{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SHYA434D7PXT3YVPSS4MC2CIYP","short_pith_number":"pith:SHYA434D","schema_version":"1.0","canonical_sha256":"91f00e6f83fbef3de2af94b8c16848c3e1fb79dcefe537ef05cb7bf31aa68686","source":{"kind":"arxiv","id":"2312.11459","version":3},"attestation_state":"computed","paper":{"title":"VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Chunyu Wang, Dong Chen, Jianmin Bao, Shuyang Gu, Ting Zhang, Zhicong Tang","submitted_at":"2023-12-18T18:59:05Z","abstract_excerpt":"This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view images. The 3D volumes are then trained on a diffusion model for text-to-3D generation using a 3D U-Net. This research further addresses the challenges of inaccurate object captions and high-dimensional feature volumes. The proposed model, trained on the public Objaverse dataset, demonstrates promising outcomes in producing diverse and recognizable samples fro"},"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":"2312.11459","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-18T18:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"9014d71b128bb47f635cc9f66aa1ad30e78ce25a1a40eb456c08aba780869a2f","abstract_canon_sha256":"182dcf7155dcb3ae63fe1f7ca725aa7b3a0bec7aa852db45aad301966c9d870c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:45.544951Z","signature_b64":"697dDsf1gdV/BKXnH3YI4s2aFe4oof4ojvq/BNMEzubocXvF1PHzy+d0tAwxYX9w4ZEc1xA/xCOaqmx2G/k1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91f00e6f83fbef3de2af94b8c16848c3e1fb79dcefe537ef05cb7bf31aa68686","last_reissued_at":"2026-07-05T08:54:45.544515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:45.544515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Chunyu Wang, Dong Chen, Jianmin Bao, Shuyang Gu, Ting Zhang, Zhicong Tang","submitted_at":"2023-12-18T18:59:05Z","abstract_excerpt":"This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view images. The 3D volumes are then trained on a diffusion model for text-to-3D generation using a 3D U-Net. This research further addresses the challenges of inaccurate object captions and high-dimensional feature volumes. The proposed model, trained on the public Objaverse dataset, demonstrates promising outcomes in producing diverse and recognizable samples fro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11459","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/2312.11459/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":"2312.11459","created_at":"2026-07-05T08:54:45.544571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11459v3","created_at":"2026-07-05T08:54:45.544571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11459","created_at":"2026-07-05T08:54:45.544571+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHYA434D7PXT","created_at":"2026-07-05T08:54:45.544571+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHYA434D7PXT3YVP","created_at":"2026-07-05T08:54:45.544571+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHYA434D","created_at":"2026-07-05T08:54:45.544571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21121","citing_title":"ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01743","citing_title":"MOC-3D: Manifold-Order Consistency for Text-to-3D Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05721","citing_title":"GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidance","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21592","citing_title":"Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP","json":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP.json","graph_json":"https://pith.science/api/pith-number/SHYA434D7PXT3YVPSS4MC2CIYP/graph.json","events_json":"https://pith.science/api/pith-number/SHYA434D7PXT3YVPSS4MC2CIYP/events.json","paper":"https://pith.science/paper/SHYA434D"},"agent_actions":{"view_html":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP","download_json":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP.json","view_paper":"https://pith.science/paper/SHYA434D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11459&json=true","fetch_graph":"https://pith.science/api/pith-number/SHYA434D7PXT3YVPSS4MC2CIYP/graph.json","fetch_events":"https://pith.science/api/pith-number/SHYA434D7PXT3YVPSS4MC2CIYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP/action/storage_attestation","attest_author":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP/action/author_attestation","sign_citation":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP/action/citation_signature","submit_replication":"https://pith.science/pith/SHYA434D7PXT3YVPSS4MC2CIYP/action/replication_record"}},"created_at":"2026-07-05T08:54:45.544571+00:00","updated_at":"2026-07-05T08:54:45.544571+00:00"}