{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZNS5JZOQPB55UAZLJO6PA2FXF","short_pith_number":"pith:TZNS5JZO","schema_version":"1.0","canonical_sha256":"9e5b2ea72e83c3ded0195a5de78345b97a4630da5342e87504e050f4c98efa25","source":{"kind":"arxiv","id":"2501.00602","version":1},"attestation_state":"computed","paper":{"title":"STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Apoorva Sharma, Boris Ivanovic, Boyi Li, Danfei Xu, Jiahui Huang, Jiawei Yang, Marco Pavone, Maximilian Igl, Peter Karkus, Yan Wang, Yue Wang, Yurong You, Yuxiao Chen","submitted_at":"2024-12-31T18:59:58Z","abstract_excerpt":"We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often rely on per-scene optimization, dense observations across space and time, and strong motion supervision, resulting in lengthy optimization times, limited generalization to novel views or scenes, and degenerated quality caused by noisy pseudo-labels for dynamics. To address these challenges, STORM leverages a data-driven Transformer architecture that directly infers dynamic 3D scene representations--parameterized by 3"},"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":"2501.00602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T18:59:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6bbfb0aafc336f780bf477e034cc6b9a31854e7b11ab2fd0a62846cc28899cf4","abstract_canon_sha256":"f640fc2b285c1008568f3c8867641da2674efd042d8549e27a8b83d2ccd6a58d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:08.004386Z","signature_b64":"UsKSDsZYlf259XHEECjQe8Ald4VyWRr9+fc407ki3dr+G5xl+46/KGrBMiNV7bNeUMgWGF8FcI5LzQbnPQL8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e5b2ea72e83c3ded0195a5de78345b97a4630da5342e87504e050f4c98efa25","last_reissued_at":"2026-07-05T09:56:08.003955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:08.003955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Apoorva Sharma, Boris Ivanovic, Boyi Li, Danfei Xu, Jiahui Huang, Jiawei Yang, Marco Pavone, Maximilian Igl, Peter Karkus, Yan Wang, Yue Wang, Yurong You, Yuxiao Chen","submitted_at":"2024-12-31T18:59:58Z","abstract_excerpt":"We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often rely on per-scene optimization, dense observations across space and time, and strong motion supervision, resulting in lengthy optimization times, limited generalization to novel views or scenes, and degenerated quality caused by noisy pseudo-labels for dynamics. To address these challenges, STORM leverages a data-driven Transformer architecture that directly infers dynamic 3D scene representations--parameterized by 3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00602","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/2501.00602/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":"2501.00602","created_at":"2026-07-05T09:56:08.004022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00602v1","created_at":"2026-07-05T09:56:08.004022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00602","created_at":"2026-07-05T09:56:08.004022+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZNS5JZOQPB5","created_at":"2026-07-05T09:56:08.004022+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZNS5JZOQPB55UAZ","created_at":"2026-07-05T09:56:08.004022+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZNS5JZO","created_at":"2026-07-05T09:56:08.004022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10656","citing_title":"Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18137","citing_title":"Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29374","citing_title":"L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30347","citing_title":"FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23180","citing_title":"GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18137","citing_title":"Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.23369","citing_title":"SimScale: Learning to Drive via Real-World Simulation at Scale","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03210","citing_title":"Flux4D: Flow-based Unsupervised 4D Reconstruction","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11594","citing_title":"PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26238","citing_title":"EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09688","citing_title":"ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15239","citing_title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04435","citing_title":"Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF","json":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF.json","graph_json":"https://pith.science/api/pith-number/TZNS5JZOQPB55UAZLJO6PA2FXF/graph.json","events_json":"https://pith.science/api/pith-number/TZNS5JZOQPB55UAZLJO6PA2FXF/events.json","paper":"https://pith.science/paper/TZNS5JZO"},"agent_actions":{"view_html":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF","download_json":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF.json","view_paper":"https://pith.science/paper/TZNS5JZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00602&json=true","fetch_graph":"https://pith.science/api/pith-number/TZNS5JZOQPB55UAZLJO6PA2FXF/graph.json","fetch_events":"https://pith.science/api/pith-number/TZNS5JZOQPB55UAZLJO6PA2FXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF/action/storage_attestation","attest_author":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF/action/author_attestation","sign_citation":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF/action/citation_signature","submit_replication":"https://pith.science/pith/TZNS5JZOQPB55UAZLJO6PA2FXF/action/replication_record"}},"created_at":"2026-07-05T09:56:08.004022+00:00","updated_at":"2026-07-05T09:56:08.004022+00:00"}