{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W4XHI77H2UEDMDY5ZEUBBL5FRG","short_pith_number":"pith:W4XHI77H","schema_version":"1.0","canonical_sha256":"b72e747fe7d508360f1dc92810afa589a82def96de2b2a32bf0f95013759144b","source":{"kind":"arxiv","id":"2602.07272","version":2},"attestation_state":"computed","paper":{"title":"VideoNeuMat: Neural Material Extraction from Generative Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bowen Xue, Fabrice Rousselle, Milos Hasan, Saeed Hadadan, Zahra Montazeri, Zheng Zeng","submitted_at":"2026-02-06T23:49:10Z","abstract_excerpt":"Creating photorealistic materials for 3D rendering requires exceptional artistic skill. Generative models for materials could help, but are currently limited by the lack of high-quality training data. While recent video generative models effortlessly produce realistic material appearances, this knowledge remains entangled with geometry and lighting. We present VideoNeuMat, a two-stage pipeline that extracts reusable neural material assets from video diffusion models. First, we finetune a large video model (Wan 2.1 14B) to generate material sample videos under controlled camera and lighting tra"},"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":"2602.07272","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-06T23:49:10Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"d911d60887f33b03f0a4a239709ca6841fa849977ecf00e12591a14c9403a988","abstract_canon_sha256":"d28540a72ff219f4e4974be77e573dd882e4544daf867db07c1aa57065c477a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:09.510725Z","signature_b64":"Wqi6L4p1warmzKjQGz546pkTRANHA2poox1Vtah7B5y01/kHF/ZWy2Vmnq7VeyH+GI5WuVs9+K9hVwgNhOl8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72e747fe7d508360f1dc92810afa589a82def96de2b2a32bf0f95013759144b","last_reissued_at":"2026-05-20T00:02:09.509879Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:09.509879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoNeuMat: Neural Material Extraction from Generative Video Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Bowen Xue, Fabrice Rousselle, Milos Hasan, Saeed Hadadan, Zahra Montazeri, Zheng Zeng","submitted_at":"2026-02-06T23:49:10Z","abstract_excerpt":"Creating photorealistic materials for 3D rendering requires exceptional artistic skill. Generative models for materials could help, but are currently limited by the lack of high-quality training data. While recent video generative models effortlessly produce realistic material appearances, this knowledge remains entangled with geometry and lighting. We present VideoNeuMat, a two-stage pipeline that extracts reusable neural material assets from video diffusion models. First, we finetune a large video model (Wan 2.1 14B) to generate material sample videos under controlled camera and lighting tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07272","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/2602.07272/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":"2602.07272","created_at":"2026-05-20T00:02:09.510013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.07272v2","created_at":"2026-05-20T00:02:09.510013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07272","created_at":"2026-05-20T00:02:09.510013+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4XHI77H2UED","created_at":"2026-05-20T00:02:09.510013+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4XHI77H2UEDMDY5","created_at":"2026-05-20T00:02:09.510013+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4XHI77H","created_at":"2026-05-20T00:02:09.510013+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/W4XHI77H2UEDMDY5ZEUBBL5FRG","json":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG.json","graph_json":"https://pith.science/api/pith-number/W4XHI77H2UEDMDY5ZEUBBL5FRG/graph.json","events_json":"https://pith.science/api/pith-number/W4XHI77H2UEDMDY5ZEUBBL5FRG/events.json","paper":"https://pith.science/paper/W4XHI77H"},"agent_actions":{"view_html":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG","download_json":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG.json","view_paper":"https://pith.science/paper/W4XHI77H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.07272&json=true","fetch_graph":"https://pith.science/api/pith-number/W4XHI77H2UEDMDY5ZEUBBL5FRG/graph.json","fetch_events":"https://pith.science/api/pith-number/W4XHI77H2UEDMDY5ZEUBBL5FRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG/action/storage_attestation","attest_author":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG/action/author_attestation","sign_citation":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG/action/citation_signature","submit_replication":"https://pith.science/pith/W4XHI77H2UEDMDY5ZEUBBL5FRG/action/replication_record"}},"created_at":"2026-05-20T00:02:09.510013+00:00","updated_at":"2026-05-20T00:02:09.510013+00:00"}