{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BCELRMWIYLSNWO7SGTESNQJP77","short_pith_number":"pith:BCELRMWI","schema_version":"1.0","canonical_sha256":"0888b8b2c8c2e4db3bf234c926c12fffdf9c61c051115ce487e3b4b656b8a31e","source":{"kind":"arxiv","id":"2506.16627","version":2},"attestation_state":"computed","paper":{"title":"FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Aleksander Plocharski, Haotian Yin, Michal Jan Wlodarczyk, Mikolaj Kida, Przemyslaw Musialski","submitted_at":"2025-06-19T21:54:08Z","abstract_excerpt":"Neural signed-distance fields (SDFs) are a versatile backbone for neural geometry representation, but enforcing CAD-style developability usually requires Gaussian-curvature penalties with full Hessian evaluation and second-order differentiation, which are costly in memory and time. We introduce an off-diagonal Weingarten loss that regularizes only the mixed shape operator term that represents the gap between principal curvatures and flattens the surface. We present two variants: a finite-difference version using six SDF evaluations plus one gradient, and an auto-diff version using a single Hes"},"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":"2506.16627","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-06-19T21:54:08Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"1d2a5bb5001e6ded839f5a176be43db6159b61420b7a90b835f342a12802878a","abstract_canon_sha256":"bb98f62b4f1ab3957f5d10cb27821bf85803c04638a935d0e0eb2e99a76ed4a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:31.612678Z","signature_b64":"yIsnwiMx8Nshu7q6tYytOcDnmsrr1f7q5TsWztJqKBq4l7qsiRAPhu3ijLSn5KO9lors/VKD2eb/7u6GbtrODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0888b8b2c8c2e4db3bf234c926c12fffdf9c61c051115ce487e3b4b656b8a31e","last_reissued_at":"2026-07-05T11:58:31.612230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:31.612230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Aleksander Plocharski, Haotian Yin, Michal Jan Wlodarczyk, Mikolaj Kida, Przemyslaw Musialski","submitted_at":"2025-06-19T21:54:08Z","abstract_excerpt":"Neural signed-distance fields (SDFs) are a versatile backbone for neural geometry representation, but enforcing CAD-style developability usually requires Gaussian-curvature penalties with full Hessian evaluation and second-order differentiation, which are costly in memory and time. We introduce an off-diagonal Weingarten loss that regularizes only the mixed shape operator term that represents the gap between principal curvatures and flattens the surface. We present two variants: a finite-difference version using six SDF evaluations plus one gradient, and an auto-diff version using a single Hes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16627","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/2506.16627/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":"2506.16627","created_at":"2026-07-05T11:58:31.612286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16627v2","created_at":"2026-07-05T11:58:31.612286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16627","created_at":"2026-07-05T11:58:31.612286+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCELRMWIYLSN","created_at":"2026-07-05T11:58:31.612286+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCELRMWIYLSNWO7S","created_at":"2026-07-05T11:58:31.612286+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCELRMWI","created_at":"2026-07-05T11:58:31.612286+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/BCELRMWIYLSNWO7SGTESNQJP77","json":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77.json","graph_json":"https://pith.science/api/pith-number/BCELRMWIYLSNWO7SGTESNQJP77/graph.json","events_json":"https://pith.science/api/pith-number/BCELRMWIYLSNWO7SGTESNQJP77/events.json","paper":"https://pith.science/paper/BCELRMWI"},"agent_actions":{"view_html":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77","download_json":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77.json","view_paper":"https://pith.science/paper/BCELRMWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16627&json=true","fetch_graph":"https://pith.science/api/pith-number/BCELRMWIYLSNWO7SGTESNQJP77/graph.json","fetch_events":"https://pith.science/api/pith-number/BCELRMWIYLSNWO7SGTESNQJP77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77/action/storage_attestation","attest_author":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77/action/author_attestation","sign_citation":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77/action/citation_signature","submit_replication":"https://pith.science/pith/BCELRMWIYLSNWO7SGTESNQJP77/action/replication_record"}},"created_at":"2026-07-05T11:58:31.612286+00:00","updated_at":"2026-07-05T11:58:31.612286+00:00"}