{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUHBC3YGXEDEB4MGKYXCPJSCFU","short_pith_number":"pith:YUHBC3YG","schema_version":"1.0","canonical_sha256":"c50e116f06b90640f186562e27a6422d0dc55939ec21c2247593b82c8c9cea15","source":{"kind":"arxiv","id":"2412.07770","version":1},"attestation_state":"computed","paper":{"title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Kusupati, Ali Farhadi, Anand Bhattad, Aniruddha Kembhavi, Matt Deitke, Matthew Wallingford, Roozbeh Mottaghi, Sham Kakade, Vivek Ramanujan, Wei-Chiu Ma","submitted_at":"2024-12-10T18:59:44Z","abstract_excerpt":"Three-dimensional (3D) understanding of objects and scenes play a key role in humans' ability to interact with the world and has been an active area of research in computer vision, graphics, and robotics. Large scale synthetic and object-centric 3D datasets have shown to be effective in training models that have 3D understanding of objects. However, applying a similar approach to real-world objects and scenes is difficult due to a lack of large-scale data. Videos are a potential source for real-world 3D data, but finding diverse yet corresponding views of the same content has shown to be diffi"},"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":"2412.07770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ffe13388c152178d62d9e5f9ae74c9a51b099e7b634fa8d7f1c4ade344cdabe4","abstract_canon_sha256":"5f41ffabf5b807b9c5403a3b1ab6b39d88d106a179183e8a587437ebedfe19e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:15.128187Z","signature_b64":"ppEgGD0hULIF78S3RGjOGfml1j5at9ya4ZEfqWWjfSnNA/X6ShayPoAoNkwWHr0OCMfOFBX/b/Kj7bW14dl1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50e116f06b90640f186562e27a6422d0dc55939ec21c2247593b82c8c9cea15","last_reissued_at":"2026-07-05T09:47:15.127688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:15.127688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Kusupati, Ali Farhadi, Anand Bhattad, Aniruddha Kembhavi, Matt Deitke, Matthew Wallingford, Roozbeh Mottaghi, Sham Kakade, Vivek Ramanujan, Wei-Chiu Ma","submitted_at":"2024-12-10T18:59:44Z","abstract_excerpt":"Three-dimensional (3D) understanding of objects and scenes play a key role in humans' ability to interact with the world and has been an active area of research in computer vision, graphics, and robotics. Large scale synthetic and object-centric 3D datasets have shown to be effective in training models that have 3D understanding of objects. However, applying a similar approach to real-world objects and scenes is difficult due to a lack of large-scale data. Videos are a potential source for real-world 3D data, but finding diverse yet corresponding views of the same content has shown to be diffi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07770","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/2412.07770/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":"2412.07770","created_at":"2026-07-05T09:47:15.127750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07770v1","created_at":"2026-07-05T09:47:15.127750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07770","created_at":"2026-07-05T09:47:15.127750+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUHBC3YGXEDE","created_at":"2026-07-05T09:47:15.127750+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUHBC3YGXEDEB4MG","created_at":"2026-07-05T09:47:15.127750+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUHBC3YG","created_at":"2026-07-05T09:47:15.127750+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/YUHBC3YGXEDEB4MGKYXCPJSCFU","json":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU.json","graph_json":"https://pith.science/api/pith-number/YUHBC3YGXEDEB4MGKYXCPJSCFU/graph.json","events_json":"https://pith.science/api/pith-number/YUHBC3YGXEDEB4MGKYXCPJSCFU/events.json","paper":"https://pith.science/paper/YUHBC3YG"},"agent_actions":{"view_html":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU","download_json":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU.json","view_paper":"https://pith.science/paper/YUHBC3YG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07770&json=true","fetch_graph":"https://pith.science/api/pith-number/YUHBC3YGXEDEB4MGKYXCPJSCFU/graph.json","fetch_events":"https://pith.science/api/pith-number/YUHBC3YGXEDEB4MGKYXCPJSCFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU/action/storage_attestation","attest_author":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU/action/author_attestation","sign_citation":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU/action/citation_signature","submit_replication":"https://pith.science/pith/YUHBC3YGXEDEB4MGKYXCPJSCFU/action/replication_record"}},"created_at":"2026-07-05T09:47:15.127750+00:00","updated_at":"2026-07-05T09:47:15.127750+00:00"}