{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OHLYRMV64NY7IWUMJOPP3ZVGES","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":"07b4697affbf8512311a67420b8d29b835d218857b7029b858a2658d793270d8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T06:49:24Z","title_canon_sha256":"417bb8c841b4abce63f45b0d0f823b90d8053ff8c86ce95dc488de71f512ce46"},"schema_version":"1.0","source":{"id":"2603.23994","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.23994","created_at":"2026-05-27T02:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2603.23994v2","created_at":"2026-05-27T02:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23994","created_at":"2026-05-27T02:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"OHLYRMV64NY7","created_at":"2026-05-27T02:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"OHLYRMV64NY7IWUM","created_at":"2026-05-27T02:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"OHLYRMV6","created_at":"2026-05-27T02:06:13Z"}],"graph_snapshots":[{"event_id":"sha256:5bf79620a2ec7c987895a8b727628997724cf2089fd01067326256bb8c05095d","target":"graph","created_at":"2026-05-27T02:06:13Z","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/2603.23994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach to building self-improving agents, yet in practice remains brittle: despite active research, only 9% of surveyed agents used any automated optimization. We argue that this brittleness arises because, to set up a learning loop, an engineer must make ``hidden'' design choices: What can the optimizer edit and what is the \"right\" learning evidence to provide at each update? We investigate three factors that affect most ","authors_text":"Abhinav Akkiraju, Adith Swaminathan, Allen Nie, Anish Chaudhuri, Ching-An Cheng, Max Piasevoli, Prerit Choudhary, Rasool Fakoor, Ryan Rong, Shannon Xiao, Xavier Daull, YuCheng Yuan, Zhiyi Kuang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T06:49:24Z","title":"Understanding the Challenges in Iterative Generative Optimization with LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23994","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:a26d8524a7163ff1ed3fabd3103db5e985e16d1c581406581bb7630a9ae0782d","target":"record","created_at":"2026-05-27T02:06:13Z","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":"07b4697affbf8512311a67420b8d29b835d218857b7029b858a2658d793270d8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T06:49:24Z","title_canon_sha256":"417bb8c841b4abce63f45b0d0f823b90d8053ff8c86ce95dc488de71f512ce46"},"schema_version":"1.0","source":{"id":"2603.23994","kind":"arxiv","version":2}},"canonical_sha256":"71d788b2bee371f45a8c4b9efde6a62485a4b18c0efa461894642142172b0798","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71d788b2bee371f45a8c4b9efde6a62485a4b18c0efa461894642142172b0798","first_computed_at":"2026-05-27T02:06:13.854235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:06:13.854235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jY5jsN43UaC8d3abAaSMf3pw0rUfZ7fGYaa21Ed8MfqVU3QJ3RyiBcBjFhckmiFCQmIVaHyUcmi2TuAhFuLHCw==","signature_status":"signed_v1","signed_at":"2026-05-27T02:06:13.855032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.23994","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26d8524a7163ff1ed3fabd3103db5e985e16d1c581406581bb7630a9ae0782d","sha256:5bf79620a2ec7c987895a8b727628997724cf2089fd01067326256bb8c05095d"],"state_sha256":"5ec5923f2d1972ff2b1b6998a496ea77b1a4ac5600588b03c9de0bfe733b882e"}