{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5OPQJ5WWPRGEB6X5RHCYB4AHTO","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":"3451a8e86530119363c9a298d42f388af5b867aad990cb928b233f45dcdd8877","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-19T01:14:36Z","title_canon_sha256":"9032bdc2e72b83942b4ed874c70acec101d94b886aee5b9f3aa474749443b299"},"schema_version":"1.0","source":{"id":"2603.18388","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.18388","created_at":"2026-06-09T02:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2603.18388v2","created_at":"2026-06-09T02:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.18388","created_at":"2026-06-09T02:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"5OPQJ5WWPRGE","created_at":"2026-06-09T02:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"5OPQJ5WWPRGEB6X5","created_at":"2026-06-09T02:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"5OPQJ5WW","created_at":"2026-06-09T02:07:24Z"}],"graph_snapshots":[{"event_id":"sha256:a2c2406a5417cd1f1398e7db0d31e08d7e8c6968f2c6eaefb1717b05fc430b33","target":"graph","created_at":"2026-06-09T02:07:24Z","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/2603.18388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iteratively refine prompts by diagnosing failure cases, but the optimization process remains black-box and label-free, leading to uninterpretable trajectories and systematic failure. We identify and empirically demonstrate four limitations: on GSM8K with a defective seed, GEPA degrades accuracy from 23.81% to 13.50%. We propose VISTA, a multi-agent APO framework that decouples hypothesis generation from prompt rewriting, ena","authors_text":"Qifeng Xia, Qiyun Xia, Rui Qu, Shiyan Liu, Xinyu Yu, Yisheng Liu","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-19T01:14:36Z","title":"Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.18388","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":"sha256:464bc2bffc73425bfabd73bf60e2b3937c398f13e1f8d4a3a015162d26f42885","target":"record","created_at":"2026-06-09T02:07:24Z","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":"3451a8e86530119363c9a298d42f388af5b867aad990cb928b233f45dcdd8877","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-19T01:14:36Z","title_canon_sha256":"9032bdc2e72b83942b4ed874c70acec101d94b886aee5b9f3aa474749443b299"},"schema_version":"1.0","source":{"id":"2603.18388","kind":"arxiv","version":2}},"canonical_sha256":"eb9f04f6d67c4c40fafd89c580f0079b9b248b27e3b361ee22cd90b9013f9308","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb9f04f6d67c4c40fafd89c580f0079b9b248b27e3b361ee22cd90b9013f9308","first_computed_at":"2026-06-09T02:07:24.422622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:24.422622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PCliUxW7uvR7deX7QBGRO/SYcpt+B9FIZCV1Zurl2v3ebYxmrRzLvxCPp3oYDkbkN5qbPluRnkoBdIgl4mJbCg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:24.423754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.18388","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:464bc2bffc73425bfabd73bf60e2b3937c398f13e1f8d4a3a015162d26f42885","sha256:a2c2406a5417cd1f1398e7db0d31e08d7e8c6968f2c6eaefb1717b05fc430b33"],"state_sha256":"e5c6942130e3f0d8ee06f134468150038b71410c8521fb12949ddedadac4a4d8"}