{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TDPHGDNHNN4IOAOQXUYGRRGQTU","short_pith_number":"pith:TDPHGDNH","schema_version":"1.0","canonical_sha256":"98de730da76b788701d0bd3068c4d09d195a28b84e25ac3e3639ecc0afa02db3","source":{"kind":"arxiv","id":"2602.03045","version":2},"attestation_state":"computed","paper":{"title":"Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Hu, Bo Yuan, Petr Molodyk, Yongxin Chen, Zelin Zhao","submitted_at":"2026-02-03T03:10:27Z","abstract_excerpt":"Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural-language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints may conflict. However, existing fine-tuned models tend to reactively follow the user instructions and hallucinate dimensions when the text is ambiguous. To address this, we propose a proactive agentic framework for text-to-CadQuery generation, named as ProCAD, that resolves specification issues befor"},"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":"2602.03045","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T03:10:27Z","cross_cats_sorted":[],"title_canon_sha256":"37a403a40e09a76498f685ee0cb4fdc560eee5df65a575ae64c7bfd0ca829d78","abstract_canon_sha256":"6a6c6a2e158ab19e0766498cd82cc24abba25740112ca3fc5b2c459d29085065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:54.328481Z","signature_b64":"o5RTJQ25ENGGhCaNo9bHqWrA/LC7XibBALoRgVkcEa918NUA3FP33dzZP6ZDT96RPSnrUG+tg74lvjvLWweqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98de730da76b788701d0bd3068c4d09d195a28b84e25ac3e3639ecc0afa02db3","last_reissued_at":"2026-06-19T16:09:54.328044Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:54.328044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Hu, Bo Yuan, Petr Molodyk, Yongxin Chen, Zelin Zhao","submitted_at":"2026-02-03T03:10:27Z","abstract_excerpt":"Large language models have recently enabled text-to-CAD systems that synthesize parametric CAD programs (e.g., CadQuery) from natural-language prompts. In practice, however, geometric descriptions can be under-specified or internally inconsistent: critical dimensions may be missing and constraints may conflict. However, existing fine-tuned models tend to reactively follow the user instructions and hallucinate dimensions when the text is ambiguous. To address this, we propose a proactive agentic framework for text-to-CadQuery generation, named as ProCAD, that resolves specification issues befor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03045","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/2602.03045/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":"2602.03045","created_at":"2026-06-19T16:09:54.328101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.03045v2","created_at":"2026-06-19T16:09:54.328101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03045","created_at":"2026-06-19T16:09:54.328101+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDPHGDNHNN4I","created_at":"2026-06-19T16:09:54.328101+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDPHGDNHNN4IOAOQ","created_at":"2026-06-19T16:09:54.328101+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDPHGDNH","created_at":"2026-06-19T16:09:54.328101+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/TDPHGDNHNN4IOAOQXUYGRRGQTU","json":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU.json","graph_json":"https://pith.science/api/pith-number/TDPHGDNHNN4IOAOQXUYGRRGQTU/graph.json","events_json":"https://pith.science/api/pith-number/TDPHGDNHNN4IOAOQXUYGRRGQTU/events.json","paper":"https://pith.science/paper/TDPHGDNH"},"agent_actions":{"view_html":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU","download_json":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU.json","view_paper":"https://pith.science/paper/TDPHGDNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.03045&json=true","fetch_graph":"https://pith.science/api/pith-number/TDPHGDNHNN4IOAOQXUYGRRGQTU/graph.json","fetch_events":"https://pith.science/api/pith-number/TDPHGDNHNN4IOAOQXUYGRRGQTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU/action/storage_attestation","attest_author":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU/action/author_attestation","sign_citation":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU/action/citation_signature","submit_replication":"https://pith.science/pith/TDPHGDNHNN4IOAOQXUYGRRGQTU/action/replication_record"}},"created_at":"2026-06-19T16:09:54.328101+00:00","updated_at":"2026-06-19T16:09:54.328101+00:00"}