{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J6OJDROQSK2D3PTGIELFITL3CY","short_pith_number":"pith:J6OJDROQ","schema_version":"1.0","canonical_sha256":"4f9c91c5d092b43dbe664116544d7b1610cf6cf30194a5f3fc63b2e46e7ea8f1","source":{"kind":"arxiv","id":"2412.06787","version":2},"attestation_state":"computed","paper":{"title":"[MASK] is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Vincent Tao Hu","submitted_at":"2024-12-09T18:59:56Z","abstract_excerpt":"In generative models, two paradigms have gained attraction in various applications: next-set prediction-based Masked Generative Models and next-noise prediction-based Non-Autoregressive Models, e.g., Diffusion Models. In this work, we propose using discrete-state models to connect them and explore their scalability in the vision domain. First, we conduct a step-by-step analysis in a unified design space across two types of models including timestep-independence, noise schedule, temperature, guidance strength, etc in a scalable manner. Second, we re-cast typical discriminative tasks, e.g., imag"},"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":"2412.06787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T18:59:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d1b2eea06ac0b996f45388c0adb27739c8dba2020a6fb380a89eb018aa2fb65","abstract_canon_sha256":"02185ec11d8e9516192542f46099a11c31bfc588dae8ef51cc8e7c710173e7c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:56.924253Z","signature_b64":"vo+y7QpSfgbpiHZNKPnmcuRbb6k/nfd5jzOh9gn+BgNjfmWQfXfuWaPCOqpXer8Sj1F01YuaFag+ksV/WpwlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f9c91c5d092b43dbe664116544d7b1610cf6cf30194a5f3fc63b2e46e7ea8f1","last_reissued_at":"2026-07-05T09:46:56.923699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:56.923699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"[MASK] is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Vincent Tao Hu","submitted_at":"2024-12-09T18:59:56Z","abstract_excerpt":"In generative models, two paradigms have gained attraction in various applications: next-set prediction-based Masked Generative Models and next-noise prediction-based Non-Autoregressive Models, e.g., Diffusion Models. In this work, we propose using discrete-state models to connect them and explore their scalability in the vision domain. First, we conduct a step-by-step analysis in a unified design space across two types of models including timestep-independence, noise schedule, temperature, guidance strength, etc in a scalable manner. Second, we re-cast typical discriminative tasks, e.g., imag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06787","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/2412.06787/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":"2412.06787","created_at":"2026-07-05T09:46:56.923757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06787v2","created_at":"2026-07-05T09:46:56.923757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06787","created_at":"2026-07-05T09:46:56.923757+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6OJDROQSK2D","created_at":"2026-07-05T09:46:56.923757+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6OJDROQSK2D3PTG","created_at":"2026-07-05T09:46:56.923757+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6OJDROQ","created_at":"2026-07-05T09:46:56.923757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07193","citing_title":"Coupling Models for One-Step Discrete Generation","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY","json":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY.json","graph_json":"https://pith.science/api/pith-number/J6OJDROQSK2D3PTGIELFITL3CY/graph.json","events_json":"https://pith.science/api/pith-number/J6OJDROQSK2D3PTGIELFITL3CY/events.json","paper":"https://pith.science/paper/J6OJDROQ"},"agent_actions":{"view_html":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY","download_json":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY.json","view_paper":"https://pith.science/paper/J6OJDROQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06787&json=true","fetch_graph":"https://pith.science/api/pith-number/J6OJDROQSK2D3PTGIELFITL3CY/graph.json","fetch_events":"https://pith.science/api/pith-number/J6OJDROQSK2D3PTGIELFITL3CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY/action/storage_attestation","attest_author":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY/action/author_attestation","sign_citation":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY/action/citation_signature","submit_replication":"https://pith.science/pith/J6OJDROQSK2D3PTGIELFITL3CY/action/replication_record"}},"created_at":"2026-07-05T09:46:56.923757+00:00","updated_at":"2026-07-05T09:46:56.923757+00:00"}