{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2ADZGDWN6APBSGOTU63JCMBZG4","short_pith_number":"pith:2ADZGDWN","schema_version":"1.0","canonical_sha256":"d007930ecdf01e1919d3a7b69130393735bdfec5c3ef9b163638f6468997b78d","source":{"kind":"arxiv","id":"2412.09621","version":2},"attestation_state":"computed","paper":{"title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, David Fouhey, Linyi Jin, Noah Snavely, Richard Tucker, Zhengqi Li","submitted_at":"2024-12-12T18:59:54Z","abstract_excerpt":"Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly supervising methods for recovering 3D motion remains challenging due to the fundamental difficulty of obtaining ground truth annotations. We present a system for mining high-quality 4D reconstructions from internet stereoscopic, wide-angle videos. Our system fuses and filters the outputs of camera pose estimation, stereo depth estimation, and temporal tracking method"},"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":"2412.09621","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:54Z","cross_cats_sorted":[],"title_canon_sha256":"3b65c5b7c036625a7c2c37cbf42d4732610ba5a731173c61534513745495dc3f","abstract_canon_sha256":"9ddb0e4b1c84045a12884ec1f92c6342c4d6cabdb036dd48442bddb65010cd41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:13.199932Z","signature_b64":"98uTCGA33cxXn9PWWucUuBdeCuUEri3AOdasV449GPYya8gG4FEOuddjFSj2ccJtAq0HOWMIn5mZpo3XqoYRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d007930ecdf01e1919d3a7b69130393735bdfec5c3ef9b163638f6468997b78d","last_reissued_at":"2026-07-05T10:56:13.199473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:13.199473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksander Holynski, David Fouhey, Linyi Jin, Noah Snavely, Richard Tucker, Zhengqi Li","submitted_at":"2024-12-12T18:59:54Z","abstract_excerpt":"Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly supervising methods for recovering 3D motion remains challenging due to the fundamental difficulty of obtaining ground truth annotations. We present a system for mining high-quality 4D reconstructions from internet stereoscopic, wide-angle videos. Our system fuses and filters the outputs of camera pose estimation, stereo depth estimation, and temporal tracking method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09621","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/2412.09621/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":"2412.09621","created_at":"2026-07-05T10:56:13.199532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09621v2","created_at":"2026-07-05T10:56:13.199532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09621","created_at":"2026-07-05T10:56:13.199532+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ADZGDWN6APB","created_at":"2026-07-05T10:56:13.199532+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ADZGDWN6APBSGOT","created_at":"2026-07-05T10:56:13.199532+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ADZGDWN","created_at":"2026-07-05T10:56:13.199532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18558","citing_title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13122","citing_title":"DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00181","citing_title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12587","citing_title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05207","citing_title":"Syn4D: A Multiview Synthetic 4D Dataset","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4","json":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4.json","graph_json":"https://pith.science/api/pith-number/2ADZGDWN6APBSGOTU63JCMBZG4/graph.json","events_json":"https://pith.science/api/pith-number/2ADZGDWN6APBSGOTU63JCMBZG4/events.json","paper":"https://pith.science/paper/2ADZGDWN"},"agent_actions":{"view_html":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4","download_json":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4.json","view_paper":"https://pith.science/paper/2ADZGDWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09621&json=true","fetch_graph":"https://pith.science/api/pith-number/2ADZGDWN6APBSGOTU63JCMBZG4/graph.json","fetch_events":"https://pith.science/api/pith-number/2ADZGDWN6APBSGOTU63JCMBZG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4/action/storage_attestation","attest_author":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4/action/author_attestation","sign_citation":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4/action/citation_signature","submit_replication":"https://pith.science/pith/2ADZGDWN6APBSGOTU63JCMBZG4/action/replication_record"}},"created_at":"2026-07-05T10:56:13.199532+00:00","updated_at":"2026-07-05T10:56:13.199532+00:00"}