{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z543TA55LN7WK4NL2VHFBT72WX","short_pith_number":"pith:Z543TA55","schema_version":"1.0","canonical_sha256":"cf79b983bd5b7f6571abd54e50cffab5fea48455de9243e7584756e74a92ff57","source":{"kind":"arxiv","id":"2402.14009","version":4},"attestation_state":"computed","paper":{"title":"Geometry-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andreas Radler, Arturs Berzins, Eric Volkmann, Johannes Brandstetter, Sebastian Sanokowski, Sepp Hochreiter","submitted_at":"2024-02-21T18:50:12Z","abstract_excerpt":"Geometry is a ubiquitous tool in computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learning methods and motivates the exploration of alternative learning strategies. To this end, we introduce geometry-informed neural networks (GINNs) -- a framework for training shape-generative neural fields without data by leveraging user-specified design requirements in the form of objectives and constraints. By adding diversity as an explicit constraint, GINNs avoid mode-collapse and can generate multiple diverse solut"},"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":"2402.14009","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T18:50:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1fbe6d5be7f0d462d9c3bd8ca2705c825c1c6dfa7a8939b9f8f0f2e9ae347441","abstract_canon_sha256":"56d97b19cd06531f0aff144a717118bd79f327bc9900b3508c85c5dc703c9078"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:02.241013Z","signature_b64":"xeT+qthNpeXdTAqAugBKU5CxQZxnHTsWkahNPujeVadK28tbNeGRt5RZwCuHGbKFET4JC7mgcKhU7y/mDI4vCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf79b983bd5b7f6571abd54e50cffab5fea48455de9243e7584756e74a92ff57","last_reissued_at":"2026-07-05T11:39:02.240571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:02.240571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry-Informed Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andreas Radler, Arturs Berzins, Eric Volkmann, Johannes Brandstetter, Sebastian Sanokowski, Sepp Hochreiter","submitted_at":"2024-02-21T18:50:12Z","abstract_excerpt":"Geometry is a ubiquitous tool in computer graphics, design, and engineering. However, the lack of large shape datasets limits the application of state-of-the-art supervised learning methods and motivates the exploration of alternative learning strategies. To this end, we introduce geometry-informed neural networks (GINNs) -- a framework for training shape-generative neural fields without data by leveraging user-specified design requirements in the form of objectives and constraints. By adding diversity as an explicit constraint, GINNs avoid mode-collapse and can generate multiple diverse solut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14009","kind":"arxiv","version":4},"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/2402.14009/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":"2402.14009","created_at":"2026-07-05T11:39:02.240624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14009v4","created_at":"2026-07-05T11:39:02.240624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14009","created_at":"2026-07-05T11:39:02.240624+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z543TA55LN7W","created_at":"2026-07-05T11:39:02.240624+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z543TA55LN7WK4NL","created_at":"2026-07-05T11:39:02.240624+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z543TA55","created_at":"2026-07-05T11:39:02.240624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07682","citing_title":"Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24243","citing_title":"GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19469","citing_title":"GLUE: Coordinating Pre-Trained Generative Models for System-Level Design","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX","json":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX.json","graph_json":"https://pith.science/api/pith-number/Z543TA55LN7WK4NL2VHFBT72WX/graph.json","events_json":"https://pith.science/api/pith-number/Z543TA55LN7WK4NL2VHFBT72WX/events.json","paper":"https://pith.science/paper/Z543TA55"},"agent_actions":{"view_html":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX","download_json":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX.json","view_paper":"https://pith.science/paper/Z543TA55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14009&json=true","fetch_graph":"https://pith.science/api/pith-number/Z543TA55LN7WK4NL2VHFBT72WX/graph.json","fetch_events":"https://pith.science/api/pith-number/Z543TA55LN7WK4NL2VHFBT72WX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX/action/storage_attestation","attest_author":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX/action/author_attestation","sign_citation":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX/action/citation_signature","submit_replication":"https://pith.science/pith/Z543TA55LN7WK4NL2VHFBT72WX/action/replication_record"}},"created_at":"2026-07-05T11:39:02.240624+00:00","updated_at":"2026-07-05T11:39:02.240624+00:00"}