{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BYMASWWZIUPWUDQK2TE2FQSPTN","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":"5f6b8be4025a3c02ce46ba00f75dcd7384dacb455668ca3d9937007f59b40f3c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:06:47Z","title_canon_sha256":"c1566d40e98e0caa35d2d167362d656b398087c5fa6eaf5beea1544ca4890e7c"},"schema_version":"1.0","source":{"id":"2509.08777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08777","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08777v1","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08777","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"BYMASWWZIUPW","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"BYMASWWZIUPWUDQK","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"BYMASWWZ","created_at":"2026-07-05T12:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:8e9085ee76f8b739aa9c606407eb04c24f5f40345bf47588584d580fbbba7018","target":"graph","created_at":"2026-07-05T12:08:36Z","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/2509.08777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly used to evaluate text-to-image (TTI) generation systems, providing automated judgments based on visual and textual context. However, these \"judge\" models often suffer from biases, overconfidence, and inconsistent performance across diverse image domains. While prompt ensembling has shown promise for mitigating these issues in unimodal, text-only settings, our experiments reveal that standard ensembling methods fail to generalize effectively for TTI tasks. To address these limitations, we propose a new multimodal-aware method called Mult","authors_text":"Eric Slyman, Kushal Kafle, Mehrab Tanjim, Stefan Lee","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:06:47Z","title":"Calibrating MLLM-as-a-judge via Multimodal Bayesian Prompt Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08777","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:fb152f2c740f24b29e9677a56ca3d0541026c50561ed71d9f76ecda872764471","target":"record","created_at":"2026-07-05T12:08:36Z","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":"5f6b8be4025a3c02ce46ba00f75dcd7384dacb455668ca3d9937007f59b40f3c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T17:06:47Z","title_canon_sha256":"c1566d40e98e0caa35d2d167362d656b398087c5fa6eaf5beea1544ca4890e7c"},"schema_version":"1.0","source":{"id":"2509.08777","kind":"arxiv","version":1}},"canonical_sha256":"0e18095ad9451f6a0e0ad4c9a2c24f9b4e103007d18eb5c72ae774a2fc35ac36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e18095ad9451f6a0e0ad4c9a2c24f9b4e103007d18eb5c72ae774a2fc35ac36","first_computed_at":"2026-07-05T12:08:36.073536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:36.073536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WTOsknWbOkQKSNvRZZU60dpjbpbVnNxrhj9NRq2kQUwFXzH8cNm83R7EGXfEiRNJFA818sIdvCNk7YmpbAnGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:36.074119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb152f2c740f24b29e9677a56ca3d0541026c50561ed71d9f76ecda872764471","sha256:8e9085ee76f8b739aa9c606407eb04c24f5f40345bf47588584d580fbbba7018"],"state_sha256":"09208de668dd3a205ed61dd16ce7bf75121d6620e25162b5e28ddd1fa1ddef0d"}