{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LSHRHSSCFA6BHLU75QVTOZIZRY","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":"984f2d72f4566aad1cc93e04944489bd2712609024f8403e5140853db5209011","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T07:47:01Z","title_canon_sha256":"4d8c1f122051e5d3c3d200a55daa40843c91b9ce8f5895ebc5e3615d8876bc18"},"schema_version":"1.0","source":{"id":"2310.16427","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16427","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16427v2","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16427","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_12","alias_value":"LSHRHSSCFA6B","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_16","alias_value":"LSHRHSSCFA6BHLU7","created_at":"2026-07-05T07:21:28Z"},{"alias_kind":"pith_short_8","alias_value":"LSHRHSSC","created_at":"2026-07-05T07:21:28Z"}],"graph_snapshots":[{"event_id":"sha256:5de4064aae16bd25f46125eca0f24f3be6b460fd533274aa63721f0177bb2183","target":"graph","created_at":"2026-07-05T07:21:28Z","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/2310.16427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task. However, automating the generation of such expert-level prompts remains elusive. Existing prompt optimization methods tend to overlook the depth of domain knowledge and struggle to efficiently explore the vast space of expert-level prompts. Addressing this, we present PromptAgent, an optimization method that autonomously crafts prompts equival","authors_text":"Chenxi Li, Eric P. Xing, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Xinyuan Wang, Zhen Wang, Zhiting Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T07:47:01Z","title":"PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16427","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:bedbd7b7e55c99c57f656bfcee2b7973c53e72dcae166aa485811d22ff508185","target":"record","created_at":"2026-07-05T07:21:28Z","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":"984f2d72f4566aad1cc93e04944489bd2712609024f8403e5140853db5209011","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T07:47:01Z","title_canon_sha256":"4d8c1f122051e5d3c3d200a55daa40843c91b9ce8f5895ebc5e3615d8876bc18"},"schema_version":"1.0","source":{"id":"2310.16427","kind":"arxiv","version":2}},"canonical_sha256":"5c8f13ca42283c13ae9fec2b3765198e1f48621d1d4584dc68271adfe7aa082b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c8f13ca42283c13ae9fec2b3765198e1f48621d1d4584dc68271adfe7aa082b","first_computed_at":"2026-07-05T07:21:28.631211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:28.631211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TTnQLF766EiynY5an8NeHYWQ0eoTR5xjJFYVkQwbQQ22Q+BQZ0NZjq4uw7neZtbBOkPu1QmpFScwDZ/KVq30BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:28.631827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16427","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bedbd7b7e55c99c57f656bfcee2b7973c53e72dcae166aa485811d22ff508185","sha256:5de4064aae16bd25f46125eca0f24f3be6b460fd533274aa63721f0177bb2183"],"state_sha256":"4615eef2142660d7673aa2ef29cbeb48dc530a1c3e865d0109339ff926e2361e"}