{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IRW4YIN647LK2FWPIMUNZ3H5CZ","short_pith_number":"pith:IRW4YIN6","schema_version":"1.0","canonical_sha256":"446dcc21bee7d6ad16cf4328dcecfd1655a0071b322dcdb2a7a3414bdcf4fc4c","source":{"kind":"arxiv","id":"2206.14176","version":1},"attestation_state":"computed","paper":{"title":"DayDreamer: World Models for Physical Robot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alejandro Escontrela, Danijar Hafner, Ken Goldberg, Philipp Wu, Pieter Abbeel","submitted_at":"2022-06-28T17:44:48Z","abstract_excerpt":"To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the physical world. As a consequence, many advances in robot learning rely on simulators. On the other hand, learning inside of simulators fails to capture the complexity of the real world, is prone to simulator inaccuracies, and the resulting behaviors do not adapt to changes in the world. The Dreamer algorithm has recently shown great promise for learning from small "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.14176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-06-28T17:44:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e371c455cb7f912f7267b3d2aad73dbc4e05944b701459f4e154d284184bbeb","abstract_canon_sha256":"e57684a6a3d2b40fd4a918bce41afaa76980c206913546152e9e724aa3707f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:53.836023Z","signature_b64":"0c2nePEw3jsByjt2Ta+/JnSz6pUvAHO7+SkJGwpybnFgrZOA8b3uEevjthiyYYWoYrfHIL4BG5iAzx9A8oblCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446dcc21bee7d6ad16cf4328dcecfd1655a0071b322dcdb2a7a3414bdcf4fc4c","last_reissued_at":"2026-07-05T04:35:53.835646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:53.835646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DayDreamer: World Models for Physical Robot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Alejandro Escontrela, Danijar Hafner, Ken Goldberg, Philipp Wu, Pieter Abbeel","submitted_at":"2022-06-28T17:44:48Z","abstract_excerpt":"To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the physical world. As a consequence, many advances in robot learning rely on simulators. On the other hand, learning inside of simulators fails to capture the complexity of the real world, is prone to simulator inaccuracies, and the resulting behaviors do not adapt to changes in the world. The Dreamer algorithm has recently shown great promise for learning from small "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.14176","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/2206.14176/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.14176","created_at":"2026-07-05T04:35:53.835708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.14176v1","created_at":"2026-07-05T04:35:53.835708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.14176","created_at":"2026-07-05T04:35:53.835708+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRW4YIN647LK","created_at":"2026-07-05T04:35:53.835708+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRW4YIN647LK2FWP","created_at":"2026-07-05T04:35:53.835708+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRW4YIN6","created_at":"2026-07-05T04:35:53.835708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15015","citing_title":"NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02486","citing_title":"Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.15032","citing_title":"How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01694","citing_title":"Latent State Design for World Models under Sufficiency Constraints","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ","json":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ.json","graph_json":"https://pith.science/api/pith-number/IRW4YIN647LK2FWPIMUNZ3H5CZ/graph.json","events_json":"https://pith.science/api/pith-number/IRW4YIN647LK2FWPIMUNZ3H5CZ/events.json","paper":"https://pith.science/paper/IRW4YIN6"},"agent_actions":{"view_html":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ","download_json":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ.json","view_paper":"https://pith.science/paper/IRW4YIN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.14176&json=true","fetch_graph":"https://pith.science/api/pith-number/IRW4YIN647LK2FWPIMUNZ3H5CZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IRW4YIN647LK2FWPIMUNZ3H5CZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ/action/storage_attestation","attest_author":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ/action/author_attestation","sign_citation":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ/action/citation_signature","submit_replication":"https://pith.science/pith/IRW4YIN647LK2FWPIMUNZ3H5CZ/action/replication_record"}},"created_at":"2026-07-05T04:35:53.835708+00:00","updated_at":"2026-07-05T04:35:53.835708+00:00"}