{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OG3EDDZWKJEREA64O4HL7ERQM2","short_pith_number":"pith:OG3EDDZW","schema_version":"1.0","canonical_sha256":"71b6418f3652491203dc770ebf92306691a8ecca4d23d409164c08367446cc83","source":{"kind":"arxiv","id":"2508.16577","version":1},"attestation_state":"computed","paper":{"title":"MV-RAG: Retrieval Augmented Multiview Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Omer Benishu, Sagie Benaim, Yosef Dayani","submitted_at":"2025-08-22T17:59:40Z","abstract_excerpt":"Text-to-3D generation approaches have advanced significantly by leveraging pretrained 2D diffusion priors, producing high-quality and 3D-consistent outputs. However, they often fail to produce out-of-domain (OOD) or rare concepts, yielding inconsistent or inaccurate results. To this end, we propose MV-RAG, a novel text-to-3D pipeline that first retrieves relevant 2D images from a large in-the-wild 2D database and then conditions a multiview diffusion model on these images to synthesize consistent and accurate multiview outputs. Training such a retrieval-conditioned model is achieved via a nove"},"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":"2508.16577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-22T17:59:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb76ae1b9981313404104f8cef19e6c35ed5b54c543d88794a5c919a0c5b5dc9","abstract_canon_sha256":"edf1cec694a4f1acd15d5b864db97b570320d2384fc19ff1229f7a0c014a7cbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:51.212398Z","signature_b64":"gygBhXe4r1AYN31KfCeN+POWofdW7l1X3qJ8z0xMrYQcdEpYD/D02ZbKMlCmynm6adQUVzMH281eJYhP6rxhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71b6418f3652491203dc770ebf92306691a8ecca4d23d409164c08367446cc83","last_reissued_at":"2026-07-05T11:57:51.211730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:51.211730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MV-RAG: Retrieval Augmented Multiview Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Omer Benishu, Sagie Benaim, Yosef Dayani","submitted_at":"2025-08-22T17:59:40Z","abstract_excerpt":"Text-to-3D generation approaches have advanced significantly by leveraging pretrained 2D diffusion priors, producing high-quality and 3D-consistent outputs. However, they often fail to produce out-of-domain (OOD) or rare concepts, yielding inconsistent or inaccurate results. To this end, we propose MV-RAG, a novel text-to-3D pipeline that first retrieves relevant 2D images from a large in-the-wild 2D database and then conditions a multiview diffusion model on these images to synthesize consistent and accurate multiview outputs. Training such a retrieval-conditioned model is achieved via a nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16577","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/2508.16577/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":"2508.16577","created_at":"2026-07-05T11:57:51.211824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16577v1","created_at":"2026-07-05T11:57:51.211824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16577","created_at":"2026-07-05T11:57:51.211824+00:00"},{"alias_kind":"pith_short_12","alias_value":"OG3EDDZWKJER","created_at":"2026-07-05T11:57:51.211824+00:00"},{"alias_kind":"pith_short_16","alias_value":"OG3EDDZWKJEREA64","created_at":"2026-07-05T11:57:51.211824+00:00"},{"alias_kind":"pith_short_8","alias_value":"OG3EDDZW","created_at":"2026-07-05T11:57:51.211824+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2","json":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2.json","graph_json":"https://pith.science/api/pith-number/OG3EDDZWKJEREA64O4HL7ERQM2/graph.json","events_json":"https://pith.science/api/pith-number/OG3EDDZWKJEREA64O4HL7ERQM2/events.json","paper":"https://pith.science/paper/OG3EDDZW"},"agent_actions":{"view_html":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2","download_json":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2.json","view_paper":"https://pith.science/paper/OG3EDDZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16577&json=true","fetch_graph":"https://pith.science/api/pith-number/OG3EDDZWKJEREA64O4HL7ERQM2/graph.json","fetch_events":"https://pith.science/api/pith-number/OG3EDDZWKJEREA64O4HL7ERQM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2/action/storage_attestation","attest_author":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2/action/author_attestation","sign_citation":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2/action/citation_signature","submit_replication":"https://pith.science/pith/OG3EDDZWKJEREA64O4HL7ERQM2/action/replication_record"}},"created_at":"2026-07-05T11:57:51.211824+00:00","updated_at":"2026-07-05T11:57:51.211824+00:00"}