{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GS2IW2E6HJ6I6KVPBB47TAA7C3","short_pith_number":"pith:GS2IW2E6","schema_version":"1.0","canonical_sha256":"34b48b689e3a7c8f2aaf0879f9801f16f3d279809d1c74178259554634135675","source":{"kind":"arxiv","id":"2410.08261","version":4},"attestation_state":"computed","paper":{"title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enxin Song, Jinbin Bai, Lei Zhu, Shuicheng Yan, Tian Ye, Wei Chow, Xiangtai Li, Zhen Dong","submitted_at":"2024-10-10T17:59:17Z","abstract_excerpt":"We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations, advanced positional encoding strategies, and optimized sampling conditions, Meissonic substantially improves MIM's performance and efficiency. Additionally, we leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model no"},"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":"2410.08261","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:17Z","cross_cats_sorted":[],"title_canon_sha256":"53ed297829bec6a2e8c987726e87b9bff9b92a508ae5d63611a9a5782a925fb2","abstract_canon_sha256":"baecf83f6d526a21f16245eee26792ea1238e5b823a6b300f27d4595c614b5ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:24.464576Z","signature_b64":"VEUHYyl7GjPuNDQIAne3iBLHLft/gizKggrb4JRno7bvbvcPis9fBXsP7W4fkqPirVCJfjGDZxGAZfmH9qGABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34b48b689e3a7c8f2aaf0879f9801f16f3d279809d1c74178259554634135675","last_reissued_at":"2026-07-05T10:30:24.463546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:24.463546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enxin Song, Jinbin Bai, Lei Zhu, Shuicheng Yan, Tian Ye, Wei Chow, Xiangtai Li, Zhen Dong","submitted_at":"2024-10-10T17:59:17Z","abstract_excerpt":"We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations, advanced positional encoding strategies, and optimized sampling conditions, Meissonic substantially improves MIM's performance and efficiency. Additionally, we leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08261","kind":"arxiv","version":4},"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/2410.08261/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":"2410.08261","created_at":"2026-07-05T10:30:24.463690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08261v4","created_at":"2026-07-05T10:30:24.463690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08261","created_at":"2026-07-05T10:30:24.463690+00:00"},{"alias_kind":"pith_short_12","alias_value":"GS2IW2E6HJ6I","created_at":"2026-07-05T10:30:24.463690+00:00"},{"alias_kind":"pith_short_16","alias_value":"GS2IW2E6HJ6I6KVP","created_at":"2026-07-05T10:30:24.463690+00:00"},{"alias_kind":"pith_short_8","alias_value":"GS2IW2E6","created_at":"2026-07-05T10:30:24.463690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29814","citing_title":"Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10859","citing_title":"Masked Generative Transformer Is What You Need for Image Editing","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04653","citing_title":"Threshold-Guided Optimization for Visual Generative Models","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3","json":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3.json","graph_json":"https://pith.science/api/pith-number/GS2IW2E6HJ6I6KVPBB47TAA7C3/graph.json","events_json":"https://pith.science/api/pith-number/GS2IW2E6HJ6I6KVPBB47TAA7C3/events.json","paper":"https://pith.science/paper/GS2IW2E6"},"agent_actions":{"view_html":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3","download_json":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3.json","view_paper":"https://pith.science/paper/GS2IW2E6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08261&json=true","fetch_graph":"https://pith.science/api/pith-number/GS2IW2E6HJ6I6KVPBB47TAA7C3/graph.json","fetch_events":"https://pith.science/api/pith-number/GS2IW2E6HJ6I6KVPBB47TAA7C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3/action/storage_attestation","attest_author":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3/action/author_attestation","sign_citation":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3/action/citation_signature","submit_replication":"https://pith.science/pith/GS2IW2E6HJ6I6KVPBB47TAA7C3/action/replication_record"}},"created_at":"2026-07-05T10:30:24.463690+00:00","updated_at":"2026-07-05T10:30:24.463690+00:00"}