{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TYB2U2RTWXJ3C2CF23CG5ZDC4G","short_pith_number":"pith:TYB2U2RT","schema_version":"1.0","canonical_sha256":"9e03aa6a33b5d3b16845d6c46ee462e1978f7b610eb0dd1808f0e48f6df1d286","source":{"kind":"arxiv","id":"2411.14808","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.14808","created_at":"2026-07-05T10:22:10.215135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14808v2","created_at":"2026-07-05T10:22:10.215135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14808","created_at":"2026-07-05T10:22:10.215135+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYB2U2RTWXJ3","created_at":"2026-07-05T10:22:10.215135+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYB2U2RTWXJ3C2CF","created_at":"2026-07-05T10:22:10.215135+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYB2U2RT","created_at":"2026-07-05T10:22:10.215135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G","json":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G.json","graph_json":"https://pith.science/api/pith-number/TYB2U2RTWXJ3C2CF23CG5ZDC4G/graph.json","events_json":"https://pith.science/api/pith-number/TYB2U2RTWXJ3C2CF23CG5ZDC4G/events.json","paper":"https://pith.science/paper/TYB2U2RT"},"agent_actions":{"view_html":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G","download_json":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G.json","view_paper":"https://pith.science/paper/TYB2U2RT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14808&json=true","fetch_graph":"https://pith.science/api/pith-number/TYB2U2RTWXJ3C2CF23CG5ZDC4G/graph.json","fetch_events":"https://pith.science/api/pith-number/TYB2U2RTWXJ3C2CF23CG5ZDC4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/action/storage_attestation","attest_author":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/action/author_attestation","sign_citation":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/action/citation_signature","submit_replication":"https://pith.science/pith/TYB2U2RTWXJ3C2CF23CG5ZDC4G/action/replication_record"}},"created_at":"2026-07-05T10:22:10.215135+00:00","updated_at":"2026-07-05T10:22:10.215135+00:00"}