{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WSSNDNYWPGZJZGLCAHHSIJVRAI","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":"5ebb0fa51c76ed090524b74dc53c3d1bd3e7f75c2b33e8576e10f3ceb52315e7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:47:55Z","title_canon_sha256":"0a4477b4505f0e4752e79e26975d27f52eb087b42d43e8674a53dcbfe8c22326"},"schema_version":"1.0","source":{"id":"2505.00759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00759","created_at":"2026-07-05T11:01:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00759v2","created_at":"2026-07-05T11:01:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00759","created_at":"2026-07-05T11:01:57Z"},{"alias_kind":"pith_short_12","alias_value":"WSSNDNYWPGZJ","created_at":"2026-07-05T11:01:57Z"},{"alias_kind":"pith_short_16","alias_value":"WSSNDNYWPGZJZGLC","created_at":"2026-07-05T11:01:57Z"},{"alias_kind":"pith_short_8","alias_value":"WSSNDNYW","created_at":"2026-07-05T11:01:57Z"}],"graph_snapshots":[{"event_id":"sha256:3857ae1b96c0d07c29f9b01611d427973c80d4d7620c329e7153ee8228e81081","target":"graph","created_at":"2026-07-05T11:01:57Z","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/2505.00759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The steady improvements of text-to-image (T2I) generative models lead to slow deprecation of automatic evaluation benchmarks that rely on static datasets, motivating researchers to seek alternative ways to evaluate the T2I progress. In this paper, we explore the potential of multi-modal large language models (MLLMs) as evaluator agents that interact with a T2I model, with the objective of assessing prompt-generation consistency and image aesthetics. We present Multimodal Text-to-Image Eval (MT2IE), an evaluation framework that iteratively generates prompts for evaluation, scores generated imag","authors_text":"Adriana Romero-Soriano, Candace Ross, Jiahui Chen, Koustuv Sinha, Melissa Hall, Michal Drozdzal, Reyhane Askari-Hemmat","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:47:55Z","title":"Multi-Modal Language Models as Text-to-Image Model Evaluators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00759","kind":"arxiv","version":2},"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:e438de675a6fd03f70736f3baa8f52928afa427f428dc3d6d9582011c7711d8b","target":"record","created_at":"2026-07-05T11:01:57Z","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":"5ebb0fa51c76ed090524b74dc53c3d1bd3e7f75c2b33e8576e10f3ceb52315e7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-01T17:47:55Z","title_canon_sha256":"0a4477b4505f0e4752e79e26975d27f52eb087b42d43e8674a53dcbfe8c22326"},"schema_version":"1.0","source":{"id":"2505.00759","kind":"arxiv","version":2}},"canonical_sha256":"b4a4d1b71679b29c996201cf2426b10222f6cb101ef7ef892f2e04db0cbd5688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4a4d1b71679b29c996201cf2426b10222f6cb101ef7ef892f2e04db0cbd5688","first_computed_at":"2026-07-05T11:01:57.314279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:57.314279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uhArqW4wwCCvZyrysRD8LU9vqlF5gf4V66uZutzxEMOkIiq/uGT6nR5tdGVbUVGEhScbLvk8OCOxOPrjky2BAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:57.314847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e438de675a6fd03f70736f3baa8f52928afa427f428dc3d6d9582011c7711d8b","sha256:3857ae1b96c0d07c29f9b01611d427973c80d4d7620c329e7153ee8228e81081"],"state_sha256":"57dd9df26ba94f28cf1a8abac9f02580644d06102cae053049ad3a78d54b0c50"}