{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WKYJLQMBAUVRUFRACMHMKGQWP4","short_pith_number":"pith:WKYJLQMB","schema_version":"1.0","canonical_sha256":"b2b095c181052b1a1620130ec51a167f28d185e94de65f8064e60be64198f54e","source":{"kind":"arxiv","id":"2604.14585","version":2},"attestation_state":"computed","paper":{"title":"Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Prompt optimization in compound AI systems performs no better than random chance on most tasks.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing Zhu, Guanghui Wang, Peiyang He, Wei Qiu, Xing Zhang, Yanwei Cui, Ziyuan Li","submitted_at":"2026-04-16T03:23:46Z","abstract_excerpt":"Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku 4.5 (6 methods $\\times$ 4 tasks $\\times$ 3 repeats), 49% score below zero-shot; on Amazon Nova Lite, the failure rate is even higher. Yet on one task, all six methods improve over zero-shot by up to $+6.8$ points. What distinguishes success from failure? We investigate with 18,000 grid evaluations and 144 optimization runs, testing two assumptions behind end-to-end optimization tools like TextGrad and DSPy, in the order they must be answered: (A) agent pro"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.14585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-16T03:23:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"662f573db131e5cd7e7c7cd80bc165db3f7d6623bfbf3d3f4723bd87495016e4","abstract_canon_sha256":"ff912bb80d5464568b224fd1c42b15b927036bbb6e95114c81bb049248c97f08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:40.145846Z","signature_b64":"/aPqtMu1Iv9BxTaKhBa7uO4LEWL3omUuDG0o/weGkJJ6OvuhS9ffs2FAjeJ2DVIwTS+17zRouN7mjo8PH5C2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2b095c181052b1a1620130ec51a167f28d185e94de65f8064e60be64198f54e","last_reissued_at":"2026-05-28T01:04:40.145303Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:40.145303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Prompt optimization in compound AI systems performs no better than random chance on most tasks.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing Zhu, Guanghui Wang, Peiyang He, Wei Qiu, Xing Zhang, Yanwei Cui, Ziyuan Li","submitted_at":"2026-04-16T03:23:46Z","abstract_excerpt":"Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku 4.5 (6 methods $\\times$ 4 tasks $\\times$ 3 repeats), 49% score below zero-shot; on Amazon Nova Lite, the failure rate is even higher. Yet on one task, all six methods improve over zero-shot by up to $+6.8$ points. What distinguishes success from failure? We investigate with 18,000 grid evaluations and 144 optimization runs, testing two assumptions behind end-to-end optimization tools like TextGrad and DSPy, in the order they must be answered: (A) agent pro"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku (6 methods × 4 tasks × 3 repeats), 49% score below zero-shot; ... optimization helps only when the task has exploitable output structure -- a format the model can produce but does not default to.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the tested tasks, models (Claude Haiku, Amazon Nova Lite), and optimization methods are representative enough for the conclusions about interaction effects (p > 0.52) and exploitable output structure to generalize to other compound AI systems.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Prompt optimization in compound AI systems is statistically indistinguishable from random chance except when tasks have exploitable output structure; a two-stage diagnostic predicts success.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Prompt optimization in compound AI systems performs no better than random chance on most tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e658e18bac694bde6c020690665d8a06dc1c5a191d1a25c8ad695aeeed33eb24"},"source":{"id":"2604.14585","kind":"arxiv","version":2},"verdict":{"id":"5b6170b0-f2ff-4fb6-9a54-d624623dd0fe","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T11:13:25.020340Z","strongest_claim":"Prompt optimization in compound AI systems is statistically indistinguishable from a coin flip: across 72 optimization runs on Claude Haiku (6 methods × 4 tasks × 3 repeats), 49% score below zero-shot; ... optimization helps only when the task has exploitable output structure -- a format the model can produce but does not default to.","one_line_summary":"Prompt optimization in compound AI systems is statistically indistinguishable from random chance except when tasks have exploitable output structure; a two-stage diagnostic predicts success.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the tested tasks, models (Claude Haiku, Amazon Nova Lite), and optimization methods are representative enough for the conclusions about interaction effects (p > 0.52) and exploitable output structure to generalize to other compound AI systems.","pith_extraction_headline":"Prompt optimization in compound AI systems performs no better than random chance on most tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.14585/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.14585","created_at":"2026-05-28T01:04:40.145395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.14585v2","created_at":"2026-05-28T01:04:40.145395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.14585","created_at":"2026-05-28T01:04:40.145395+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKYJLQMBAUVR","created_at":"2026-05-28T01:04:40.145395+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKYJLQMBAUVRUFRA","created_at":"2026-05-28T01:04:40.145395+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKYJLQMB","created_at":"2026-05-28T01:04:40.145395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4","json":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4.json","graph_json":"https://pith.science/api/pith-number/WKYJLQMBAUVRUFRACMHMKGQWP4/graph.json","events_json":"https://pith.science/api/pith-number/WKYJLQMBAUVRUFRACMHMKGQWP4/events.json","paper":"https://pith.science/paper/WKYJLQMB"},"agent_actions":{"view_html":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4","download_json":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4.json","view_paper":"https://pith.science/paper/WKYJLQMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.14585&json=true","fetch_graph":"https://pith.science/api/pith-number/WKYJLQMBAUVRUFRACMHMKGQWP4/graph.json","fetch_events":"https://pith.science/api/pith-number/WKYJLQMBAUVRUFRACMHMKGQWP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4/action/storage_attestation","attest_author":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4/action/author_attestation","sign_citation":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4/action/citation_signature","submit_replication":"https://pith.science/pith/WKYJLQMBAUVRUFRACMHMKGQWP4/action/replication_record"}},"created_at":"2026-05-28T01:04:40.145395+00:00","updated_at":"2026-05-28T01:04:40.145395+00:00"}