{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZEHR4M57HLIIHAU5H67XKPU7KA","short_pith_number":"pith:ZEHR4M57","schema_version":"1.0","canonical_sha256":"c90f1e33bf3ad083829d3fbf753e9f5033e4e9fbb7b11d6e57f897cbdecbcac0","source":{"kind":"arxiv","id":"2607.14105","version":1},"attestation_state":"computed","paper":{"title":"Automatically Evolving Prompt Guidelines for Task-Specific Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cedric Richter, Mike Papadakis, Salah Ghamizi","submitted_at":"2026-05-07T15:50:42Z","abstract_excerpt":"For Large Language Models to reliably answer user queries, users must clearly specify requirements, context, and constraints. In practice, however, user queries are often underspecified, forcing models to infer unstated assumptions that may misalign with the actual user intent. Existing prompt engineering guidelines aim to mitigate this issue, they are typically generic and task-agnostic, limiting their practical utility. Additionally, existing guidelines are formed manually and in a non-systematic way. To this end, we study prompt guideline optimization: the problem of automatically generatin"},"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":"2607.14105","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-07T15:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"897825db0ee217e29ac41632ea737335e0b4ea95222bce7d7e711a8a6caffb3c","abstract_canon_sha256":"1bd8e476b0125d7587c0f33878946b2fe4a5ea454dde2e6ea45f2b0a86efb3af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:52.324155Z","signature_b64":"MUfVXCkMNOpt7+5ht/gG/4EEQ5rCtUZmOy+IkED0QtUZ9xWiXzFLj/oe17meyPfQ/BcuyuqjV2V50HOudTzXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c90f1e33bf3ad083829d3fbf753e9f5033e4e9fbb7b11d6e57f897cbdecbcac0","last_reissued_at":"2026-07-17T00:20:52.323301Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:52.323301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatically Evolving Prompt Guidelines for Task-Specific Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cedric Richter, Mike Papadakis, Salah Ghamizi","submitted_at":"2026-05-07T15:50:42Z","abstract_excerpt":"For Large Language Models to reliably answer user queries, users must clearly specify requirements, context, and constraints. In practice, however, user queries are often underspecified, forcing models to infer unstated assumptions that may misalign with the actual user intent. Existing prompt engineering guidelines aim to mitigate this issue, they are typically generic and task-agnostic, limiting their practical utility. Additionally, existing guidelines are formed manually and in a non-systematic way. To this end, we study prompt guideline optimization: the problem of automatically generatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14105","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/2607.14105/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":"2607.14105","created_at":"2026-07-17T00:20:52.323761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14105v1","created_at":"2026-07-17T00:20:52.323761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14105","created_at":"2026-07-17T00:20:52.323761+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEHR4M57HLII","created_at":"2026-07-17T00:20:52.323761+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEHR4M57HLIIHAU5","created_at":"2026-07-17T00:20:52.323761+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEHR4M57","created_at":"2026-07-17T00:20:52.323761+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/ZEHR4M57HLIIHAU5H67XKPU7KA","json":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA.json","graph_json":"https://pith.science/api/pith-number/ZEHR4M57HLIIHAU5H67XKPU7KA/graph.json","events_json":"https://pith.science/api/pith-number/ZEHR4M57HLIIHAU5H67XKPU7KA/events.json","paper":"https://pith.science/paper/ZEHR4M57"},"agent_actions":{"view_html":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA","download_json":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA.json","view_paper":"https://pith.science/paper/ZEHR4M57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14105&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEHR4M57HLIIHAU5H67XKPU7KA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEHR4M57HLIIHAU5H67XKPU7KA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA/action/storage_attestation","attest_author":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA/action/author_attestation","sign_citation":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA/action/citation_signature","submit_replication":"https://pith.science/pith/ZEHR4M57HLIIHAU5H67XKPU7KA/action/replication_record"}},"created_at":"2026-07-17T00:20:52.323761+00:00","updated_at":"2026-07-17T00:20:52.323761+00:00"}