{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LXQNYJM4VPTP3MEU6Z4DPK6MX2","short_pith_number":"pith:LXQNYJM4","schema_version":"1.0","canonical_sha256":"5de0dc259cabe6fdb094f67837abccbea66c748e80310e6ca7acf91a1939ed4a","source":{"kind":"arxiv","id":"2506.18017","version":1},"attestation_state":"computed","paper":{"title":"Auto-Regressive Surface Cutting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Biwen Lei, Chunchao Guo, Haohan Weng, Jingwei Huang, Victor Cheung, Xinhai Liu, Yang Li, Yuguang Chen, Zhongjin Luo, Zhuo Chen, Zibo Zhao","submitted_at":"2025-06-22T12:53:07Z","abstract_excerpt":"Surface cutting is a fundamental task in computer graphics, with applications in UV parameterization, texture mapping, and mesh decomposition. However, existing methods often produce technically valid but overly fragmented atlases that lack semantic coherence. We introduce SeamGPT, an auto-regressive model that generates cutting seams by mimicking professional workflows. Our key technical innovation lies in formulating surface cutting as a next token prediction task: sample point clouds on mesh vertices and edges, encode them as shape conditions, and employ a GPT-style transformer to sequentia"},"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":"2506.18017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-06-22T12:53:07Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8a7c426f87c2248236d22ca68f7689b4de8abe9b5d567a64eb28af8d45ad3fc4","abstract_canon_sha256":"ef9f24d6f3df92d14b6a553946206ca57e432f954398652dde32c0fde016222d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:27.160464Z","signature_b64":"ZGb1ZdngLvzsqQRMOr1q0FIOn9nBhr+qPcvsjSP8LKoqQokILAbTG/Cl7awUv9lEZb3m3QSmQCsFmTWm1d9jDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5de0dc259cabe6fdb094f67837abccbea66c748e80310e6ca7acf91a1939ed4a","last_reissued_at":"2026-07-05T11:25:27.159940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:27.159940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-Regressive Surface Cutting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Biwen Lei, Chunchao Guo, Haohan Weng, Jingwei Huang, Victor Cheung, Xinhai Liu, Yang Li, Yuguang Chen, Zhongjin Luo, Zhuo Chen, Zibo Zhao","submitted_at":"2025-06-22T12:53:07Z","abstract_excerpt":"Surface cutting is a fundamental task in computer graphics, with applications in UV parameterization, texture mapping, and mesh decomposition. However, existing methods often produce technically valid but overly fragmented atlases that lack semantic coherence. We introduce SeamGPT, an auto-regressive model that generates cutting seams by mimicking professional workflows. Our key technical innovation lies in formulating surface cutting as a next token prediction task: sample point clouds on mesh vertices and edges, encode them as shape conditions, and employ a GPT-style transformer to sequentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18017","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/2506.18017/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":"2506.18017","created_at":"2026-07-05T11:25:27.159999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18017v1","created_at":"2026-07-05T11:25:27.159999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18017","created_at":"2026-07-05T11:25:27.159999+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXQNYJM4VPTP","created_at":"2026-07-05T11:25:27.159999+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXQNYJM4VPTP3MEU","created_at":"2026-07-05T11:25:27.159999+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXQNYJM4","created_at":"2026-07-05T11:25:27.159999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22445","citing_title":"DreamUV: Unwrap Artist-like UV by End-to-End Flow Matching","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16813","citing_title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","ref_index":230,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2","json":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2.json","graph_json":"https://pith.science/api/pith-number/LXQNYJM4VPTP3MEU6Z4DPK6MX2/graph.json","events_json":"https://pith.science/api/pith-number/LXQNYJM4VPTP3MEU6Z4DPK6MX2/events.json","paper":"https://pith.science/paper/LXQNYJM4"},"agent_actions":{"view_html":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2","download_json":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2.json","view_paper":"https://pith.science/paper/LXQNYJM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18017&json=true","fetch_graph":"https://pith.science/api/pith-number/LXQNYJM4VPTP3MEU6Z4DPK6MX2/graph.json","fetch_events":"https://pith.science/api/pith-number/LXQNYJM4VPTP3MEU6Z4DPK6MX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2/action/storage_attestation","attest_author":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2/action/author_attestation","sign_citation":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2/action/citation_signature","submit_replication":"https://pith.science/pith/LXQNYJM4VPTP3MEU6Z4DPK6MX2/action/replication_record"}},"created_at":"2026-07-05T11:25:27.159999+00:00","updated_at":"2026-07-05T11:25:27.159999+00:00"}