{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OCGDATC2RZEMO5IKK3BH4CLSNP","short_pith_number":"pith:OCGDATC2","schema_version":"1.0","canonical_sha256":"708c304c5a8e48c7750a56c27e09726bd14c68f422265349e431ce0d200ddc74","source":{"kind":"arxiv","id":"2505.06507","version":1},"attestation_state":"computed","paper":{"title":"Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Feng Ju, Haoyang Xie","submitted_at":"2025-05-10T04:47:08Z","abstract_excerpt":"Computer-aided design (CAD) is fundamental to modern engineering and manufacturing, but creating CAD models still requires expert knowledge and specialized software. Recent advances in large language models (LLMs) open up the possibility of generative CAD, where natural language is directly translated into parametric 3D models. However, most existing methods generate task-specific command sequences that pretrained models cannot directly handle. These sequences must be converted into CAD representations such as CAD vectors before a 3D model can be produced, which requires training models from s"},"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":"2505.06507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-10T04:47:08Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"615d8dc32d0a087ceaf5ab17202ba80a8ed71d9a158926747ae5de50ab5bff7a","abstract_canon_sha256":"806eaa7b97eed4ac0076be32b23d0b2ccd2e4468e063e47dd472db2f6a5225c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:10.754757Z","signature_b64":"VJ/CcgdJlqd1mW9pxvEwyHgZ3n6e6K6yzAth1XrrDGQHmSJwYHXeaKlU2792yR82iTsJmI9t60DhBD+QU5/iBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"708c304c5a8e48c7750a56c27e09726bd14c68f422265349e431ce0d200ddc74","last_reissued_at":"2026-07-05T11:01:10.754257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:10.754257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Feng Ju, Haoyang Xie","submitted_at":"2025-05-10T04:47:08Z","abstract_excerpt":"Computer-aided design (CAD) is fundamental to modern engineering and manufacturing, but creating CAD models still requires expert knowledge and specialized software. Recent advances in large language models (LLMs) open up the possibility of generative CAD, where natural language is directly translated into parametric 3D models. However, most existing methods generate task-specific command sequences that pretrained models cannot directly handle. These sequences must be converted into CAD representations such as CAD vectors before a 3D model can be produced, which requires training models from s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06507","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/2505.06507/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":"2505.06507","created_at":"2026-07-05T11:01:10.754322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06507v1","created_at":"2026-07-05T11:01:10.754322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06507","created_at":"2026-07-05T11:01:10.754322+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCGDATC2RZEM","created_at":"2026-07-05T11:01:10.754322+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCGDATC2RZEMO5IK","created_at":"2026-07-05T11:01:10.754322+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCGDATC2","created_at":"2026-07-05T11:01:10.754322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"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":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13368","citing_title":"IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11152","citing_title":"P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05058","citing_title":"UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02434","citing_title":"Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10873","citing_title":"CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13368","citing_title":"IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17448","citing_title":"Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29301","citing_title":"Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01031","citing_title":"CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20190","citing_title":"Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration","ref_index":36,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17448","citing_title":"Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01031","citing_title":"CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19171","citing_title":"HistCAD: A Constraint-Aware Parametric History-Based CAD Representation, Dataset, and Benchmark with Industrial Complexity","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04337","citing_title":"Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19773","citing_title":"PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10873","citing_title":"CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10992","citing_title":"ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code Generation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05547","citing_title":"COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15184","citing_title":"Agent-Aided Design for Dynamic CAD Models","ref_index":37,"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":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP","json":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP.json","graph_json":"https://pith.science/api/pith-number/OCGDATC2RZEMO5IKK3BH4CLSNP/graph.json","events_json":"https://pith.science/api/pith-number/OCGDATC2RZEMO5IKK3BH4CLSNP/events.json","paper":"https://pith.science/paper/OCGDATC2"},"agent_actions":{"view_html":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP","download_json":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP.json","view_paper":"https://pith.science/paper/OCGDATC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06507&json=true","fetch_graph":"https://pith.science/api/pith-number/OCGDATC2RZEMO5IKK3BH4CLSNP/graph.json","fetch_events":"https://pith.science/api/pith-number/OCGDATC2RZEMO5IKK3BH4CLSNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP/action/storage_attestation","attest_author":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP/action/author_attestation","sign_citation":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP/action/citation_signature","submit_replication":"https://pith.science/pith/OCGDATC2RZEMO5IKK3BH4CLSNP/action/replication_record"}},"created_at":"2026-07-05T11:01:10.754322+00:00","updated_at":"2026-07-05T11:01:10.754322+00:00"}