{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KXSV5A53774JTNVBJYJIZUVIQB","short_pith_number":"pith:KXSV5A53","schema_version":"1.0","canonical_sha256":"55e55e83bbfff899b6a14e128cd2a880611b732bda8354916cd759d9fc15541c","source":{"kind":"arxiv","id":"2301.11497","version":2},"attestation_state":"computed","paper":{"title":"D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Ali Mahdavi Amiri, Fenggen Yu, Hao Zhang, Maham Tanveer, Qimin Chen","submitted_at":"2023-01-27T02:13:14Z","abstract_excerpt":"We present D$^2$CSG, a neural model composed of two dual and complementary network branches, with dropouts, for unsupervised learning of compact constructive solid geometry (CSG) representations of 3D CAD shapes. Our network is trained to reconstruct a 3D shape by a fixed-order assembly of quadric primitives, with both branches producing a union of primitive intersections or inverses. A key difference between D$^2$CSG and all prior neural CSG models is its dedicated residual branch to assemble the potentially complex shape complement, which is subtracted from an overall shape modeled by the co"},"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":"2301.11497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-27T02:13:14Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"cb787fa2b23bd239dd5b7136129949b684bd0c6b5d16dcf5eed70bca4bcffeec","abstract_canon_sha256":"3a8069423b4c59ea32024f54c77923c46e45755339e025a06b9162a5b9f123f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:15.282294Z","signature_b64":"gM0xDFZWPaEk4YJCiUzON2PQn5pFcQShOL0H+9BmiMfCQQGN9pG8Pkk0Wf9JF4hDkdLIXpiicznjriEZEhbXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55e55e83bbfff899b6a14e128cd2a880611b732bda8354916cd759d9fc15541c","last_reissued_at":"2026-07-05T06:16:15.281845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:15.281845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Ali Mahdavi Amiri, Fenggen Yu, Hao Zhang, Maham Tanveer, Qimin Chen","submitted_at":"2023-01-27T02:13:14Z","abstract_excerpt":"We present D$^2$CSG, a neural model composed of two dual and complementary network branches, with dropouts, for unsupervised learning of compact constructive solid geometry (CSG) representations of 3D CAD shapes. Our network is trained to reconstruct a 3D shape by a fixed-order assembly of quadric primitives, with both branches producing a union of primitive intersections or inverses. A key difference between D$^2$CSG and all prior neural CSG models is its dedicated residual branch to assemble the potentially complex shape complement, which is subtracted from an overall shape modeled by the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11497","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/2301.11497/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":"2301.11497","created_at":"2026-07-05T06:16:15.281903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11497v2","created_at":"2026-07-05T06:16:15.281903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11497","created_at":"2026-07-05T06:16:15.281903+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXSV5A53774J","created_at":"2026-07-05T06:16:15.281903+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXSV5A53774JTNVB","created_at":"2026-07-05T06:16:15.281903+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXSV5A53","created_at":"2026-07-05T06:16:15.281903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.21105","citing_title":"BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB","json":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB.json","graph_json":"https://pith.science/api/pith-number/KXSV5A53774JTNVBJYJIZUVIQB/graph.json","events_json":"https://pith.science/api/pith-number/KXSV5A53774JTNVBJYJIZUVIQB/events.json","paper":"https://pith.science/paper/KXSV5A53"},"agent_actions":{"view_html":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB","download_json":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB.json","view_paper":"https://pith.science/paper/KXSV5A53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11497&json=true","fetch_graph":"https://pith.science/api/pith-number/KXSV5A53774JTNVBJYJIZUVIQB/graph.json","fetch_events":"https://pith.science/api/pith-number/KXSV5A53774JTNVBJYJIZUVIQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB/action/storage_attestation","attest_author":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB/action/author_attestation","sign_citation":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB/action/citation_signature","submit_replication":"https://pith.science/pith/KXSV5A53774JTNVBJYJIZUVIQB/action/replication_record"}},"created_at":"2026-07-05T06:16:15.281903+00:00","updated_at":"2026-07-05T06:16:15.281903+00:00"}