{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JRQ3VRLDQESYDCM6V5GSXYETB7","short_pith_number":"pith:JRQ3VRLD","schema_version":"1.0","canonical_sha256":"4c61bac563812581899eaf4d2be0930ff9cd90ccc2db42da404a7476bbef9838","source":{"kind":"arxiv","id":"2501.19054","version":3},"attestation_state":"computed","paper":{"title":"Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiang Bian, Ruiyu Wang, Shizhao Sun, Yu Yuan","submitted_at":"2025-01-31T11:28:16Z","abstract_excerpt":"Creating Computer-Aided Design (CAD) models requires significant expertise and effort. Text-to-CAD, which converts textual descriptions into CAD parametric sequences, is crucial in streamlining this process. Recent studies have utilized ground-truth parametric sequences, known as sequential signals, as supervision to achieve this goal. However, CAD models are inherently multimodal, comprising parametric sequences and corresponding rendered visual objects. Besides,the rendering process from parametric sequences to visual objects is many-to-one. Therefore, both sequential and visual signals are "},"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":"2501.19054","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T11:28:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6b83abcd777c231e84d466f9685f63e442faf7004c407d3c2f4545d71d5e397d","abstract_canon_sha256":"d6edf2f1f7c85de6f80138da28d089b81711ee815383039f5d6c496b8c5193ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:05.656661Z","signature_b64":"IFtqIUi3nJpXFsoE3CDIsgJx15Xx2s5siPR9V9XnBqzVn905JTWI1rRakvllY/jB7K9p571MbJVaBVtnIxDiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c61bac563812581899eaf4d2be0930ff9cd90ccc2db42da404a7476bbef9838","last_reissued_at":"2026-07-05T11:16:05.656075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:05.656075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jiang Bian, Ruiyu Wang, Shizhao Sun, Yu Yuan","submitted_at":"2025-01-31T11:28:16Z","abstract_excerpt":"Creating Computer-Aided Design (CAD) models requires significant expertise and effort. Text-to-CAD, which converts textual descriptions into CAD parametric sequences, is crucial in streamlining this process. Recent studies have utilized ground-truth parametric sequences, known as sequential signals, as supervision to achieve this goal. However, CAD models are inherently multimodal, comprising parametric sequences and corresponding rendered visual objects. Besides,the rendering process from parametric sequences to visual objects is many-to-one. Therefore, both sequential and visual signals are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19054","kind":"arxiv","version":3},"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/2501.19054/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":"2501.19054","created_at":"2026-07-05T11:16:05.656156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19054v3","created_at":"2026-07-05T11:16:05.656156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19054","created_at":"2026-07-05T11:16:05.656156+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRQ3VRLDQESY","created_at":"2026-07-05T11:16:05.656156+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRQ3VRLDQESYDCM6","created_at":"2026-07-05T11:16:05.656156+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRQ3VRLD","created_at":"2026-07-05T11:16:05.656156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05750","citing_title":"ArtisanCAD: An Industrial-Level CAD Agent with Expert-Grounded Knowledge Distillation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20146","citing_title":"BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17696","citing_title":"FllumaOne: A Code-Native Multimodal CAD Dataset with Executable Programs and Kernel-Validated Feature Histories","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05515","citing_title":"BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28579","citing_title":"MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18430","citing_title":"Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19717","citing_title":"Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19748","citing_title":"Memory-Augmented Reinforcement Learning Agent for CAD Generation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19713","citing_title":"CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16170","citing_title":"neuralCAD-Edit: An Expert Benchmark for Multimodal-Instructed 3D CAD Model Editing","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7","json":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7.json","graph_json":"https://pith.science/api/pith-number/JRQ3VRLDQESYDCM6V5GSXYETB7/graph.json","events_json":"https://pith.science/api/pith-number/JRQ3VRLDQESYDCM6V5GSXYETB7/events.json","paper":"https://pith.science/paper/JRQ3VRLD"},"agent_actions":{"view_html":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7","download_json":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7.json","view_paper":"https://pith.science/paper/JRQ3VRLD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19054&json=true","fetch_graph":"https://pith.science/api/pith-number/JRQ3VRLDQESYDCM6V5GSXYETB7/graph.json","fetch_events":"https://pith.science/api/pith-number/JRQ3VRLDQESYDCM6V5GSXYETB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7/action/storage_attestation","attest_author":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7/action/author_attestation","sign_citation":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7/action/citation_signature","submit_replication":"https://pith.science/pith/JRQ3VRLDQESYDCM6V5GSXYETB7/action/replication_record"}},"created_at":"2026-07-05T11:16:05.656156+00:00","updated_at":"2026-07-05T11:16:05.656156+00:00"}