{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TKL6EN2VWPKMLCGDIJEADSJ43B","short_pith_number":"pith:TKL6EN2V","schema_version":"1.0","canonical_sha256":"9a97e23755b3d4c588c3424801c93cd8586a89f851e20b552272b08602387db3","source":{"kind":"arxiv","id":"2606.11459","version":1},"attestation_state":"computed","paper":{"title":"APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cho-Jui Hsieh, Fei Wang, Inderjit S. Dhillon, Si Si","submitted_at":"2026-06-09T21:22:06Z","abstract_excerpt":"Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While evolutionary algorithms have emerged as the dominant paradigm, they suffer from a critical bottleneck: data efficiency. Current methods treat the development dataset as a static benchmark, wasting significant compute budget on uninformative data. In this work, we introduce APEX (Automatic Prompt Engineering eXpert), a novel framework that optimizes the data usage alongside the prompt search. APEX dynamically stratifies the dataset into Easy, Hard, "},"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":"2606.11459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T21:22:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0d6c96a20bb67c994dbb18235f867e5afccbf89a45fd155b4c72a82d1857271d","abstract_canon_sha256":"83c68d0364686a4a11edb7f18a86145ef29b1999f00153cf2b4deee081ca7784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:49.750034Z","signature_b64":"V0XwBU0RrIWazJLv8WkzU1Mim/NhtWCXBQjfB8MRCs4LsD/Kfn26PHyIu4xfU4P9UvxgN8hsEGWu8yBjLQ2RAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a97e23755b3d4c588c3424801c93cd8586a89f851e20b552272b08602387db3","last_reissued_at":"2026-06-11T01:09:49.749167Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:49.749167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cho-Jui Hsieh, Fei Wang, Inderjit S. Dhillon, Si Si","submitted_at":"2026-06-09T21:22:06Z","abstract_excerpt":"Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While evolutionary algorithms have emerged as the dominant paradigm, they suffer from a critical bottleneck: data efficiency. Current methods treat the development dataset as a static benchmark, wasting significant compute budget on uninformative data. In this work, we introduce APEX (Automatic Prompt Engineering eXpert), a novel framework that optimizes the data usage alongside the prompt search. APEX dynamically stratifies the dataset into Easy, Hard, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11459","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.11459/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":"2606.11459","created_at":"2026-06-11T01:09:49.749311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11459v1","created_at":"2026-06-11T01:09:49.749311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11459","created_at":"2026-06-11T01:09:49.749311+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKL6EN2VWPKM","created_at":"2026-06-11T01:09:49.749311+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKL6EN2VWPKMLCGD","created_at":"2026-06-11T01:09:49.749311+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKL6EN2V","created_at":"2026-06-11T01:09:49.749311+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/TKL6EN2VWPKMLCGDIJEADSJ43B","json":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B.json","graph_json":"https://pith.science/api/pith-number/TKL6EN2VWPKMLCGDIJEADSJ43B/graph.json","events_json":"https://pith.science/api/pith-number/TKL6EN2VWPKMLCGDIJEADSJ43B/events.json","paper":"https://pith.science/paper/TKL6EN2V"},"agent_actions":{"view_html":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B","download_json":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B.json","view_paper":"https://pith.science/paper/TKL6EN2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11459&json=true","fetch_graph":"https://pith.science/api/pith-number/TKL6EN2VWPKMLCGDIJEADSJ43B/graph.json","fetch_events":"https://pith.science/api/pith-number/TKL6EN2VWPKMLCGDIJEADSJ43B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B/action/storage_attestation","attest_author":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B/action/author_attestation","sign_citation":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B/action/citation_signature","submit_replication":"https://pith.science/pith/TKL6EN2VWPKMLCGDIJEADSJ43B/action/replication_record"}},"created_at":"2026-06-11T01:09:49.749311+00:00","updated_at":"2026-06-11T01:09:49.749311+00:00"}