{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GH4HQDB5PPTTOAB3Y5QEGI3VPV","short_pith_number":"pith:GH4HQDB5","schema_version":"1.0","canonical_sha256":"31f8780c3d7be737003bc7604323757d6ee3b9fc3e66fe9576128b50167ec6c4","source":{"kind":"arxiv","id":"2509.06579","version":1},"attestation_state":"computed","paper":{"title":"CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Watson, Federico Tombari, Michael Niemeyer, Xin Kong, Yannick Str\\\"umpler","submitted_at":"2025-09-08T11:49:51Z","abstract_excerpt":"Multi-view diffusion models have shown promise in 3D novel view synthesis, but most existing methods adopt a non-autoregressive formulation. This limits their applicability in world modeling, as they only support a fixed number of views and suffer from slow inference due to denoising all frames simultaneously. To address these limitations, we propose CausNVS, a multi-view diffusion model in an autoregressive setting, which supports arbitrary input-output view configurations and generates views sequentially. We train CausNVS with causal masking and per-frame noise, using pairwise-relative camer"},"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":"2509.06579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T11:49:51Z","cross_cats_sorted":[],"title_canon_sha256":"32d35a851d2262c61613a8b99bbce197ed83d7026a4dcbe7c5b99553d7bae552","abstract_canon_sha256":"84206628af59b6fc994af500e55da36725178023ac9b9062bc6ca90274a78e1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:38.592809Z","signature_b64":"Lrxb5I5q1mpHtkheWAPYBwV9rRX6Zib83t+iz1vkTPzdOmNvKhnkHIiAHYYJsN3s+rH/jS73raE02sV/ZqcfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31f8780c3d7be737003bc7604323757d6ee3b9fc3e66fe9576128b50167ec6c4","last_reissued_at":"2026-07-05T12:06:38.592421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:38.592421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Watson, Federico Tombari, Michael Niemeyer, Xin Kong, Yannick Str\\\"umpler","submitted_at":"2025-09-08T11:49:51Z","abstract_excerpt":"Multi-view diffusion models have shown promise in 3D novel view synthesis, but most existing methods adopt a non-autoregressive formulation. This limits their applicability in world modeling, as they only support a fixed number of views and suffer from slow inference due to denoising all frames simultaneously. To address these limitations, we propose CausNVS, a multi-view diffusion model in an autoregressive setting, which supports arbitrary input-output view configurations and generates views sequentially. We train CausNVS with causal masking and per-frame noise, using pairwise-relative camer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06579","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/2509.06579/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":"2509.06579","created_at":"2026-07-05T12:06:38.592477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06579v1","created_at":"2026-07-05T12:06:38.592477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06579","created_at":"2026-07-05T12:06:38.592477+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH4HQDB5PPTT","created_at":"2026-07-05T12:06:38.592477+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH4HQDB5PPTTOAB3","created_at":"2026-07-05T12:06:38.592477+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH4HQDB5","created_at":"2026-07-05T12:06:38.592477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10839","citing_title":"HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV","json":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV.json","graph_json":"https://pith.science/api/pith-number/GH4HQDB5PPTTOAB3Y5QEGI3VPV/graph.json","events_json":"https://pith.science/api/pith-number/GH4HQDB5PPTTOAB3Y5QEGI3VPV/events.json","paper":"https://pith.science/paper/GH4HQDB5"},"agent_actions":{"view_html":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV","download_json":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV.json","view_paper":"https://pith.science/paper/GH4HQDB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06579&json=true","fetch_graph":"https://pith.science/api/pith-number/GH4HQDB5PPTTOAB3Y5QEGI3VPV/graph.json","fetch_events":"https://pith.science/api/pith-number/GH4HQDB5PPTTOAB3Y5QEGI3VPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV/action/storage_attestation","attest_author":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV/action/author_attestation","sign_citation":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV/action/citation_signature","submit_replication":"https://pith.science/pith/GH4HQDB5PPTTOAB3Y5QEGI3VPV/action/replication_record"}},"created_at":"2026-07-05T12:06:38.592477+00:00","updated_at":"2026-07-05T12:06:38.592477+00:00"}