{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TYB2U2RTWXJ3C2CF23CG5ZDC4G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3a5eebef89cf9594e0ebf46e5be4533065c9a30bdcf5080d6870e80b3c332872","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:58Z","title_canon_sha256":"90a7c2a598df7122270040ffd2aea4ce9db4f46a05aa95f20ffcf012423557db"},"schema_version":"1.0","source":{"id":"2411.14808","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14808","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14808v2","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14808","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_12","alias_value":"TYB2U2RTWXJ3","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_16","alias_value":"TYB2U2RTWXJ3C2CF","created_at":"2026-07-05T10:22:10Z"},{"alias_kind":"pith_short_8","alias_value":"TYB2U2RT","created_at":"2026-07-05T10:22:10Z"}],"graph_snapshots":[{"event_id":"sha256:670d7b22890cf5d8bfb042bf2d8ddd32b7fb25e934925fcc3d0ec8c9a6b6383a","target":"graph","created_at":"2026-07-05T10:22:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.14808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, autoregressive models have demonstrated remarkable performance in class-conditional image generation. However, the application of next-token prediction to high-resolution text-to-image generation remains largely unexplored. In this paper, we introduce \\textbf{D-JEPA$\\cdot$T2I}, an autoregressive model based on continuous tokens that incorporates innovations in both architecture and training strategy to generate high-quality, photorealistic images at arbitrary resolutions, up to 4K. Architecturally, we adopt the denoising joint embedding predictive architecture (D-JEPA) while leveragi","authors_text":"Dengsheng Chen, Enhua Wu, Jie Hu, Tiezhu Yue, Xiaoming Wei","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:58Z","title":"High-Resolution Image Synthesis via Next-Token Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14808","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f881098576bcb53fe6d3f6e611fd227ed76bc9f52e1783a8d846ad15120f32c9","target":"record","created_at":"2026-07-05T10:22:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3a5eebef89cf9594e0ebf46e5be4533065c9a30bdcf5080d6870e80b3c332872","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:58Z","title_canon_sha256":"90a7c2a598df7122270040ffd2aea4ce9db4f46a05aa95f20ffcf012423557db"},"schema_version":"1.0","source":{"id":"2411.14808","kind":"arxiv","version":2}},"canonical_sha256":"9e03aa6a33b5d3b16845d6c46ee462e1978f7b610eb0dd1808f0e48f6df1d286","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e03aa6a33b5d3b16845d6c46ee462e1978f7b610eb0dd1808f0e48f6df1d286","first_computed_at":"2026-07-05T10:22:10.215075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:10.215075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UaBW76ZDhFEfeEnwFgMoAyYF+UbLI3/T7Lk4fZ82H7IzG14DEdz3ZYXTeMuAORKVIFt7Mv6be0MzUBdWrj71DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:10.215624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14808","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f881098576bcb53fe6d3f6e611fd227ed76bc9f52e1783a8d846ad15120f32c9","sha256:670d7b22890cf5d8bfb042bf2d8ddd32b7fb25e934925fcc3d0ec8c9a6b6383a"],"state_sha256":"d0e3ab15030a693474843ac8a40c1de0d15783e0e4a756cc5ee373847d114c9a"}