{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CX6UHTFDYIRRNCOQHY7WTG3ZNH","short_pith_number":"pith:CX6UHTFD","schema_version":"1.0","canonical_sha256":"15fd43cca3c2231689d03e3f699b7969d6a830cda76fec67bf405e78e8df7121","source":{"kind":"arxiv","id":"2502.18746","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bradley A. Malin, Damien Lopez, Hao Sun, Jiaxin Zhang, Kamalika Das, Sricharan Kumar, Wendi Cui, Zhuohang Li","submitted_at":"2025-02-26T01:42:08Z","abstract_excerpt":"Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central to guiding model outputs. While manual methods can be effective, they typically rely on intuition and do not automatically refine prompts over time. In contrast, automatic prompt optimization employing heuristic-based search algorithms can systematically explore and improve prompts with minimal human oversight. This survey proposes a comprehensive taxonomy of these methods, categorizing them by where optimization occu"},"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":"2502.18746","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T01:42:08Z","cross_cats_sorted":[],"title_canon_sha256":"cf2673b6da0a5eb7d390de94a085b95bae420052995d0e4527ae37f07a2f13f5","abstract_canon_sha256":"d572a1a7390092d5caa86df426e60c2d3a49b61506987001a3e24490f6cd88d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:53.788827Z","signature_b64":"gIz56LMcJ9YCI5vvY/0ZXmJKzFPRzCu3ICtRbWg0Mn1LQoRpqYjxWbDUBsrU81YmYJU+yKoYca9t0fZGjM6MCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15fd43cca3c2231689d03e3f699b7969d6a830cda76fec67bf405e78e8df7121","last_reissued_at":"2026-07-05T11:35:53.788297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:53.788297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Automatic Prompt Optimization with Instruction-focused Heuristic-based Search Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bradley A. Malin, Damien Lopez, Hao Sun, Jiaxin Zhang, Kamalika Das, Sricharan Kumar, Wendi Cui, Zhuohang Li","submitted_at":"2025-02-26T01:42:08Z","abstract_excerpt":"Recent advances in Large Language Models have led to remarkable achievements across a variety of Natural Language Processing tasks, making prompt engineering increasingly central to guiding model outputs. While manual methods can be effective, they typically rely on intuition and do not automatically refine prompts over time. In contrast, automatic prompt optimization employing heuristic-based search algorithms can systematically explore and improve prompts with minimal human oversight. This survey proposes a comprehensive taxonomy of these methods, categorizing them by where optimization occu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18746","kind":"arxiv","version":2},"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/2502.18746/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":"2502.18746","created_at":"2026-07-05T11:35:53.788366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18746v2","created_at":"2026-07-05T11:35:53.788366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18746","created_at":"2026-07-05T11:35:53.788366+00:00"},{"alias_kind":"pith_short_12","alias_value":"CX6UHTFDYIRR","created_at":"2026-07-05T11:35:53.788366+00:00"},{"alias_kind":"pith_short_16","alias_value":"CX6UHTFDYIRRNCOQ","created_at":"2026-07-05T11:35:53.788366+00:00"},{"alias_kind":"pith_short_8","alias_value":"CX6UHTFD","created_at":"2026-07-05T11:35:53.788366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04221","citing_title":"Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04221","citing_title":"Self-Prompting Small Language Models for Privacy-Sensitive Clinical Information Extraction","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH","json":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH.json","graph_json":"https://pith.science/api/pith-number/CX6UHTFDYIRRNCOQHY7WTG3ZNH/graph.json","events_json":"https://pith.science/api/pith-number/CX6UHTFDYIRRNCOQHY7WTG3ZNH/events.json","paper":"https://pith.science/paper/CX6UHTFD"},"agent_actions":{"view_html":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH","download_json":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH.json","view_paper":"https://pith.science/paper/CX6UHTFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18746&json=true","fetch_graph":"https://pith.science/api/pith-number/CX6UHTFDYIRRNCOQHY7WTG3ZNH/graph.json","fetch_events":"https://pith.science/api/pith-number/CX6UHTFDYIRRNCOQHY7WTG3ZNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH/action/storage_attestation","attest_author":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH/action/author_attestation","sign_citation":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH/action/citation_signature","submit_replication":"https://pith.science/pith/CX6UHTFDYIRRNCOQHY7WTG3ZNH/action/replication_record"}},"created_at":"2026-07-05T11:35:53.788366+00:00","updated_at":"2026-07-05T11:35:53.788366+00:00"}