{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VNWJHB6GSR47VPJHCTCDUPRJ7M","short_pith_number":"pith:VNWJHB6G","schema_version":"1.0","canonical_sha256":"ab6c9387c69479fabd2714c43a3e29fb0f6bda408b62613d22224a1309ba1d66","source":{"kind":"arxiv","id":"2504.14367","version":1},"attestation_state":"computed","paper":{"title":"Diverse Prompts: Illuminating the Prompt Space of Large Language Models with MAP-Elites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabriel Machado Santos, Marcelo Zanchetta do Nascimento, Rita Maria da Silva Julia","submitted_at":"2025-04-19T17:50:34Z","abstract_excerpt":"Prompt engineering is essential for optimizing large language models (LLMs), yet the link between prompt structures and task performance remains underexplored. This work introduces an evolutionary approach that combines context-free grammar (CFG) with the MAP-Elites algorithm to systematically explore the prompt space. Our method prioritizes quality and diversity, generating high-performing and structurally varied prompts while analyzing their alignment with diverse tasks by varying traits such as the number of examples (shots) and reasoning depth. By systematically mapping the phenotypic spac"},"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":"2504.14367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-19T17:50:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1003f668b97b00a375b2df038f81c2ef3f0b2e7bab42a23779838855b7f3d96e","abstract_canon_sha256":"ef516656d62a03750b8863cb1816fb73857ac554f2a70808ae2a8beb68144523"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:42.341848Z","signature_b64":"awsnzCZr7fJZUdGKuheT/lSoyNKxPMbeMEgxiO4X2A4miZ440c/xW1rFfbFY+L6EJt/sztVDSnsZU5ajdgyYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab6c9387c69479fabd2714c43a3e29fb0f6bda408b62613d22224a1309ba1d66","last_reissued_at":"2026-07-05T10:51:42.341331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:42.341331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse Prompts: Illuminating the Prompt Space of Large Language Models with MAP-Elites","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gabriel Machado Santos, Marcelo Zanchetta do Nascimento, Rita Maria da Silva Julia","submitted_at":"2025-04-19T17:50:34Z","abstract_excerpt":"Prompt engineering is essential for optimizing large language models (LLMs), yet the link between prompt structures and task performance remains underexplored. This work introduces an evolutionary approach that combines context-free grammar (CFG) with the MAP-Elites algorithm to systematically explore the prompt space. Our method prioritizes quality and diversity, generating high-performing and structurally varied prompts while analyzing their alignment with diverse tasks by varying traits such as the number of examples (shots) and reasoning depth. By systematically mapping the phenotypic spac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14367","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/2504.14367/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":"2504.14367","created_at":"2026-07-05T10:51:42.341394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14367v1","created_at":"2026-07-05T10:51:42.341394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14367","created_at":"2026-07-05T10:51:42.341394+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNWJHB6GSR47","created_at":"2026-07-05T10:51:42.341394+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNWJHB6GSR47VPJH","created_at":"2026-07-05T10:51:42.341394+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNWJHB6G","created_at":"2026-07-05T10:51:42.341394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07342","citing_title":"LLM-Guided Evolution for Medical Decision Pipelines","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M","json":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M.json","graph_json":"https://pith.science/api/pith-number/VNWJHB6GSR47VPJHCTCDUPRJ7M/graph.json","events_json":"https://pith.science/api/pith-number/VNWJHB6GSR47VPJHCTCDUPRJ7M/events.json","paper":"https://pith.science/paper/VNWJHB6G"},"agent_actions":{"view_html":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M","download_json":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M.json","view_paper":"https://pith.science/paper/VNWJHB6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14367&json=true","fetch_graph":"https://pith.science/api/pith-number/VNWJHB6GSR47VPJHCTCDUPRJ7M/graph.json","fetch_events":"https://pith.science/api/pith-number/VNWJHB6GSR47VPJHCTCDUPRJ7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M/action/storage_attestation","attest_author":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M/action/author_attestation","sign_citation":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M/action/citation_signature","submit_replication":"https://pith.science/pith/VNWJHB6GSR47VPJHCTCDUPRJ7M/action/replication_record"}},"created_at":"2026-07-05T10:51:42.341394+00:00","updated_at":"2026-07-05T10:51:42.341394+00:00"}