{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TYB2U2RTWXJ3C2CF23CG5ZDC4G","short_pith_number":"pith:TYB2U2RT","canonical_record":{"source":{"id":"2411.14808","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"90a7c2a598df7122270040ffd2aea4ce9db4f46a05aa95f20ffcf012423557db","abstract_canon_sha256":"3a5eebef89cf9594e0ebf46e5be4533065c9a30bdcf5080d6870e80b3c332872"},"schema_version":"1.0"},"canonical_sha256":"9e03aa6a33b5d3b16845d6c46ee462e1978f7b610eb0dd1808f0e48f6df1d286","source":{"kind":"arxiv","id":"2411.14808","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TYB2U2RTWXJ3C2CF23CG5ZDC4G","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14808","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-22T09:08:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"90a7c2a598df7122270040ffd2aea4ce9db4f46a05aa95f20ffcf012423557db","abstract_canon_sha256":"3a5eebef89cf9594e0ebf46e5be4533065c9a30bdcf5080d6870e80b3c332872"},"schema_version":"1.0"},"canonical_sha256":"9e03aa6a33b5d3b16845d6c46ee462e1978f7b610eb0dd1808f0e48f6df1d286","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:10.215624Z","signature_b64":"UaBW76ZDhFEfeEnwFgMoAyYF+UbLI3/T7Lk4fZ82H7IzG14DEdz3ZYXTeMuAORKVIFt7Mv6be0MzUBdWrj71DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e03aa6a33b5d3b16845d6c46ee462e1978f7b610eb0dd1808f0e48f6df1d286","last_reissued_at":"2026-07-05T10:22:10.215075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:10.215075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14808","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FNDh1+ym4wOHNYVVQS362YLxSSSJ3Or1zHje45r4g1LEj5qAhj4xxa456HyyQGeVW1uBW0jtJOgVg1dqOCrQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:35:01.895341Z"},"content_sha256":"f881098576bcb53fe6d3f6e611fd227ed76bc9f52e1783a8d846ad15120f32c9","schema_version":"1.0","event_id":"sha256:f881098576bcb53fe6d3f6e611fd227ed76bc9f52e1783a8d846ad15120f32c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TYB2U2RTWXJ3C2CF23CG5ZDC4G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High-Resolution Image Synthesis via Next-Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dengsheng Chen, Enhua Wu, Jie Hu, Tiezhu Yue, Xiaoming Wei","submitted_at":"2024-11-22T09:08:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14808","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/2411.14808/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"htQvRb8rGd+DQTY6bfJ0cf3royLpfseXzFRGUaIZs404iYvk2lvdWJdmYH1m25/NflE+ulGc29R0vmlh7N56Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:35:01.895730Z"},"content_sha256":"670d7b22890cf5d8bfb042bf2d8ddd32b7fb25e934925fcc3d0ec8c9a6b6383a","schema_version":"1.0","event_id":"sha256:670d7b22890cf5d8bfb042bf2d8ddd32b7fb25e934925fcc3d0ec8c9a6b6383a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/bundle.json","state_url":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T05:35:01Z","links":{"resolver":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G","bundle":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/bundle.json","state":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4IjA0YZr8oHHmsx4diOLhZ8S0kl7vSgPxa6DNIBEsPr/HHtVu9q70i64YZuIQBLnH6YEbwY8WKVkiTq3VzcDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:35:01.898500Z","bundle_sha256":"a475f45ac72523aa93256865352c815f18081353927750780c5fcc4f111af0da"}}