{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5IEUCGG7JZJXJO6BXBECD7MEHV","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":"5eb5e1b961bb546b14831059ad26d4b48b2d73ee0ec24a5343eb36e3e8f5e3bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T12:08:41Z","title_canon_sha256":"5c15f676b6cfa187e71aa819999a1a0d7f6a1ef317409aaa98ed92f679066f64"},"schema_version":"1.0","source":{"id":"2403.18493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18493","created_at":"2026-07-05T08:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18493v1","created_at":"2026-07-05T08:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18493","created_at":"2026-07-05T08:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"5IEUCGG7JZJX","created_at":"2026-07-05T08:01:23Z"},{"alias_kind":"pith_short_16","alias_value":"5IEUCGG7JZJXJO6B","created_at":"2026-07-05T08:01:23Z"},{"alias_kind":"pith_short_8","alias_value":"5IEUCGG7","created_at":"2026-07-05T08:01:23Z"}],"graph_snapshots":[{"event_id":"sha256:04a66d580c501bb5532f88f544b8fbcad61e6e0721ddab43237d2e9d0dd653bf","target":"graph","created_at":"2026-07-05T08:01:23Z","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/2403.18493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically accurate, faithful to text, and of good low-level quality. We present VersaT2I, a versatile training framework that can boost the performance with multiple rewards of any T2I model. We decompose the quality of the image into several aspects such as aesthetics, text-image alignment, geometry, low-level quality, etc. Then, for every quality aspect, we select high-qua","authors_text":"Gaoang Wang, Hsiang-Wei Huang, Jenq-Neng Hwang, Jianshu Guo, Jiawei Zhang, Jie Deng, Tian Ye, Wenhao Chai, Yichen Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T12:08:41Z","title":"VersaT2I: Improving Text-to-Image Models with Versatile Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18493","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:ddf1c3389223bf7763214f1cdcd25a10d2c652420dfcc2018c42aa2c4b603ab7","target":"record","created_at":"2026-07-05T08:01:23Z","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":"5eb5e1b961bb546b14831059ad26d4b48b2d73ee0ec24a5343eb36e3e8f5e3bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T12:08:41Z","title_canon_sha256":"5c15f676b6cfa187e71aa819999a1a0d7f6a1ef317409aaa98ed92f679066f64"},"schema_version":"1.0","source":{"id":"2403.18493","kind":"arxiv","version":1}},"canonical_sha256":"ea094118df4e5374bbc1b84821fd843d7aeddbbec0ae82919e91b7f1f55165ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea094118df4e5374bbc1b84821fd843d7aeddbbec0ae82919e91b7f1f55165ff","first_computed_at":"2026-07-05T08:01:23.527988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:23.527988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FaJnBddFiKtLPlWoEsljSwLZV2OKbedtcSpzVUz4cgM/o92jKrWJM4OZ8u5If6fBwKUjWQfUqgYl0Unpif52Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:23.528437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddf1c3389223bf7763214f1cdcd25a10d2c652420dfcc2018c42aa2c4b603ab7","sha256:04a66d580c501bb5532f88f544b8fbcad61e6e0721ddab43237d2e9d0dd653bf"],"state_sha256":"1a922312d7f74c32b85f2c79bf2f4043b7b90671f7c8f7d26578e0808cee2994"}