{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:76ZQVCYKPSRHMBZQBUUK224ERY","short_pith_number":"pith:76ZQVCYK","schema_version":"1.0","canonical_sha256":"ffb30a8b0a7ca27607300d28ad6b848e07025d36d95f2a742de76e3c5697a6a9","source":{"kind":"arxiv","id":"2412.12644","version":2},"attestation_state":"computed","paper":{"title":"iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiahui Li, Roman Klinger","submitted_at":"2024-12-17T08:09:15Z","abstract_excerpt":"Prompt engineering has made significant contributions to the era of large language models, yet its effectiveness depends on the skills of a prompt author. This paper introduces $\\textit{iPrOp}$, a novel interactive prompt optimization approach, to bridge manual prompt engineering and automatic prompt optimization while offering users the flexibility to assess evolving prompts. We aim to provide users with task-specific guidance to enhance human engagement in the optimization process, which is structured through prompt variations, informative instances, predictions generated by large language m"},"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":"2412.12644","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T08:09:15Z","cross_cats_sorted":[],"title_canon_sha256":"8cde1c5dc537d1f717c057be2efda3ab5fdf777625332dfc9ed5b1d2a92de99c","abstract_canon_sha256":"12393d799a82c27ab4bea7ef53bc39c41d544499083028ed695a43f5005206e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:12.954508Z","signature_b64":"yitsRapbhSbUZXLCrNIsrJF9uda4d+XP/JzR6lM4F/hrUln5JnrPa2XfV6zbweiBwNBwZOIV3d2ljy3N86WuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffb30a8b0a7ca27607300d28ad6b848e07025d36d95f2a742de76e3c5697a6a9","last_reissued_at":"2026-07-05T11:28:12.953980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:12.953980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiahui Li, Roman Klinger","submitted_at":"2024-12-17T08:09:15Z","abstract_excerpt":"Prompt engineering has made significant contributions to the era of large language models, yet its effectiveness depends on the skills of a prompt author. This paper introduces $\\textit{iPrOp}$, a novel interactive prompt optimization approach, to bridge manual prompt engineering and automatic prompt optimization while offering users the flexibility to assess evolving prompts. We aim to provide users with task-specific guidance to enhance human engagement in the optimization process, which is structured through prompt variations, informative instances, predictions generated by large language m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12644","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/2412.12644/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":"2412.12644","created_at":"2026-07-05T11:28:12.954046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12644v2","created_at":"2026-07-05T11:28:12.954046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12644","created_at":"2026-07-05T11:28:12.954046+00:00"},{"alias_kind":"pith_short_12","alias_value":"76ZQVCYKPSRH","created_at":"2026-07-05T11:28:12.954046+00:00"},{"alias_kind":"pith_short_16","alias_value":"76ZQVCYKPSRHMBZQ","created_at":"2026-07-05T11:28:12.954046+00:00"},{"alias_kind":"pith_short_8","alias_value":"76ZQVCYK","created_at":"2026-07-05T11:28:12.954046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19114","citing_title":"OOPrompt: Reifying Intents into Structured Artifacts for Modular and Iterative Prompting","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY","json":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY.json","graph_json":"https://pith.science/api/pith-number/76ZQVCYKPSRHMBZQBUUK224ERY/graph.json","events_json":"https://pith.science/api/pith-number/76ZQVCYKPSRHMBZQBUUK224ERY/events.json","paper":"https://pith.science/paper/76ZQVCYK"},"agent_actions":{"view_html":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY","download_json":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY.json","view_paper":"https://pith.science/paper/76ZQVCYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12644&json=true","fetch_graph":"https://pith.science/api/pith-number/76ZQVCYKPSRHMBZQBUUK224ERY/graph.json","fetch_events":"https://pith.science/api/pith-number/76ZQVCYKPSRHMBZQBUUK224ERY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY/action/storage_attestation","attest_author":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY/action/author_attestation","sign_citation":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY/action/citation_signature","submit_replication":"https://pith.science/pith/76ZQVCYKPSRHMBZQBUUK224ERY/action/replication_record"}},"created_at":"2026-07-05T11:28:12.954046+00:00","updated_at":"2026-07-05T11:28:12.954046+00:00"}