{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6IFHTACY2ZKIY7BWERNGNOKW5T","short_pith_number":"pith:6IFHTACY","schema_version":"1.0","canonical_sha256":"f20a798058d6548c7c36245a66b956ecf76089ce49dad8ddf1dca1df9431749a","source":{"kind":"arxiv","id":"2410.18956","version":2},"attestation_state":"computed","paper":{"title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achuta Kadambi, Boris Ivanovic, Danfei Xu, Jian Zhang, Kairun Wen, Marco Pavone, Peihao Wang, Renjie Li, Shijie Zhou, Wenyan Cong, Yue Wang, Zhangyang Wang, Zhiwen Fan","submitted_at":"2024-10-24T17:54:42Z","abstract_excerpt":"Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into multiple subtasks, each requiring complex transformations between different data representations. For instance, dense reconstruction through Structure-from-Motion (SfM) involves converting images into key points, optimizing camera parameters, and estimating structures. Afterward, accurate sparse reconstructions are required for further dense modeling, which is subsequently fed into task-specific neural networks. This m"},"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":"2410.18956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T17:54:42Z","cross_cats_sorted":[],"title_canon_sha256":"97f14e311998a59bf81f542e26e080e8730b0445ecccfa4e5c161fd1f6ec2506","abstract_canon_sha256":"49f76bfefe69d962d87e026ccb62bd8b420336e4f3bc0d8255ed3e1ce58b9ad0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:56.626934Z","signature_b64":"xXvr/lEYRa/3p+aktXgO0R/8WANDloIZN40Ogb8ghjpd2wTP5KKH01qHjAH0YZ75jDvG4+xmL1QuycTFEduHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f20a798058d6548c7c36245a66b956ecf76089ce49dad8ddf1dca1df9431749a","last_reissued_at":"2026-07-05T09:28:56.626439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:56.626439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achuta Kadambi, Boris Ivanovic, Danfei Xu, Jian Zhang, Kairun Wen, Marco Pavone, Peihao Wang, Renjie Li, Shijie Zhou, Wenyan Cong, Yue Wang, Zhangyang Wang, Zhiwen Fan","submitted_at":"2024-10-24T17:54:42Z","abstract_excerpt":"Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into multiple subtasks, each requiring complex transformations between different data representations. For instance, dense reconstruction through Structure-from-Motion (SfM) involves converting images into key points, optimizing camera parameters, and estimating structures. Afterward, accurate sparse reconstructions are required for further dense modeling, which is subsequently fed into task-specific neural networks. This m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18956","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/2410.18956/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":"2410.18956","created_at":"2026-07-05T09:28:56.626505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18956v2","created_at":"2026-07-05T09:28:56.626505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18956","created_at":"2026-07-05T09:28:56.626505+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IFHTACY2ZKI","created_at":"2026-07-05T09:28:56.626505+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IFHTACY2ZKIY7BW","created_at":"2026-07-05T09:28:56.626505+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IFHTACY","created_at":"2026-07-05T09:28:56.626505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09862","citing_title":"FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T","json":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T.json","graph_json":"https://pith.science/api/pith-number/6IFHTACY2ZKIY7BWERNGNOKW5T/graph.json","events_json":"https://pith.science/api/pith-number/6IFHTACY2ZKIY7BWERNGNOKW5T/events.json","paper":"https://pith.science/paper/6IFHTACY"},"agent_actions":{"view_html":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T","download_json":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T.json","view_paper":"https://pith.science/paper/6IFHTACY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18956&json=true","fetch_graph":"https://pith.science/api/pith-number/6IFHTACY2ZKIY7BWERNGNOKW5T/graph.json","fetch_events":"https://pith.science/api/pith-number/6IFHTACY2ZKIY7BWERNGNOKW5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T/action/storage_attestation","attest_author":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T/action/author_attestation","sign_citation":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T/action/citation_signature","submit_replication":"https://pith.science/pith/6IFHTACY2ZKIY7BWERNGNOKW5T/action/replication_record"}},"created_at":"2026-07-05T09:28:56.626505+00:00","updated_at":"2026-07-05T09:28:56.626505+00:00"}