{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UM4ORRCFYXBUOGWI5IETB7NQMI","short_pith_number":"pith:UM4ORRCF","schema_version":"1.0","canonical_sha256":"a338e8c445c5c3471ac8ea0930fdb06214ac7f92c8bd2da8031fa445dde29274","source":{"kind":"arxiv","id":"2502.04317","version":1},"attestation_state":"computed","paper":{"title":"Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Kamenev, Chris Choy, Jan Kautz, Jean Kossaifi, Kamyar Azizzadenesheli, Max Rietmann","submitted_at":"2025-02-06T18:57:57Z","abstract_excerpt":"Computational Fluid Dynamics (CFD) is crucial for automotive design, requiring the analysis of large 3D point clouds to study how vehicle geometry affects pressure fields and drag forces. However, existing deep learning approaches for CFD struggle with the computational complexity of processing high-resolution 3D data. We propose Factorized Implicit Global Convolution (FIGConv), a novel architecture that efficiently solves CFD problems for very large 3D meshes with arbitrary input and output geometries. FIGConv achieves quadratic complexity $O(N^2)$, a significant improvement over existing 3D "},"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":"2502.04317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T18:57:57Z","cross_cats_sorted":[],"title_canon_sha256":"32b8eedbe6f6165c1b8c9dc884d14431f5217255ab5e35190481079374bbd767","abstract_canon_sha256":"a708a11df7296a74bb2c84f8fca23632b399ec33ddcf3c4f92b4c80ac5550ee0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:36.665814Z","signature_b64":"BaPP9wDgrkyWCwxMwnd8fK/pEjGZi6VXjZWUC4httgjd+Yulep5eiSgctSmshgC1RjU98CuSHDmBszSufknDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a338e8c445c5c3471ac8ea0930fdb06214ac7f92c8bd2da8031fa445dde29274","last_reissued_at":"2026-07-05T10:10:36.665339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:36.665339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Kamenev, Chris Choy, Jan Kautz, Jean Kossaifi, Kamyar Azizzadenesheli, Max Rietmann","submitted_at":"2025-02-06T18:57:57Z","abstract_excerpt":"Computational Fluid Dynamics (CFD) is crucial for automotive design, requiring the analysis of large 3D point clouds to study how vehicle geometry affects pressure fields and drag forces. However, existing deep learning approaches for CFD struggle with the computational complexity of processing high-resolution 3D data. We propose Factorized Implicit Global Convolution (FIGConv), a novel architecture that efficiently solves CFD problems for very large 3D meshes with arbitrary input and output geometries. FIGConv achieves quadratic complexity $O(N^2)$, a significant improvement over existing 3D "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04317","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/2502.04317/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":"2502.04317","created_at":"2026-07-05T10:10:36.665397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04317v1","created_at":"2026-07-05T10:10:36.665397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04317","created_at":"2026-07-05T10:10:36.665397+00:00"},{"alias_kind":"pith_short_12","alias_value":"UM4ORRCFYXBU","created_at":"2026-07-05T10:10:36.665397+00:00"},{"alias_kind":"pith_short_16","alias_value":"UM4ORRCFYXBUOGWI","created_at":"2026-07-05T10:10:36.665397+00:00"},{"alias_kind":"pith_short_8","alias_value":"UM4ORRCF","created_at":"2026-07-05T10:10:36.665397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07098","citing_title":"CarCrashNet: A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19565","citing_title":"HiLiftAeroML: High-Fidelity Computational Fluid Dynamics Dataset for High-Lift Aircraft Aerodynamics","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11111","citing_title":"ShardTensor: Domain Parallelism for Scientific Machine Learning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05586","citing_title":"AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modeling","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07098","citing_title":"CarCrashNet: A Large-Scale Dataset and Hierarchical Neural Solver for Data-Driven Structural Crash Simulation","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI","json":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI.json","graph_json":"https://pith.science/api/pith-number/UM4ORRCFYXBUOGWI5IETB7NQMI/graph.json","events_json":"https://pith.science/api/pith-number/UM4ORRCFYXBUOGWI5IETB7NQMI/events.json","paper":"https://pith.science/paper/UM4ORRCF"},"agent_actions":{"view_html":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI","download_json":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI.json","view_paper":"https://pith.science/paper/UM4ORRCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04317&json=true","fetch_graph":"https://pith.science/api/pith-number/UM4ORRCFYXBUOGWI5IETB7NQMI/graph.json","fetch_events":"https://pith.science/api/pith-number/UM4ORRCFYXBUOGWI5IETB7NQMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI/action/storage_attestation","attest_author":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI/action/author_attestation","sign_citation":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI/action/citation_signature","submit_replication":"https://pith.science/pith/UM4ORRCFYXBUOGWI5IETB7NQMI/action/replication_record"}},"created_at":"2026-07-05T10:10:36.665397+00:00","updated_at":"2026-07-05T10:10:36.665397+00:00"}