{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FPJNFMHJVKJRNTQVTNHDSA5ZEV","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":"c04aaa40184fb92119153f8409d6b7ac730a193d68f98c85e6745f9c4aef8bdb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:59:59Z","title_canon_sha256":"430c4f420266d19a67e99f8c8ac05c9f4baf749aa6b2774880c97a60a68f70d0"},"schema_version":"1.0","source":{"id":"2410.13863","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13863","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13863v1","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13863","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_12","alias_value":"FPJNFMHJVKJR","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_16","alias_value":"FPJNFMHJVKJRNTQV","created_at":"2026-07-05T09:22:06Z"},{"alias_kind":"pith_short_8","alias_value":"FPJNFMHJ","created_at":"2026-07-05T09:22:06Z"}],"graph_snapshots":[{"event_id":"sha256:ec210dc07b8819b1eba4fdcbaa970b9ec4ecb64629a0d211b37f10b9f14d49aa","target":"graph","created_at":"2026-07-05T09:22:06Z","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/2410.13863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling up autoregressive models in vision has not proven as beneficial as in large language models. In this work, we investigate this scaling problem in the context of text-to-image generation, focusing on two critical factors: whether models use discrete or continuous tokens, and whether tokens are generated in a random or fixed raster order using BERT- or GPT-like transformer architectures. Our empirical results show that, while all models scale effectively in terms of validation loss, their evaluation performance -- measured by FID, GenEval score, and visual quality -- follows different tr","authors_text":"Chen Sun, Deqing Sun, Kaiming He, Lijie Fan, Michael Rubinstein, Siyang Qin, Tianhong Li, Yonglong Tian, Yuanzhen Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:59:59Z","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13863","kind":"arxiv","version":1},"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":"sha256:1ad8658efcc8962865b36c266392f0f8a301fba6d0d7f3b3e8f3d57ea62863f1","target":"record","created_at":"2026-07-05T09:22:06Z","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":"c04aaa40184fb92119153f8409d6b7ac730a193d68f98c85e6745f9c4aef8bdb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-17T17:59:59Z","title_canon_sha256":"430c4f420266d19a67e99f8c8ac05c9f4baf749aa6b2774880c97a60a68f70d0"},"schema_version":"1.0","source":{"id":"2410.13863","kind":"arxiv","version":1}},"canonical_sha256":"2bd2d2b0e9aa9316ce159b4e3903b92566661304f0b95caa429c7274c43b7235","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bd2d2b0e9aa9316ce159b4e3903b92566661304f0b95caa429c7274c43b7235","first_computed_at":"2026-07-05T09:22:06.784868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:06.784868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BB9pjhVDCtSga4BObhshYMxmib7DczMt3J/8O8+MrnKvi/n2O3X/CFs9rcWecOYGwd1mDVAfSM9kfSDmlEbmDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:06.785366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13863","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ad8658efcc8962865b36c266392f0f8a301fba6d0d7f3b3e8f3d57ea62863f1","sha256:ec210dc07b8819b1eba4fdcbaa970b9ec4ecb64629a0d211b37f10b9f14d49aa"],"state_sha256":"49a3520d4ecec4af3cfabfcc6b2e3b56963eba7415dc1ebac78b57e69117d870"}