{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZSZSUH7CKTEXLGHHHWRFJIP7GX","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":"dee2d047fbd40b05e5f95efa17b9ff8c80b2d8639a39cdd8eb0b7859f7244c8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T07:01:50Z","title_canon_sha256":"d942ba238094d7c681dac1f44b9ac8546c0f597aa09e7afb92aee306ec5513d8"},"schema_version":"1.0","source":{"id":"2507.19002","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19002","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19002v1","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19002","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZSZSUH7CKTEX","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"pith_short_16","alias_value":"ZSZSUH7CKTEXLGHH","created_at":"2026-07-05T11:43:17Z"},{"alias_kind":"pith_short_8","alias_value":"ZSZSUH7C","created_at":"2026-07-05T11:43:17Z"}],"graph_snapshots":[{"event_id":"sha256:771459305035176bc13be06ee52d70f3b16228c70ac7f620b91f0e3e3727df2a","target":"graph","created_at":"2026-07-05T11:43:17Z","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/2507.19002/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contemporary image generation systems have achieved high fidelity and superior aesthetic quality beyond basic text-image alignment. However, existing evaluation frameworks have failed to evolve in parallel. This study reveals that human preference reward models fine-tuned based on CLIP and BLIP architectures have inherent flaws: they inappropriately assign low scores to images with rich details and high aesthetic value, creating a significant discrepancy with actual human aesthetic preferences. To address this issue, we design a novel evaluation score, ICT (Image-Contained-Text) score, that ac","authors_text":"Bing Su, Ji-Rong Wen, Tao Liang, Tianyu Zhang, Wenyi Mo, Yalong Bai, Ying Ba","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T07:01:50Z","title":"Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19002","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":"sha256:81782101add6452ee17095a8c6a5c28ff3d9516d4f79ea191d6d57851b21a8d7","target":"record","created_at":"2026-07-05T11:43:17Z","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":"dee2d047fbd40b05e5f95efa17b9ff8c80b2d8639a39cdd8eb0b7859f7244c8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T07:01:50Z","title_canon_sha256":"d942ba238094d7c681dac1f44b9ac8546c0f597aa09e7afb92aee306ec5513d8"},"schema_version":"1.0","source":{"id":"2507.19002","kind":"arxiv","version":1}},"canonical_sha256":"ccb32a1fe254c97598e73da254a1ff35d901bd4c645f520284b5b8209794de86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccb32a1fe254c97598e73da254a1ff35d901bd4c645f520284b5b8209794de86","first_computed_at":"2026-07-05T11:43:17.651846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:17.651846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LUAjxcpgKngJD09mNIVaf36mI5NpuFP2rk9PawKREn9ySUPP5kJ/bzshsgtBLKfMU1Qx7IeRCCa4pX343DE/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:17.652245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19002","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81782101add6452ee17095a8c6a5c28ff3d9516d4f79ea191d6d57851b21a8d7","sha256:771459305035176bc13be06ee52d70f3b16228c70ac7f620b91f0e3e3727df2a"],"state_sha256":"e42f7581a3a9f8c957dcd498addabb854d9ae97c26c139281091c56702a73fb9"}