{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7IW5O6225PRJHL6YY2QTLWGNZO","short_pith_number":"pith:7IW5O622","schema_version":"1.0","canonical_sha256":"fa2dd77b5aebe293afd8c6a135d8cdcb9e1dc50d3c8129812762cf899cc9088e","source":{"kind":"arxiv","id":"2504.20355","version":1},"attestation_state":"computed","paper":{"title":"Local Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Vishal Chowdhary, Yash Jain","submitted_at":"2025-04-29T01:45:47Z","abstract_excerpt":"In recent years, the use of prompts to guide the output of Large Language Models have increased dramatically. However, even the best of experts struggle to choose the correct words to stitch up a prompt for the desired task. To solve this, LLM driven prompt optimization emerged as an important problem. Existing prompt optimization methods optimize a prompt globally, where in all the prompt tokens have to be optimized over a large vocabulary while solving a complex task. The large optimization space (tokens) leads to insufficient guidance for a better prompt. In this work, we introduce Local Pr"},"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":"2504.20355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-29T01:45:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2047787ee512d943ed62d13fa74e8d6ee3d704f82ce740146cfefd8e644124e4","abstract_canon_sha256":"51f5fc05873d060955413f7c761e416d3f2f2c40a9ab783dcdabcf1327764f4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:41.268417Z","signature_b64":"bzIpJmIHrBnhoDKlmQjHPU1mp7LCY/fRKKqdxfDh2xCiboD/Kz8qAuTQ2x9I8Zh45cZi+fKF5+q+eQ34HNMuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa2dd77b5aebe293afd8c6a135d8cdcb9e1dc50d3c8129812762cf899cc9088e","last_reissued_at":"2026-07-05T10:55:41.267986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:41.267986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Vishal Chowdhary, Yash Jain","submitted_at":"2025-04-29T01:45:47Z","abstract_excerpt":"In recent years, the use of prompts to guide the output of Large Language Models have increased dramatically. However, even the best of experts struggle to choose the correct words to stitch up a prompt for the desired task. To solve this, LLM driven prompt optimization emerged as an important problem. Existing prompt optimization methods optimize a prompt globally, where in all the prompt tokens have to be optimized over a large vocabulary while solving a complex task. The large optimization space (tokens) leads to insufficient guidance for a better prompt. In this work, we introduce Local Pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20355","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/2504.20355/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":"2504.20355","created_at":"2026-07-05T10:55:41.268040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20355v1","created_at":"2026-07-05T10:55:41.268040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20355","created_at":"2026-07-05T10:55:41.268040+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IW5O6225PRJ","created_at":"2026-07-05T10:55:41.268040+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IW5O6225PRJHL6Y","created_at":"2026-07-05T10:55:41.268040+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IW5O622","created_at":"2026-07-05T10:55:41.268040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20727","citing_title":"Supplement Generation Training for Enhancing Agentic Task Performance","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO","json":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO.json","graph_json":"https://pith.science/api/pith-number/7IW5O6225PRJHL6YY2QTLWGNZO/graph.json","events_json":"https://pith.science/api/pith-number/7IW5O6225PRJHL6YY2QTLWGNZO/events.json","paper":"https://pith.science/paper/7IW5O622"},"agent_actions":{"view_html":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO","download_json":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO.json","view_paper":"https://pith.science/paper/7IW5O622","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20355&json=true","fetch_graph":"https://pith.science/api/pith-number/7IW5O6225PRJHL6YY2QTLWGNZO/graph.json","fetch_events":"https://pith.science/api/pith-number/7IW5O6225PRJHL6YY2QTLWGNZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO/action/storage_attestation","attest_author":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO/action/author_attestation","sign_citation":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO/action/citation_signature","submit_replication":"https://pith.science/pith/7IW5O6225PRJHL6YY2QTLWGNZO/action/replication_record"}},"created_at":"2026-07-05T10:55:41.268040+00:00","updated_at":"2026-07-05T10:55:41.268040+00:00"}