{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ARMWIOIFN4SSM2KXZR2H4UW2JI","short_pith_number":"pith:ARMWIOIF","schema_version":"1.0","canonical_sha256":"04596439056f25266957cc747e52da4a31e608336280afadc58e1b52d899e9cf","source":{"kind":"arxiv","id":"2512.14099","version":3},"attestation_state":"computed","paper":{"title":"ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyuan Zhang, Jiacheng Sun, Ping Luo, Ruishu Zhu, Xuelong Li, Zhihao Huang","submitted_at":"2025-12-16T05:15:07Z","abstract_excerpt":"Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce ViewMask-1-to-3, formulating multi-view generation as a discrete sequence modeling problem where each viewpoint is represented as visual tokens from MAGVIT-v2. Through discrete diffusion via masked token prediction, our approach enables progressive multi-view generation via iterative token unmasking, unifying language and vision in a shared token space. Importantly, simple random masking combined with self-attention n"},"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":"2512.14099","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-16T05:15:07Z","cross_cats_sorted":[],"title_canon_sha256":"00b8bb33c017b83447de5fd57a6ffbd74423f71d962a90d05d4840355cffad58","abstract_canon_sha256":"265681043531d2d194f7339cbce769a7d35241257f13fd661020bc550eed052e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:37.978882Z","signature_b64":"bBMGJcT2RQazebvhctezdC4frpyXOF9YcYBmDo1lPPnWdmOfeYnQ4DaeDx7M9P9BMo652iBPLVfL1mMk/MqsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04596439056f25266957cc747e52da4a31e608336280afadc58e1b52d899e9cf","last_reissued_at":"2026-06-04T01:08:37.977928Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:37.977928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyuan Zhang, Jiacheng Sun, Ping Luo, Ruishu Zhu, Xuelong Li, Zhihao Huang","submitted_at":"2025-12-16T05:15:07Z","abstract_excerpt":"Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce ViewMask-1-to-3, formulating multi-view generation as a discrete sequence modeling problem where each viewpoint is represented as visual tokens from MAGVIT-v2. Through discrete diffusion via masked token prediction, our approach enables progressive multi-view generation via iterative token unmasking, unifying language and vision in a shared token space. Importantly, simple random masking combined with self-attention n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14099","kind":"arxiv","version":3},"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/2512.14099/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":"2512.14099","created_at":"2026-06-04T01:08:37.978046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.14099v3","created_at":"2026-06-04T01:08:37.978046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14099","created_at":"2026-06-04T01:08:37.978046+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARMWIOIFN4SS","created_at":"2026-06-04T01:08:37.978046+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARMWIOIFN4SSM2KX","created_at":"2026-06-04T01:08:37.978046+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARMWIOIF","created_at":"2026-06-04T01:08:37.978046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22060","citing_title":"Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI","json":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI.json","graph_json":"https://pith.science/api/pith-number/ARMWIOIFN4SSM2KXZR2H4UW2JI/graph.json","events_json":"https://pith.science/api/pith-number/ARMWIOIFN4SSM2KXZR2H4UW2JI/events.json","paper":"https://pith.science/paper/ARMWIOIF"},"agent_actions":{"view_html":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI","download_json":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI.json","view_paper":"https://pith.science/paper/ARMWIOIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.14099&json=true","fetch_graph":"https://pith.science/api/pith-number/ARMWIOIFN4SSM2KXZR2H4UW2JI/graph.json","fetch_events":"https://pith.science/api/pith-number/ARMWIOIFN4SSM2KXZR2H4UW2JI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI/action/storage_attestation","attest_author":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI/action/author_attestation","sign_citation":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI/action/citation_signature","submit_replication":"https://pith.science/pith/ARMWIOIFN4SSM2KXZR2H4UW2JI/action/replication_record"}},"created_at":"2026-06-04T01:08:37.978046+00:00","updated_at":"2026-06-04T01:08:37.978046+00:00"}