{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CXFZBGMX4UPP2OKPE6OS3TP7QR","short_pith_number":"pith:CXFZBGMX","schema_version":"1.0","canonical_sha256":"15cb909997e51efd394f279d2dcdff84473fae5e22a346845c7c39a5c5f50161","source":{"kind":"arxiv","id":"2602.22284","version":3},"attestation_state":"computed","paper":{"title":"BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyungki Kim, Jungwoo Kang, Mingi Kim, Yongjun Kim","submitted_at":"2026-02-25T12:44:28Z","abstract_excerpt":"Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) domain.However, most existing approaches rely on task-specifi c models requiring structural modifi cations for new tasks, and they predominantly focus on point clouds or images rather than the industry-standard Boundary Representation (B-rep) format. To address these limitations, we propose BrepCoder, a unifi ed Multimodal Large Language Model (MLLM) that performs diverse CAD tasks from B-rep inputs. By leveraging the code generation capabilities of Large Language Models (LLMs"},"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":"2602.22284","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-25T12:44:28Z","cross_cats_sorted":[],"title_canon_sha256":"d623eb290376af843097fdaee4060eda19212bd6f378f58a34e31d15fd5619cb","abstract_canon_sha256":"ee4c8424a517ced9e36a32b95a9843c651f40d16a999d6c37c41fad5b93fd5a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:17.673780Z","signature_b64":"FnrCm2DZ8ssQ14hWMTmFQw9NRvdJkYqinU6oz7kJS1SQvGbB5zKWKxzQmd/iNCyCsaO7PjIhE8i/mtpv1eXPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15cb909997e51efd394f279d2dcdff84473fae5e22a346845c7c39a5c5f50161","last_reissued_at":"2026-06-26T01:15:17.673284Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:17.673284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyungki Kim, Jungwoo Kang, Mingi Kim, Yongjun Kim","submitted_at":"2026-02-25T12:44:28Z","abstract_excerpt":"Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) domain.However, most existing approaches rely on task-specifi c models requiring structural modifi cations for new tasks, and they predominantly focus on point clouds or images rather than the industry-standard Boundary Representation (B-rep) format. To address these limitations, we propose BrepCoder, a unifi ed Multimodal Large Language Model (MLLM) that performs diverse CAD tasks from B-rep inputs. By leveraging the code generation capabilities of Large Language Models (LLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22284","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/2602.22284/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":"2602.22284","created_at":"2026-06-26T01:15:17.673359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22284v3","created_at":"2026-06-26T01:15:17.673359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22284","created_at":"2026-06-26T01:15:17.673359+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXFZBGMX4UPP","created_at":"2026-06-26T01:15:17.673359+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXFZBGMX4UPP2OKP","created_at":"2026-06-26T01:15:17.673359+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXFZBGMX","created_at":"2026-06-26T01:15:17.673359+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.05515","citing_title":"BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR","json":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR.json","graph_json":"https://pith.science/api/pith-number/CXFZBGMX4UPP2OKPE6OS3TP7QR/graph.json","events_json":"https://pith.science/api/pith-number/CXFZBGMX4UPP2OKPE6OS3TP7QR/events.json","paper":"https://pith.science/paper/CXFZBGMX"},"agent_actions":{"view_html":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR","download_json":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR.json","view_paper":"https://pith.science/paper/CXFZBGMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22284&json=true","fetch_graph":"https://pith.science/api/pith-number/CXFZBGMX4UPP2OKPE6OS3TP7QR/graph.json","fetch_events":"https://pith.science/api/pith-number/CXFZBGMX4UPP2OKPE6OS3TP7QR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR/action/storage_attestation","attest_author":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR/action/author_attestation","sign_citation":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR/action/citation_signature","submit_replication":"https://pith.science/pith/CXFZBGMX4UPP2OKPE6OS3TP7QR/action/replication_record"}},"created_at":"2026-06-26T01:15:17.673359+00:00","updated_at":"2026-06-26T01:15:17.673359+00:00"}