{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YFBNTXE5MMUKVM2AKOG4NSUYS3","short_pith_number":"pith:YFBNTXE5","schema_version":"1.0","canonical_sha256":"c142d9dc9d6328aab340538dc6ca9896d92e15f6a01dd6752dc41ce69456ad9a","source":{"kind":"arxiv","id":"2507.00006","version":1},"attestation_state":"computed","paper":{"title":"MVGBench: Comprehensive Benchmark for Multi-view Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.GR","authors_text":"Chuhang Zou, Gerard Pons-Moll, Jan Eric Lenssen, Meher Gitika Karumuri, Xianghui Xie","submitted_at":"2025-06-11T08:02:40Z","abstract_excerpt":"We propose MVGBench, a comprehensive benchmark for multi-view image generation models (MVGs) that evaluates 3D consistency in geometry and texture, image quality, and semantics (using vision language models). Recently, MVGs have been the main driving force in 3D object creation. However, existing metrics compare generated images against ground truth target views, which is not suitable for generative tasks where multiple solutions exist while differing from ground truth. Furthermore, different MVGs are trained on different view angles, synthetic data and specific lightings -- robustness to thes"},"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":"2507.00006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2025-06-11T08:02:40Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"2b070ffb210ad8238099fc72afcf21e56448c7a181c03344b423fca128318235","abstract_canon_sha256":"0f4be2da6cb3dcbe2d090df22b55f5fe72657b06cf066f2854ffcf567dfdfb95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:34.944709Z","signature_b64":"VhU1STktKwS+5B+N9dJGmUYzBZ9RbvRtppVHkIHZtOMouPErS4WTPHlTqC2gcaPGfgsFFCm+F6mcdoxuPI0KBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c142d9dc9d6328aab340538dc6ca9896d92e15f6a01dd6752dc41ce69456ad9a","last_reissued_at":"2026-07-05T11:29:34.944156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:34.944156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVGBench: Comprehensive Benchmark for Multi-view Generation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.GR","authors_text":"Chuhang Zou, Gerard Pons-Moll, Jan Eric Lenssen, Meher Gitika Karumuri, Xianghui Xie","submitted_at":"2025-06-11T08:02:40Z","abstract_excerpt":"We propose MVGBench, a comprehensive benchmark for multi-view image generation models (MVGs) that evaluates 3D consistency in geometry and texture, image quality, and semantics (using vision language models). Recently, MVGs have been the main driving force in 3D object creation. However, existing metrics compare generated images against ground truth target views, which is not suitable for generative tasks where multiple solutions exist while differing from ground truth. Furthermore, different MVGs are trained on different view angles, synthetic data and specific lightings -- robustness to thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00006","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/2507.00006/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":"2507.00006","created_at":"2026-07-05T11:29:34.944217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00006v1","created_at":"2026-07-05T11:29:34.944217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00006","created_at":"2026-07-05T11:29:34.944217+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFBNTXE5MMUK","created_at":"2026-07-05T11:29:34.944217+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFBNTXE5MMUKVM2A","created_at":"2026-07-05T11:29:34.944217+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFBNTXE5","created_at":"2026-07-05T11:29:34.944217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18451","citing_title":"A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25220","citing_title":"Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3","json":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3.json","graph_json":"https://pith.science/api/pith-number/YFBNTXE5MMUKVM2AKOG4NSUYS3/graph.json","events_json":"https://pith.science/api/pith-number/YFBNTXE5MMUKVM2AKOG4NSUYS3/events.json","paper":"https://pith.science/paper/YFBNTXE5"},"agent_actions":{"view_html":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3","download_json":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3.json","view_paper":"https://pith.science/paper/YFBNTXE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00006&json=true","fetch_graph":"https://pith.science/api/pith-number/YFBNTXE5MMUKVM2AKOG4NSUYS3/graph.json","fetch_events":"https://pith.science/api/pith-number/YFBNTXE5MMUKVM2AKOG4NSUYS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3/action/storage_attestation","attest_author":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3/action/author_attestation","sign_citation":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3/action/citation_signature","submit_replication":"https://pith.science/pith/YFBNTXE5MMUKVM2AKOG4NSUYS3/action/replication_record"}},"created_at":"2026-07-05T11:29:34.944217+00:00","updated_at":"2026-07-05T11:29:34.944217+00:00"}