{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZBIFWSXZCRK25QX3ZE4WQV57YY","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":"e077e947455c08faeeffd580af4ac6df67e4d70cea716257013f40d32d2322a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T12:31:58Z","title_canon_sha256":"c337b1cb1beb64f1a46d0711724b311cf5c639e9c049e33d0260d67687bd933e"},"schema_version":"1.0","source":{"id":"2607.24354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24354","created_at":"2026-07-28T02:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24354v1","created_at":"2026-07-28T02:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24354","created_at":"2026-07-28T02:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZBIFWSXZCRK2","created_at":"2026-07-28T02:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZBIFWSXZCRK25QX3","created_at":"2026-07-28T02:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZBIFWSXZ","created_at":"2026-07-28T02:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:83650338140fcb7b1dab1286cea77a45e998b17a635b56f4b3ecb58087669046","target":"graph","created_at":"2026-07-28T02:23:58Z","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/2607.24354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic prompt optimization (APO) has been widely adopted to adapt vision-language models (VLMs) to downstream tasks without weight updates, yielding promising results. However, on multimodal tasks, the effectiveness of APO is fundamentally bottlenecked by a blind feedback channel: the optimizer reads the question, the prediction, and the gold answer, but never the input image on which the model failed, and therefore cannot diagnose visually grounded errors. As a remedy, we introduce Cross-Modal Visual Feedback (CMVF). CMVF incorporates (1) a failure-conditioned visual diagnosis stage, in wh","authors_text":"Haoyue Liu, Xiaoying Tang, Xiaoyu Ma, Ye Chen, Yuexian Zou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T12:31:58Z","title":"Are Prompt Optimizers Blind? Cross-Modal Visual Feedback for Automatic Prompt Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24354","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:e7dba9ed99a6ea53619ecb5472b0ff744cdd8770fd2584b730be0ee70c2a23d4","target":"record","created_at":"2026-07-28T02:23:58Z","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":"e077e947455c08faeeffd580af4ac6df67e4d70cea716257013f40d32d2322a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-27T12:31:58Z","title_canon_sha256":"c337b1cb1beb64f1a46d0711724b311cf5c639e9c049e33d0260d67687bd933e"},"schema_version":"1.0","source":{"id":"2607.24354","kind":"arxiv","version":1}},"canonical_sha256":"c8505b4af91455aec2fbc9396857bfc63b772b1a2a5a8f40b992b9547ae02d45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8505b4af91455aec2fbc9396857bfc63b772b1a2a5a8f40b992b9547ae02d45","first_computed_at":"2026-07-28T02:23:58.881587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:23:58.881587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DmK7jntZhNT6RJeSVmo+LvcwpzcWjBUJeOESDm7GRKKRcy7F5eY39Xoc/pP1x6/Mj9icd2Ymfaw5ngzU68QXAQ==","signature_status":"signed_v1","signed_at":"2026-07-28T02:23:58.882487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7dba9ed99a6ea53619ecb5472b0ff744cdd8770fd2584b730be0ee70c2a23d4","sha256:83650338140fcb7b1dab1286cea77a45e998b17a635b56f4b3ecb58087669046"],"state_sha256":"f986635f4b2746bd8eff149e2534388c62d244d7d55b489a71bf081e253c53f3"}