{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FWUGH6CHHDHARF2ESMWC2RXKD3","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":"adc158b6455d27ad87423648c9506f5a0d52d424a16a466b72b206d421e7e774","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:46:53Z","title_canon_sha256":"5f8e838e12f752436a1554d61ae530be687b34f3eef794d6740f7f0710481fca"},"schema_version":"1.0","source":{"id":"2408.02657","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02657","created_at":"2026-07-05T10:53:38Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02657v3","created_at":"2026-07-05T10:53:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02657","created_at":"2026-07-05T10:53:38Z"},{"alias_kind":"pith_short_12","alias_value":"FWUGH6CHHDHA","created_at":"2026-07-05T10:53:38Z"},{"alias_kind":"pith_short_16","alias_value":"FWUGH6CHHDHARF2E","created_at":"2026-07-05T10:53:38Z"},{"alias_kind":"pith_short_8","alias_value":"FWUGH6CH","created_at":"2026-07-05T10:53:38Z"}],"graph_snapshots":[{"event_id":"sha256:4bbc689f2c266423ade2f4fc0a25608463fd21f8618ed629e0832002f2b9ad86","target":"graph","created_at":"2026-07-05T10:53:38Z","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/2408.02657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Lumina-mGPT, a family of multimodal autoregressive models capable of various vision and language tasks, particularly excelling in generating flexible photorealistic images from text descriptions. By initializing from multimodal Generative PreTraining (mGPT), we demonstrate that decoder-only Autoregressive (AR) model can achieve image generation performance comparable to modern diffusion models with high efficiency through Flexible Progressive Supervised Fine-tuning (FP-SFT). Equipped with our proposed Unambiguous image Representation (UniRep), Lumina-mGPT can flexibly generate high-","authors_text":"Dongyang Liu, Hongsheng Li, Le Zhuo, Peng Gao, Qi Qin, Shitian Zhao, Weifeng Lin, Xinyue Li, Yi Xin, Yu Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:46:53Z","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02657","kind":"arxiv","version":3},"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":"sha256:9546e3688e9d76aff2bc1c4387be73672d6e9242dae076cda8d47bbf246387bf","target":"record","created_at":"2026-07-05T10:53:38Z","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":"adc158b6455d27ad87423648c9506f5a0d52d424a16a466b72b206d421e7e774","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:46:53Z","title_canon_sha256":"5f8e838e12f752436a1554d61ae530be687b34f3eef794d6740f7f0710481fca"},"schema_version":"1.0","source":{"id":"2408.02657","kind":"arxiv","version":3}},"canonical_sha256":"2da863f84738ce089744932c2d46ea1ef45b772cb3fda77ef1549b86ff1e6d5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2da863f84738ce089744932c2d46ea1ef45b772cb3fda77ef1549b86ff1e6d5c","first_computed_at":"2026-07-05T10:53:38.833162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:38.833162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o1sdVvhozv+/xz8OIs6roYlDVlUkJYr4bmoOH19TVt4jl8Fb2+pI7N4TfCtHnwsHrBi+V1dib/TYfzF9R9dXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:38.833682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02657","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9546e3688e9d76aff2bc1c4387be73672d6e9242dae076cda8d47bbf246387bf","sha256:4bbc689f2c266423ade2f4fc0a25608463fd21f8618ed629e0832002f2b9ad86"],"state_sha256":"dd2c0a3b1eac9864b6f6a92c0768f2bc4a0f6b947804898e7cd25256950b49ef"}