{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7F2UNAP56VMQLJUFXAIWTOX6B5","short_pith_number":"pith:7F2UNAP5","schema_version":"1.0","canonical_sha256":"f9754681fdf55905a685b81169bafe0f4717b5b34700ee804273022237d4e77b","source":{"kind":"arxiv","id":"2507.14241","version":3},"attestation_state":"computed","paper":{"title":"Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Huan Wang, Jielin Qiu, Juntao Tan, Liangwei Yang, Ming Zhu, Rithesh Murthy, Shelby Heinecke, Silvio Savarese","submitted_at":"2025-07-17T18:18:20Z","abstract_excerpt":"Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms natural language task descriptions into high-quality prompts without requiring manual tuning or domain expertise. Promptomatix supports both a lightweight meta-prompt-based optimizer and a DSPy-powered compiler, with modular design enabling future extension to more advanced frameworks. The system analyzes user intent, generates synthetic training data, sele"},"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":"2507.14241","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T18:18:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22a0ca649b9b0c7bffb8a7562b5611cc988d1fc0463acd99fc65e25a5f99900c","abstract_canon_sha256":"cdf7bf8375bee4b0ba554a8d007d3e5a8f26f08d9e3f161f9d85c4b9d236f301"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:55.267877Z","signature_b64":"4qzgT8yCDdr8JCmHxBd4Mjm2fNyzt+nzFeldTyeANq+wwt9XgR3IgEbm2jegpVY2qLzwf5FlzZAy5B0S2uxkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9754681fdf55905a685b81169bafe0f4717b5b34700ee804273022237d4e77b","last_reissued_at":"2026-07-05T11:42:55.267383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:55.267383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Huan Wang, Jielin Qiu, Juntao Tan, Liangwei Yang, Ming Zhu, Rithesh Murthy, Shelby Heinecke, Silvio Savarese","submitted_at":"2025-07-17T18:18:20Z","abstract_excerpt":"Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms natural language task descriptions into high-quality prompts without requiring manual tuning or domain expertise. Promptomatix supports both a lightweight meta-prompt-based optimizer and a DSPy-powered compiler, with modular design enabling future extension to more advanced frameworks. The system analyzes user intent, generates synthetic training data, sele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14241","kind":"arxiv","version":3},"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/2507.14241/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":"2507.14241","created_at":"2026-07-05T11:42:55.267446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14241v3","created_at":"2026-07-05T11:42:55.267446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14241","created_at":"2026-07-05T11:42:55.267446+00:00"},{"alias_kind":"pith_short_12","alias_value":"7F2UNAP56VMQ","created_at":"2026-07-05T11:42:55.267446+00:00"},{"alias_kind":"pith_short_16","alias_value":"7F2UNAP56VMQLJUF","created_at":"2026-07-05T11:42:55.267446+00:00"},{"alias_kind":"pith_short_8","alias_value":"7F2UNAP5","created_at":"2026-07-05T11:42:55.267446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14197","citing_title":"The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5","json":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5.json","graph_json":"https://pith.science/api/pith-number/7F2UNAP56VMQLJUFXAIWTOX6B5/graph.json","events_json":"https://pith.science/api/pith-number/7F2UNAP56VMQLJUFXAIWTOX6B5/events.json","paper":"https://pith.science/paper/7F2UNAP5"},"agent_actions":{"view_html":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5","download_json":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5.json","view_paper":"https://pith.science/paper/7F2UNAP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14241&json=true","fetch_graph":"https://pith.science/api/pith-number/7F2UNAP56VMQLJUFXAIWTOX6B5/graph.json","fetch_events":"https://pith.science/api/pith-number/7F2UNAP56VMQLJUFXAIWTOX6B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5/action/storage_attestation","attest_author":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5/action/author_attestation","sign_citation":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5/action/citation_signature","submit_replication":"https://pith.science/pith/7F2UNAP56VMQLJUFXAIWTOX6B5/action/replication_record"}},"created_at":"2026-07-05T11:42:55.267446+00:00","updated_at":"2026-07-05T11:42:55.267446+00:00"}