{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NTPAXTRDWPLCFSH7HEXFAP6OR7","short_pith_number":"pith:NTPAXTRD","schema_version":"1.0","canonical_sha256":"6cde0bce23b3d622c8ff392e503fce8fe02acb85b619e09b3f3890c24b48e338","source":{"kind":"arxiv","id":"2412.06614","version":1},"attestation_state":"computed","paper":{"title":"MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoqian Wang, Haoran Xu, Jun Meng, Weitao Wang, Yuxiao Yang, Zhifang Liu","submitted_at":"2024-12-09T16:05:31Z","abstract_excerpt":"Recent years have witnessed remarkable progress in 3D content generation. However, corresponding evaluation methods struggle to keep pace. Automatic approaches have proven challenging to align with human preferences, and the mixed comparison of text- and image-driven methods often leads to unfair evaluations. In this paper, we present a comprehensive framework to better align and evaluate multi-view diffusion models with human preferences. To begin with, we first collect and filter a standardized image prompt set from DALL$\\cdot$E and Objaverse, which we then use to generate multi-view assets "},"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":"2412.06614","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T16:05:31Z","cross_cats_sorted":[],"title_canon_sha256":"8e3658a0258140b00b97260be14fd44d9ffcc2b5e62abd36c93a8bb95dc94c7a","abstract_canon_sha256":"6259f7515706b0dc2830d3d9b439eff3d3c74a9cc44acdc63185d89a4cec9818"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:35.066353Z","signature_b64":"2GALPbXNsQj2/1bGdqAxwUJY5eszbZ8k5M4dHnjQLfDOw1s/WEvoKrEHWus4+8fGEXknC9/CX79DR0pRMnB0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cde0bce23b3d622c8ff392e503fce8fe02acb85b619e09b3f3890c24b48e338","last_reissued_at":"2026-07-05T09:46:35.065878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:35.065878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoqian Wang, Haoran Xu, Jun Meng, Weitao Wang, Yuxiao Yang, Zhifang Liu","submitted_at":"2024-12-09T16:05:31Z","abstract_excerpt":"Recent years have witnessed remarkable progress in 3D content generation. However, corresponding evaluation methods struggle to keep pace. Automatic approaches have proven challenging to align with human preferences, and the mixed comparison of text- and image-driven methods often leads to unfair evaluations. In this paper, we present a comprehensive framework to better align and evaluate multi-view diffusion models with human preferences. To begin with, we first collect and filter a standardized image prompt set from DALL$\\cdot$E and Objaverse, which we then use to generate multi-view assets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06614","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/2412.06614/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":"2412.06614","created_at":"2026-07-05T09:46:35.065942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06614v1","created_at":"2026-07-05T09:46:35.065942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06614","created_at":"2026-07-05T09:46:35.065942+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTPAXTRDWPLC","created_at":"2026-07-05T09:46:35.065942+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTPAXTRDWPLCFSH7","created_at":"2026-07-05T09:46:35.065942+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTPAXTRD","created_at":"2026-07-05T09:46:35.065942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07700","citing_title":"Make Your MoVe: Make Your 3D Contents by Adapting Multi-View Diffusion Models to External Editing","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7","json":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7.json","graph_json":"https://pith.science/api/pith-number/NTPAXTRDWPLCFSH7HEXFAP6OR7/graph.json","events_json":"https://pith.science/api/pith-number/NTPAXTRDWPLCFSH7HEXFAP6OR7/events.json","paper":"https://pith.science/paper/NTPAXTRD"},"agent_actions":{"view_html":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7","download_json":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7.json","view_paper":"https://pith.science/paper/NTPAXTRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06614&json=true","fetch_graph":"https://pith.science/api/pith-number/NTPAXTRDWPLCFSH7HEXFAP6OR7/graph.json","fetch_events":"https://pith.science/api/pith-number/NTPAXTRDWPLCFSH7HEXFAP6OR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7/action/storage_attestation","attest_author":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7/action/author_attestation","sign_citation":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7/action/citation_signature","submit_replication":"https://pith.science/pith/NTPAXTRDWPLCFSH7HEXFAP6OR7/action/replication_record"}},"created_at":"2026-07-05T09:46:35.065942+00:00","updated_at":"2026-07-05T09:46:35.065942+00:00"}