{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P767SZHFHSZVSPIGAYPXV4PWEC","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":"b2769d5dab2aaebef72d6269f69ad6b825f9e27167ea874a41f11e6d536f726c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:58:07Z","title_canon_sha256":"c6a1b55467ac5cb9bd507b7b39ab0365697170902e4366120e01e2c4f73b6d49"},"schema_version":"1.0","source":{"id":"2504.16080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16080","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16080v1","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16080","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"P767SZHFHSZV","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"P767SZHFHSZVSPIG","created_at":"2026-07-05T10:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"P767SZHF","created_at":"2026-07-05T10:52:35Z"}],"graph_snapshots":[{"event_id":"sha256:55eedfdf889fd002d4665928d16145a072eef5ff83c94aa9b179bb438e86fc33","target":"graph","created_at":"2026-07-05T10:52:35Z","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/2504.16080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes and fine-grained details. Inspired by the self-reflection capabilities emergent in large language models, we propose ReflectionFlow, an inference-time framework enabling diffusion models to iteratively reflect upon and refine their outputs. ReflectionFlow introduces three complementary inference-time scaling axes: (1) noise-level scaling to optimize latent initialization; (2) prompt-level scaling for precise semanti","authors_text":"Hongsheng Li, Le Zhuo, Liangbing Zhao, Mohamed Elhoseiny, Peng Gao, Renrui Zhang, Sayak Paul, Yi Xin, Yue Liao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:58:07Z","title":"From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16080","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:c539418d4aa643d5a9f9ec236a4a801a27b6205069502e33f5c3aa75730eb73f","target":"record","created_at":"2026-07-05T10:52:35Z","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":"b2769d5dab2aaebef72d6269f69ad6b825f9e27167ea874a41f11e6d536f726c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:58:07Z","title_canon_sha256":"c6a1b55467ac5cb9bd507b7b39ab0365697170902e4366120e01e2c4f73b6d49"},"schema_version":"1.0","source":{"id":"2504.16080","kind":"arxiv","version":1}},"canonical_sha256":"7ffdf964e53cb3593d06061f7af1f6208fd49a73b4abcc5d3d1f4b5b19cbde13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ffdf964e53cb3593d06061f7af1f6208fd49a73b4abcc5d3d1f4b5b19cbde13","first_computed_at":"2026-07-05T10:52:35.204283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:35.204283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cvYPvAtdMPKLKOgYzLbIVxG7xvWj0QG5kv2Z5KSzVtIN7wjSRSxpiV3XgAYRJgG5iYNBtkv9/HlMny764Uy7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:35.204753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c539418d4aa643d5a9f9ec236a4a801a27b6205069502e33f5c3aa75730eb73f","sha256:55eedfdf889fd002d4665928d16145a072eef5ff83c94aa9b179bb438e86fc33"],"state_sha256":"19e62f465bd7a6f35187174c470fd90b435a883a43a0a03fb2dff10f534629ff"}