{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UJTTIYFBGOTOLORU42RPT63MA4","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":"ebb0609e16fa5ac1886bb8bbaf629918be4e1c4f8a4d33134bb65219c0e80a69","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T20:29:53Z","title_canon_sha256":"158d023b40e8ba071be122afd415809f65eabb7432d3ca1f713ce4ed405bb3ec"},"schema_version":"1.0","source":{"id":"2506.08210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08210","created_at":"2026-07-05T11:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08210v1","created_at":"2026-07-05T11:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08210","created_at":"2026-07-05T11:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"UJTTIYFBGOTO","created_at":"2026-07-05T11:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"UJTTIYFBGOTOLORU","created_at":"2026-07-05T11:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"UJTTIYFB","created_at":"2026-07-05T11:21:48Z"}],"graph_snapshots":[{"event_id":"sha256:7970f7815f2bf4f669c6ef18f0ac26d0d9d8ee7b2d4fed77b5ef52d064e93de8","target":"graph","created_at":"2026-07-05T11:21:48Z","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/2506.08210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Both text-to-image generation and large language models (LLMs) have made significant advancements. However, many text-to-image models still employ the somewhat outdated T5 and CLIP as their text encoders. In this work, we investigate the effectiveness of using modern decoder-only LLMs as text encoders for text-to-image diffusion models. We build a standardized training and evaluation pipeline that allows us to isolate and evaluate the effect of different text embeddings. We train a total of 27 text-to-image models with 12 different text encoders to analyze the critical aspects of LLMs that cou","authors_text":"Andrew Z. Wang, Ming-Yu Liu, Songwei Ge, Tero Karras, Yogesh Balaji","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T20:29:53Z","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08210","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":"sha256:9d43ace3bc0f12f1a220c24e2aa23a43949463ac69f34ab5ecb2aebdef81bd76","target":"record","created_at":"2026-07-05T11:21:48Z","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":"ebb0609e16fa5ac1886bb8bbaf629918be4e1c4f8a4d33134bb65219c0e80a69","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T20:29:53Z","title_canon_sha256":"158d023b40e8ba071be122afd415809f65eabb7432d3ca1f713ce4ed405bb3ec"},"schema_version":"1.0","source":{"id":"2506.08210","kind":"arxiv","version":1}},"canonical_sha256":"a2673460a133a6e5ba34e6a2f9fb6c073db1386ec89c9537188a36a3d04981c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2673460a133a6e5ba34e6a2f9fb6c073db1386ec89c9537188a36a3d04981c3","first_computed_at":"2026-07-05T11:21:48.819133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:48.819133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2JFAOtqR1EIduQ2d6f63BoPl/IK1kP0ZzEpO3EI9sPsZ6QTRMcKUFon7rMrdK9F9P51+AAjAB+S78Z6JL7FXAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:48.819711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d43ace3bc0f12f1a220c24e2aa23a43949463ac69f34ab5ecb2aebdef81bd76","sha256:7970f7815f2bf4f669c6ef18f0ac26d0d9d8ee7b2d4fed77b5ef52d064e93de8"],"state_sha256":"09a7cf9d28c897daaddc5c02a3049218b191bcc54e55b81b18065ff124aa3516"}