{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RKEQ353E4JDQ4RU6AQRQ2YHEC7","short_pith_number":"pith:RKEQ353E","schema_version":"1.0","canonical_sha256":"8a890df764e2470e469e04230d60e417e463be73d36e736a3dac1897d5b3cdb3","source":{"kind":"arxiv","id":"2308.13934","version":2},"attestation_state":"computed","paper":{"title":"Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.GR","authors_text":"Congyi Zhang, Guodong Wei, Guying Lin, Hao Pan, John Keyser, Lei Yang, Taku Komura, Wenping Wang, Yuhan Ping","submitted_at":"2023-08-26T18:20:38Z","abstract_excerpt":"Neural implicit representations are widely used for 3D shape modeling due to their smoothness and compactness, but traditional MLP-based methods struggle with sharp features, such as edges and corners in CAD models, and require long training times. To address these limitations, we propose Patch-Grid, a unified neural implicit representation that efficiently fits complex shapes, preserves sharp features, and handles open boundaries and thin geometric structures. Patch-Grid learns a signed distance field (SDF) for each surface patch using a learnable patch feature volume. To represent sharp edge"},"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":"2308.13934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2023-08-26T18:20:38Z","cross_cats_sorted":[],"title_canon_sha256":"32d074224d6a3cf2c12eed96594a09fe4656b12f24d14d690c9402c6ca618960","abstract_canon_sha256":"46a538abb1b4d8f5777cbd8372c52d2c0b8f28c6909bba75f5bfa1ff64dc0564"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:39.765573Z","signature_b64":"/YJmIiat/xdO37n8CMFi6GviFA+R46nxGEHcHre7eA+qEyPKlTXNvaWlxqdgcdTVnVWq+Ollu2Ug0poHByBoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a890df764e2470e469e04230d60e417e463be73d36e736a3dac1897d5b3cdb3","last_reissued_at":"2026-07-05T10:31:39.764635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:39.764635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.GR","authors_text":"Congyi Zhang, Guodong Wei, Guying Lin, Hao Pan, John Keyser, Lei Yang, Taku Komura, Wenping Wang, Yuhan Ping","submitted_at":"2023-08-26T18:20:38Z","abstract_excerpt":"Neural implicit representations are widely used for 3D shape modeling due to their smoothness and compactness, but traditional MLP-based methods struggle with sharp features, such as edges and corners in CAD models, and require long training times. To address these limitations, we propose Patch-Grid, a unified neural implicit representation that efficiently fits complex shapes, preserves sharp features, and handles open boundaries and thin geometric structures. Patch-Grid learns a signed distance field (SDF) for each surface patch using a learnable patch feature volume. To represent sharp edge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13934","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/2308.13934/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":"2308.13934","created_at":"2026-07-05T10:31:39.764724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13934v2","created_at":"2026-07-05T10:31:39.764724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13934","created_at":"2026-07-05T10:31:39.764724+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKEQ353E4JDQ","created_at":"2026-07-05T10:31:39.764724+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKEQ353E4JDQ4RU6","created_at":"2026-07-05T10:31:39.764724+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKEQ353E","created_at":"2026-07-05T10:31:39.764724+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/RKEQ353E4JDQ4RU6AQRQ2YHEC7","json":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7.json","graph_json":"https://pith.science/api/pith-number/RKEQ353E4JDQ4RU6AQRQ2YHEC7/graph.json","events_json":"https://pith.science/api/pith-number/RKEQ353E4JDQ4RU6AQRQ2YHEC7/events.json","paper":"https://pith.science/paper/RKEQ353E"},"agent_actions":{"view_html":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7","download_json":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7.json","view_paper":"https://pith.science/paper/RKEQ353E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13934&json=true","fetch_graph":"https://pith.science/api/pith-number/RKEQ353E4JDQ4RU6AQRQ2YHEC7/graph.json","fetch_events":"https://pith.science/api/pith-number/RKEQ353E4JDQ4RU6AQRQ2YHEC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7/action/storage_attestation","attest_author":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7/action/author_attestation","sign_citation":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7/action/citation_signature","submit_replication":"https://pith.science/pith/RKEQ353E4JDQ4RU6AQRQ2YHEC7/action/replication_record"}},"created_at":"2026-07-05T10:31:39.764724+00:00","updated_at":"2026-07-05T10:31:39.764724+00:00"}