{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ODOBNJ3S2EPKT7T4MRP563EHW","short_pith_number":"pith:2ODOBNJ3","schema_version":"1.0","canonical_sha256":"d386e0b53b9688f54ff3e322fefb643daf9b63b44d316a091e3121622e84cabc","source":{"kind":"arxiv","id":"2506.05419","version":1},"attestation_state":"computed","paper":{"title":"Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jeongsoo Ha, Kyungsoo Kim, Yusung Kim","submitted_at":"2025-06-05T00:39:03Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) has been used to efficiently solve vision-based control tasks in highdimensional image observations. Although recent MBRL algorithms perform well in trained observations, they fail when faced with visual distractions in observations. These task-irrelevant distractions (e.g., clouds, shadows, and light) may be constantly present in real-world scenarios. In this study, we propose a novel self-supervised method, Dream to Generalize (Dr. G), for zero-shot MBRL. Dr. G trains its encoder and world model with dual contrastive learning which efficiently captur"},"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":"2506.05419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T00:39:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"17ba55264f65b40d16da2e830f8b8b3460ba82431ce733130fdc090f0e4d0d58","abstract_canon_sha256":"7f2f0b3b97bd3f26a83a3e209540dca8bc00257e89eac179723d2b9f394f4d48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:02.324402Z","signature_b64":"YJeg+Y1G+XFGNODgVbh3J1aiWpvJheDv/vR4jETQcA4xuVCxyeWrxKOFVV6BcgYLCLm6BA0UVV+F1gTNWRO1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d386e0b53b9688f54ff3e322fefb643daf9b63b44d316a091e3121622e84cabc","last_reissued_at":"2026-07-05T11:17:02.323916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:02.323916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dream to Generalize: Zero-Shot Model-Based Reinforcement Learning for Unseen Visual Distractions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jeongsoo Ha, Kyungsoo Kim, Yusung Kim","submitted_at":"2025-06-05T00:39:03Z","abstract_excerpt":"Model-based reinforcement learning (MBRL) has been used to efficiently solve vision-based control tasks in highdimensional image observations. Although recent MBRL algorithms perform well in trained observations, they fail when faced with visual distractions in observations. These task-irrelevant distractions (e.g., clouds, shadows, and light) may be constantly present in real-world scenarios. In this study, we propose a novel self-supervised method, Dream to Generalize (Dr. G), for zero-shot MBRL. Dr. G trains its encoder and world model with dual contrastive learning which efficiently captur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05419","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/2506.05419/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":"2506.05419","created_at":"2026-07-05T11:17:02.323971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05419v1","created_at":"2026-07-05T11:17:02.323971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05419","created_at":"2026-07-05T11:17:02.323971+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ODOBNJ3S2EP","created_at":"2026-07-05T11:17:02.323971+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ODOBNJ3S2EPKT7T","created_at":"2026-07-05T11:17:02.323971+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ODOBNJ3","created_at":"2026-07-05T11:17:02.323971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW","json":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW.json","graph_json":"https://pith.science/api/pith-number/2ODOBNJ3S2EPKT7T4MRP563EHW/graph.json","events_json":"https://pith.science/api/pith-number/2ODOBNJ3S2EPKT7T4MRP563EHW/events.json","paper":"https://pith.science/paper/2ODOBNJ3"},"agent_actions":{"view_html":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW","download_json":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW.json","view_paper":"https://pith.science/paper/2ODOBNJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05419&json=true","fetch_graph":"https://pith.science/api/pith-number/2ODOBNJ3S2EPKT7T4MRP563EHW/graph.json","fetch_events":"https://pith.science/api/pith-number/2ODOBNJ3S2EPKT7T4MRP563EHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW/action/storage_attestation","attest_author":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW/action/author_attestation","sign_citation":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW/action/citation_signature","submit_replication":"https://pith.science/pith/2ODOBNJ3S2EPKT7T4MRP563EHW/action/replication_record"}},"created_at":"2026-07-05T11:17:02.323971+00:00","updated_at":"2026-07-05T11:17:02.323971+00:00"}