{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KIVGSAXUETSIS6SAV73KA7VBES","short_pith_number":"pith:KIVGSAXU","schema_version":"1.0","canonical_sha256":"522a6902f424e4897a40aff6a07ea124a1a3d25b68a184eb3af690402e712f73","source":{"kind":"arxiv","id":"2402.02972","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Score Distillation for Text-to-3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Doyup Lee, In\\`es Hyeonsu Kim, Junyoung Seo, Minseop Kwak, Seungryong Kim, Susung Hong, Wooseok Jang","submitted_at":"2024-02-05T12:50:30Z","abstract_excerpt":"Text-to-3D generation has achieved significant success by incorporating powerful 2D diffusion models, but insufficient 3D prior knowledge also leads to the inconsistency of 3D geometry. Recently, since large-scale multi-view datasets have been released, fine-tuning the diffusion model on the multi-view datasets becomes a mainstream to solve the 3D inconsistency problem. However, it has confronted with fundamental difficulties regarding the limited quality and diversity of 3D data, compared with 2D data. To sidestep these trade-offs, we explore a retrieval-augmented approach tailored for score "},"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":"2402.02972","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-05T12:50:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"13088ee78c5223be072b1675588a201493ece1bd7c7e8d7fae28efd74be758dc","abstract_canon_sha256":"82c1600278ecc28545da03a43cb1dd4c74602f059d83319365f10e6eaae5cd5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:21.719694Z","signature_b64":"qziVFSsVLXFCqDgvZ2u5NDoIHCHPPPck1V+1VdyR86rrGm5H5ME/VAbowLoIZx9tKdlm6Scc0aFCoDMhyRk+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"522a6902f424e4897a40aff6a07ea124a1a3d25b68a184eb3af690402e712f73","last_reissued_at":"2026-07-05T08:14:21.719074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:21.719074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Score Distillation for Text-to-3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Doyup Lee, In\\`es Hyeonsu Kim, Junyoung Seo, Minseop Kwak, Seungryong Kim, Susung Hong, Wooseok Jang","submitted_at":"2024-02-05T12:50:30Z","abstract_excerpt":"Text-to-3D generation has achieved significant success by incorporating powerful 2D diffusion models, but insufficient 3D prior knowledge also leads to the inconsistency of 3D geometry. Recently, since large-scale multi-view datasets have been released, fine-tuning the diffusion model on the multi-view datasets becomes a mainstream to solve the 3D inconsistency problem. However, it has confronted with fundamental difficulties regarding the limited quality and diversity of 3D data, compared with 2D data. To sidestep these trade-offs, we explore a retrieval-augmented approach tailored for score "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02972","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/2402.02972/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":"2402.02972","created_at":"2026-07-05T08:14:21.719135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02972v2","created_at":"2026-07-05T08:14:21.719135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02972","created_at":"2026-07-05T08:14:21.719135+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIVGSAXUETSI","created_at":"2026-07-05T08:14:21.719135+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIVGSAXUETSIS6SA","created_at":"2026-07-05T08:14:21.719135+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIVGSAXU","created_at":"2026-07-05T08:14:21.719135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.13340","citing_title":"Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES","json":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES.json","graph_json":"https://pith.science/api/pith-number/KIVGSAXUETSIS6SAV73KA7VBES/graph.json","events_json":"https://pith.science/api/pith-number/KIVGSAXUETSIS6SAV73KA7VBES/events.json","paper":"https://pith.science/paper/KIVGSAXU"},"agent_actions":{"view_html":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES","download_json":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES.json","view_paper":"https://pith.science/paper/KIVGSAXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02972&json=true","fetch_graph":"https://pith.science/api/pith-number/KIVGSAXUETSIS6SAV73KA7VBES/graph.json","fetch_events":"https://pith.science/api/pith-number/KIVGSAXUETSIS6SAV73KA7VBES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES/action/storage_attestation","attest_author":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES/action/author_attestation","sign_citation":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES/action/citation_signature","submit_replication":"https://pith.science/pith/KIVGSAXUETSIS6SAV73KA7VBES/action/replication_record"}},"created_at":"2026-07-05T08:14:21.719135+00:00","updated_at":"2026-07-05T08:14:21.719135+00:00"}