{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T3S75OA7XHFXNU5XDIZYATNLAL","short_pith_number":"pith:T3S75OA7","schema_version":"1.0","canonical_sha256":"9ee5feb81fb9cb76d3b71a33804dab02cbb32561f0de13b9cb12d2e2e8052be0","source":{"kind":"arxiv","id":"2005.01819","version":1},"attestation_state":"computed","paper":{"title":"Neural Subdivision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Alec Jacobson, Hsueh-Ti Derek Liu, Noam Aigerman, Siddhartha Chaudhuri, Vladimir G. Kim","submitted_at":"2020-05-04T20:03:21Z","abstract_excerpt":"This paper introduces Neural Subdivision, a novel framework for data-driven coarse-to-fine geometry modeling. During inference, our method takes a coarse triangle mesh as input and recursively subdivides it to a finer geometry by applying the fixed topological updates of Loop Subdivision, but predicting vertex positions using a neural network conditioned on the local geometry of a patch. This approach enables us to learn complex non-linear subdivision schemes, beyond simple linear averaging used in classical techniques. One of our key contributions is a novel self-supervised training setup tha"},"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":"2005.01819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2020-05-04T20:03:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d43d398770ffb73bd78fe5830194f9f9ba38e4ed391aef92613c4f4b771ca47","abstract_canon_sha256":"d25613d104f25614458306639776c11e43d2965866dacf2017e3a090ff73ae2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:19.989761Z","signature_b64":"VPYWwEOzJlt/+gNM6OoNF1RbA0XWqMItI5959K6FvIfM0saVtXeGi5mkXIJgbRwS1d+h9hcPdn05Pj7Hm+JlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee5feb81fb9cb76d3b71a33804dab02cbb32561f0de13b9cb12d2e2e8052be0","last_reissued_at":"2026-07-05T01:00:19.989276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:19.989276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Subdivision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.GR","authors_text":"Alec Jacobson, Hsueh-Ti Derek Liu, Noam Aigerman, Siddhartha Chaudhuri, Vladimir G. Kim","submitted_at":"2020-05-04T20:03:21Z","abstract_excerpt":"This paper introduces Neural Subdivision, a novel framework for data-driven coarse-to-fine geometry modeling. During inference, our method takes a coarse triangle mesh as input and recursively subdivides it to a finer geometry by applying the fixed topological updates of Loop Subdivision, but predicting vertex positions using a neural network conditioned on the local geometry of a patch. This approach enables us to learn complex non-linear subdivision schemes, beyond simple linear averaging used in classical techniques. One of our key contributions is a novel self-supervised training setup tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01819","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/2005.01819/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":"2005.01819","created_at":"2026-07-05T01:00:19.989343+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.01819v1","created_at":"2026-07-05T01:00:19.989343+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01819","created_at":"2026-07-05T01:00:19.989343+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3S75OA7XHFX","created_at":"2026-07-05T01:00:19.989343+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3S75OA7XHFXNU5X","created_at":"2026-07-05T01:00:19.989343+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3S75OA7","created_at":"2026-07-05T01:00:19.989343+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27088","citing_title":"SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18069","citing_title":"Blended Chart Surfaces: A Seamless Explicit Representation for Smooth Surface Fitting","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08744","citing_title":"MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL","json":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL.json","graph_json":"https://pith.science/api/pith-number/T3S75OA7XHFXNU5XDIZYATNLAL/graph.json","events_json":"https://pith.science/api/pith-number/T3S75OA7XHFXNU5XDIZYATNLAL/events.json","paper":"https://pith.science/paper/T3S75OA7"},"agent_actions":{"view_html":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL","download_json":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL.json","view_paper":"https://pith.science/paper/T3S75OA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.01819&json=true","fetch_graph":"https://pith.science/api/pith-number/T3S75OA7XHFXNU5XDIZYATNLAL/graph.json","fetch_events":"https://pith.science/api/pith-number/T3S75OA7XHFXNU5XDIZYATNLAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL/action/storage_attestation","attest_author":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL/action/author_attestation","sign_citation":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL/action/citation_signature","submit_replication":"https://pith.science/pith/T3S75OA7XHFXNU5XDIZYATNLAL/action/replication_record"}},"created_at":"2026-07-05T01:00:19.989343+00:00","updated_at":"2026-07-05T01:00:19.989343+00:00"}