{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N5GVS7EP7BQQI2KZ7UCPVWJTAT","short_pith_number":"pith:N5GVS7EP","schema_version":"1.0","canonical_sha256":"6f4d597c8ff861046959fd04fad93304e0f1cdbc3716cf268c3eba485e9cad80","source":{"kind":"arxiv","id":"2501.06689","version":3},"attestation_state":"computed","paper":{"title":"TAPO: Task-Referenced Adaptation for Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pengyue Jia, Weibo Zhou, Weirui Wang, Wenxin Luo, Xiangyu Zhao, Xiaopeng Li","submitted_at":"2025-01-12T02:43:59Z","abstract_excerpt":"Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time-consuming and laborious nature of manual prompt design. However, much of the existing work in APO overlooks task-specific characteristics, resulting in prompts that lack domain specificity and are not well-suited for task-specific optimization. In this paper, we introduce TAPO, a multitask-aware prompt optimization framework composed of three key modules. First, a task-aware metric selection module is proposed to en"},"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":"2501.06689","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-12T02:43:59Z","cross_cats_sorted":[],"title_canon_sha256":"3e7949b86cd0b400d6eb981f6ac1d282e76a9d56cf48f2758edb7a367aae81a9","abstract_canon_sha256":"d6ea6bfb4212c8abddf39baacc7c7819ed3596f37e5a8e845f25fc288ce696c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:18.557437Z","signature_b64":"0xml3S3G6/RRCi93pKLDAt2I/ll2Iiz5TzJhMM+PI9JZ0hImmjg6RGiTOMpHTBf7403YSZFFK4sDzzss9OYUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f4d597c8ff861046959fd04fad93304e0f1cdbc3716cf268c3eba485e9cad80","last_reissued_at":"2026-07-05T10:20:18.556960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:18.556960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAPO: Task-Referenced Adaptation for Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pengyue Jia, Weibo Zhou, Weirui Wang, Wenxin Luo, Xiangyu Zhao, Xiaopeng Li","submitted_at":"2025-01-12T02:43:59Z","abstract_excerpt":"Prompt engineering can significantly improve the performance of large language models (LLMs), with automated prompt optimization (APO) gaining significant attention due to the time-consuming and laborious nature of manual prompt design. However, much of the existing work in APO overlooks task-specific characteristics, resulting in prompts that lack domain specificity and are not well-suited for task-specific optimization. In this paper, we introduce TAPO, a multitask-aware prompt optimization framework composed of three key modules. First, a task-aware metric selection module is proposed to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06689","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/2501.06689/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":"2501.06689","created_at":"2026-07-05T10:20:18.557019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06689v3","created_at":"2026-07-05T10:20:18.557019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06689","created_at":"2026-07-05T10:20:18.557019+00:00"},{"alias_kind":"pith_short_12","alias_value":"N5GVS7EP7BQQ","created_at":"2026-07-05T10:20:18.557019+00:00"},{"alias_kind":"pith_short_16","alias_value":"N5GVS7EP7BQQI2KZ","created_at":"2026-07-05T10:20:18.557019+00:00"},{"alias_kind":"pith_short_8","alias_value":"N5GVS7EP","created_at":"2026-07-05T10:20:18.557019+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/N5GVS7EP7BQQI2KZ7UCPVWJTAT","json":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT.json","graph_json":"https://pith.science/api/pith-number/N5GVS7EP7BQQI2KZ7UCPVWJTAT/graph.json","events_json":"https://pith.science/api/pith-number/N5GVS7EP7BQQI2KZ7UCPVWJTAT/events.json","paper":"https://pith.science/paper/N5GVS7EP"},"agent_actions":{"view_html":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT","download_json":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT.json","view_paper":"https://pith.science/paper/N5GVS7EP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06689&json=true","fetch_graph":"https://pith.science/api/pith-number/N5GVS7EP7BQQI2KZ7UCPVWJTAT/graph.json","fetch_events":"https://pith.science/api/pith-number/N5GVS7EP7BQQI2KZ7UCPVWJTAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT/action/storage_attestation","attest_author":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT/action/author_attestation","sign_citation":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT/action/citation_signature","submit_replication":"https://pith.science/pith/N5GVS7EP7BQQI2KZ7UCPVWJTAT/action/replication_record"}},"created_at":"2026-07-05T10:20:18.557019+00:00","updated_at":"2026-07-05T10:20:18.557019+00:00"}