{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7FXY535EWNWFHNQIDL46N5WMUU","short_pith_number":"pith:7FXY535E","schema_version":"1.0","canonical_sha256":"f96f8eefa4b36c53b6081af9e6f6cca524990a189b59af1ec5cf95c32dfe3d15","source":{"kind":"arxiv","id":"2302.02408","version":2},"attestation_state":"computed","paper":{"title":"Multi-View Masked World Models for Visual Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jinwoo Shin, Junsu Kim, Kimin Lee, Pieter Abbeel, Stephen James, Younggyo Seo","submitted_at":"2023-02-05T15:37:02Z","abstract_excerpt":"Visual robotic manipulation research and applications often use multiple cameras, or views, to better perceive the world. How else can we utilize the richness of multi-view data? In this paper, we investigate how to learn good representations with multi-view data and utilize them for visual robotic manipulation. Specifically, we train a multi-view masked autoencoder which reconstructs pixels of randomly masked viewpoints and then learn a world model operating on the representations from the autoencoder. We demonstrate the effectiveness of our method in a range of scenarios, including multi-vie"},"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":"2302.02408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-05T15:37:02Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c40631d4840e086e507972f60af7397d3ae5075742d1c7e793af61e5f8a47a54","abstract_canon_sha256":"18186bad6d12b4cceb1ea668227fcda6b810453fa096645c72e0930de423f890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:45.415828Z","signature_b64":"G/ZS4hc1Se30BYV8dAmg7+XLQXPBfCDvVdHIKqr9LTSFPcPx0gMEpbofjv5QqiUo7Ru06eQU3jMm83jX6eG2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f96f8eefa4b36c53b6081af9e6f6cca524990a189b59af1ec5cf95c32dfe3d15","last_reissued_at":"2026-07-05T06:15:45.415369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:45.415369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-View Masked World Models for Visual Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jinwoo Shin, Junsu Kim, Kimin Lee, Pieter Abbeel, Stephen James, Younggyo Seo","submitted_at":"2023-02-05T15:37:02Z","abstract_excerpt":"Visual robotic manipulation research and applications often use multiple cameras, or views, to better perceive the world. How else can we utilize the richness of multi-view data? In this paper, we investigate how to learn good representations with multi-view data and utilize them for visual robotic manipulation. Specifically, we train a multi-view masked autoencoder which reconstructs pixels of randomly masked viewpoints and then learn a world model operating on the representations from the autoencoder. We demonstrate the effectiveness of our method in a range of scenarios, including multi-vie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02408","kind":"arxiv","version":2},"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/2302.02408/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":"2302.02408","created_at":"2026-07-05T06:15:45.415427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02408v2","created_at":"2026-07-05T06:15:45.415427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02408","created_at":"2026-07-05T06:15:45.415427+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FXY535EWNWF","created_at":"2026-07-05T06:15:45.415427+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FXY535EWNWFHNQI","created_at":"2026-07-05T06:15:45.415427+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FXY535E","created_at":"2026-07-05T06:15:45.415427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05579","citing_title":"ARGUS: Aligning Robot Scene Geometry Under Shifting Views with Large 3D Vision Models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU","json":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU.json","graph_json":"https://pith.science/api/pith-number/7FXY535EWNWFHNQIDL46N5WMUU/graph.json","events_json":"https://pith.science/api/pith-number/7FXY535EWNWFHNQIDL46N5WMUU/events.json","paper":"https://pith.science/paper/7FXY535E"},"agent_actions":{"view_html":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU","download_json":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU.json","view_paper":"https://pith.science/paper/7FXY535E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02408&json=true","fetch_graph":"https://pith.science/api/pith-number/7FXY535EWNWFHNQIDL46N5WMUU/graph.json","fetch_events":"https://pith.science/api/pith-number/7FXY535EWNWFHNQIDL46N5WMUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU/action/storage_attestation","attest_author":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU/action/author_attestation","sign_citation":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU/action/citation_signature","submit_replication":"https://pith.science/pith/7FXY535EWNWFHNQIDL46N5WMUU/action/replication_record"}},"created_at":"2026-07-05T06:15:45.415427+00:00","updated_at":"2026-07-05T06:15:45.415427+00:00"}