc68d36b59757973fb9e571f2668402f1d0b802","schema_version":"1.0","event_id":"sha256:6536aaac173546c9792b1eda9fc68d36b59757973fb9e571f2668402f1d0b802"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRX7JTX5OX2QTB6JUGL5TZUV3F/bundle.json","state_url":"https://pith.science/pith/HRX7JTX5OX2QTB6JUGL5TZUV3F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRX7JTX5OX2QTB6JUGL5TZUV3F/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":"2026-08-19T14:09:03Z","links":{"resolver":"https://pith.science/pith/HRX7JTX5OX2QTB6JUGL5TZUV3F","bundle":"https://pith.science/pith/HRX7JTX5OX2QTB6JUGL5TZUV3F/bundle.json","state":"https://pith.science/pith/HRX7JTX5OX2QTB6JUGL5TZUV3F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRX7JTX5OX2QTB6JUGL5TZUV3F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HRX7JTX5OX2QTB6JUGL5TZUV3F","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":"9164ee157ac61e1af09ccc6fec8ebe89e10089946277212794c21bde3f176c4a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T14:52:33Z","title_canon_sha256":"d4448a2bfb7360af35d3dd8b7494e1a50bb9a8823d1f68b00ac511d0ac8268bb"},"schema_version":"1.0","source":{"id":"2509.05735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05735","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05735v1","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05735","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"pith_short_12","alias_value":"HRX7JTX5OX2Q","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"pith_short_16","alias_value":"HRX7JTX5OX2QTB6J","created_at":"2026-07-05T12:06:23Z"},{"alias_kind":"pith_short_8","alias_value":"HRX7JTX5","created_at":"2026-07-05T12:06:23Z"}],"graph_snapshots":[{"event_id":"sha256:6536aaac173546c9792b1eda9fc68d36b59757973fb9e571f2668402f1d0b802","target":"graph","created_at":"2026-07-05T12:06:23Z","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/2509.05735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting with the environment during online training or training on offline datasets. At first glance, the nature of learning task-agnostic environment dynamics makes world models a good candidate for effective offline training. However, the effects of online vs. offline data on world models and thus on the resulting task performance have not been thoroughly studied in the literature. In this work, we investigate both paradi","authors_text":"Cansu Sancaktar, Georg Martius, Jiaqi Chen, Ji Shi, Jonas Frey","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T14:52:33Z","title":"Offline vs. Online Learning in Model-based RL: Lessons for Data Collection Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05735","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":"sha256:19765740c46b902ec8a844836b2d491d1ca9c64c816ed09d359956d9fcc3dcd8","target":"record","created_at":"2026-07-05T12:06:23Z","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":"9164ee157ac61e1af09ccc6fec8ebe89e10089946277212794c21bde3f176c4a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T14:52:33Z","title_canon_sha256":"d4448a2bfb7360af35d3dd8b7494e1a50bb9a8823d1f68b00ac511d0ac8268bb"},"schema_version":"1.0","source":{"id":"2509.05735","kind":"arxiv","version":1}},"canonical_sha256":"3c6ff4cefd75f50987c9a197d9e695d974ad0847750c57ce2afdcbaa5e778658","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c6ff4cefd75f50987c9a197d9e695d974ad0847750c57ce2afdcbaa5e778658","first_computed_at":"2026-07-05T12:06:23.202513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:23.202513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jFu//EsiZTgiKfKrZVqVPGkoTZTMC/b4KTUvI3wbhPjN51DlfVXTR2Uvufw7+RxA68iIB8E/0CtfjAbc5JWEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:23.203020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19765740c46b902ec8a844836b2d491d1ca9c64c816ed09d359956d9fcc3dcd8","sha256:6536aaac173546c9792b1eda9fc68d36b59757973fb9e571f2668402f1d0b802"],"state_sha256":"cdc9b70e6e30d17ec4ac24f46a31cdb602196b1e9b834452bcedba140821964a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iA7me6givQ7srGMwaLpSKpEodYirIq9rsoICM3mwygp/LIHOfKBb8Y1O5Fbzh3Zffn01EXT5cGl5235YN02jCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:09:03.515659Z","bundle_sha256":"429472457137a1137f754b5f2db6acd458343f62f843180885207e7522273c6c"}}