{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YA46O7VHFZM5AZ2N4D7MYVMIKY","short_pith_number":"pith:YA46O7VH","schema_version":"1.0","canonical_sha256":"c039e77ea72e59d0674de0fecc55885612537d3ffb4b363fed88222b2fd0b363","source":{"kind":"arxiv","id":"2505.23287","version":1},"attestation_state":"computed","paper":{"title":"GenCAD-Self-Repairing: Feasibility Enhancement for 3D CAD Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chikaha Tsuji, Enrique Flores Medina, Harshit Gupta, Md Ferdous Alam","submitted_at":"2025-05-29T09:39:19Z","abstract_excerpt":"With the advancement of generative AI, research on its application to 3D model generation has gained traction, particularly in automating the creation of Computer-Aided Design (CAD) files from images. GenCAD is a notable model in this domain, leveraging an autoregressive transformer-based architecture with a contrastive learning framework to generate CAD programs.\n  However, a major limitation of GenCAD is its inability to consistently produce feasible boundary representations (B-reps), with approximately 10% of generated designs being infeasible. To address this, we propose GenCAD-Self-Repair"},"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":"2505.23287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T09:39:19Z","cross_cats_sorted":[],"title_canon_sha256":"20d5495cd03ee514048add6544b4d8749e235de1ac83b29c18aa1717811b1280","abstract_canon_sha256":"b53acc8dd587ed22efd6103bac01387bd5494db36a0bd5f60c87ba1eb98d6044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:58.959598Z","signature_b64":"UD00kVKS33rpcfxzztZJMBNEqWhu7GPVpkd6KwsoXiuDdAmjEiqYgx+d4r61Omsx+jxPyKNpVAappMMdeiFXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c039e77ea72e59d0674de0fecc55885612537d3ffb4b363fed88222b2fd0b363","last_reissued_at":"2026-07-05T11:11:58.959105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:58.959105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenCAD-Self-Repairing: Feasibility Enhancement for 3D CAD Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chikaha Tsuji, Enrique Flores Medina, Harshit Gupta, Md Ferdous Alam","submitted_at":"2025-05-29T09:39:19Z","abstract_excerpt":"With the advancement of generative AI, research on its application to 3D model generation has gained traction, particularly in automating the creation of Computer-Aided Design (CAD) files from images. GenCAD is a notable model in this domain, leveraging an autoregressive transformer-based architecture with a contrastive learning framework to generate CAD programs.\n  However, a major limitation of GenCAD is its inability to consistently produce feasible boundary representations (B-reps), with approximately 10% of generated designs being infeasible. To address this, we propose GenCAD-Self-Repair"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23287","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/2505.23287/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":"2505.23287","created_at":"2026-07-05T11:11:58.959157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23287v1","created_at":"2026-07-05T11:11:58.959157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23287","created_at":"2026-07-05T11:11:58.959157+00:00"},{"alias_kind":"pith_short_12","alias_value":"YA46O7VHFZM5","created_at":"2026-07-05T11:11:58.959157+00:00"},{"alias_kind":"pith_short_16","alias_value":"YA46O7VHFZM5AZ2N","created_at":"2026-07-05T11:11:58.959157+00:00"},{"alias_kind":"pith_short_8","alias_value":"YA46O7VH","created_at":"2026-07-05T11:11:58.959157+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/YA46O7VHFZM5AZ2N4D7MYVMIKY","json":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY.json","graph_json":"https://pith.science/api/pith-number/YA46O7VHFZM5AZ2N4D7MYVMIKY/graph.json","events_json":"https://pith.science/api/pith-number/YA46O7VHFZM5AZ2N4D7MYVMIKY/events.json","paper":"https://pith.science/paper/YA46O7VH"},"agent_actions":{"view_html":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY","download_json":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY.json","view_paper":"https://pith.science/paper/YA46O7VH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23287&json=true","fetch_graph":"https://pith.science/api/pith-number/YA46O7VHFZM5AZ2N4D7MYVMIKY/graph.json","fetch_events":"https://pith.science/api/pith-number/YA46O7VHFZM5AZ2N4D7MYVMIKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY/action/storage_attestation","attest_author":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY/action/author_attestation","sign_citation":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY/action/citation_signature","submit_replication":"https://pith.science/pith/YA46O7VHFZM5AZ2N4D7MYVMIKY/action/replication_record"}},"created_at":"2026-07-05T11:11:58.959157+00:00","updated_at":"2026-07-05T11:11:58.959157+00:00"}