{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WBFRFICAB7LNYL7TX4VZ4Q4PZN","short_pith_number":"pith:WBFRFICA","schema_version":"1.0","canonical_sha256":"b04b12a0400fd6dc2ff3bf2b9e438fcb4ca8579452f24075e6216851eb8cac99","source":{"kind":"arxiv","id":"2412.17808","version":3},"attestation_state":"computed","paper":{"title":"Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Luo, Jianfeng Zhang, Jiarui Liu, Jiashi Feng, Ping Tan, Rui Chen, Weiyu Li, Xiaoxiao Long, Xiu Li, Yixun Liang","submitted_at":"2024-12-23T18:59:06Z","abstract_excerpt":"Recent 3D content generation pipelines commonly employ Variational Autoencoders (VAEs) to encode shapes into compact latent representations for diffusion-based generation. However, the widely adopted uniform point sampling strategy in Shape VAE training often leads to a significant loss of geometric details, limiting the quality of shape reconstruction and downstream generation tasks. We present Dora-VAE, a novel approach that enhances VAE reconstruction through our proposed sharp edge sampling strategy and a dual cross-attention mechanism. By identifying and prioritizing regions with high geo"},"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":"2412.17808","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-23T18:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"339cb81496eb958c63171259bc9047be5113f737b60eccffaef1647e6646dc9d","abstract_canon_sha256":"a38daecbbe4cde2f12ba661eeb162288dd1edc2828ee7ee1e4f71ba3545ed065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:22.457423Z","signature_b64":"1a+Wy3aRxxP56qXUkGRJz3gSP9CeF2bfbJgrNJLVlt5o2HjsquIDkSpyNJ/8SdbXY1QnEbWDViWDMiJUo9OgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b04b12a0400fd6dc2ff3bf2b9e438fcb4ca8579452f24075e6216851eb8cac99","last_reissued_at":"2026-07-05T10:38:22.456946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:22.456946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guan Luo, Jianfeng Zhang, Jiarui Liu, Jiashi Feng, Ping Tan, Rui Chen, Weiyu Li, Xiaoxiao Long, Xiu Li, Yixun Liang","submitted_at":"2024-12-23T18:59:06Z","abstract_excerpt":"Recent 3D content generation pipelines commonly employ Variational Autoencoders (VAEs) to encode shapes into compact latent representations for diffusion-based generation. However, the widely adopted uniform point sampling strategy in Shape VAE training often leads to a significant loss of geometric details, limiting the quality of shape reconstruction and downstream generation tasks. We present Dora-VAE, a novel approach that enhances VAE reconstruction through our proposed sharp edge sampling strategy and a dual cross-attention mechanism. By identifying and prioritizing regions with high geo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17808","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/2412.17808/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":"2412.17808","created_at":"2026-07-05T10:38:22.457003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17808v3","created_at":"2026-07-05T10:38:22.457003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17808","created_at":"2026-07-05T10:38:22.457003+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBFRFICAB7LN","created_at":"2026-07-05T10:38:22.457003+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBFRFICAB7LNYL7T","created_at":"2026-07-05T10:38:22.457003+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBFRFICA","created_at":"2026-07-05T10:38:22.457003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15442","citing_title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN","json":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN.json","graph_json":"https://pith.science/api/pith-number/WBFRFICAB7LNYL7TX4VZ4Q4PZN/graph.json","events_json":"https://pith.science/api/pith-number/WBFRFICAB7LNYL7TX4VZ4Q4PZN/events.json","paper":"https://pith.science/paper/WBFRFICA"},"agent_actions":{"view_html":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN","download_json":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN.json","view_paper":"https://pith.science/paper/WBFRFICA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17808&json=true","fetch_graph":"https://pith.science/api/pith-number/WBFRFICAB7LNYL7TX4VZ4Q4PZN/graph.json","fetch_events":"https://pith.science/api/pith-number/WBFRFICAB7LNYL7TX4VZ4Q4PZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN/action/storage_attestation","attest_author":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN/action/author_attestation","sign_citation":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN/action/citation_signature","submit_replication":"https://pith.science/pith/WBFRFICAB7LNYL7TX4VZ4Q4PZN/action/replication_record"}},"created_at":"2026-07-05T10:38:22.457003+00:00","updated_at":"2026-07-05T10:38:22.457003+00:00"}