{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QTHJ7ZKZZU3ATAYC6PO5O6C5DR","short_pith_number":"pith:QTHJ7ZKZ","schema_version":"1.0","canonical_sha256":"84ce9fe559cd36098302f3ddd7785d1c5950052bb26177a48f0ada6a22d27502","source":{"kind":"arxiv","id":"2406.13443","version":2},"attestation_state":"computed","paper":{"title":"Dual-Phase Accelerated Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongming Gao, Fuli Feng, Junqi Zhang, Moxin Li, Muchen Yang, Yangyang Li, Yongle Li, Zijun Chen","submitted_at":"2024-06-19T11:08:56Z","abstract_excerpt":"Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of high-quality prompt initialization and the identification of effective optimization directions, thus resulting in substantial optimization steps to obtain satisfactory performance. In this light, we aim to accelerate prompt optimization process to tackle the challenge of low convergence rate. We propose a dual-phase approach which starts with generating high-q"},"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":"2406.13443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T11:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"cf69bc297756fb498be746c85fec3f42e70ef590f9f9fb310e3b082b5c8c6c3a","abstract_canon_sha256":"36897e2f4a7ed665127b012a795fd18419010975e2c7a00d1660b0cb64f3707d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:34.798129Z","signature_b64":"yn+q8FuwhZQO4nHr0Ly8Rcypg64/8EL84sRTOcImP3UActu4G4uCJhdsDcA4hTe30Xsw7dFnH2ycTjxdzoWqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ce9fe559cd36098302f3ddd7785d1c5950052bb26177a48f0ada6a22d27502","last_reissued_at":"2026-07-05T09:14:34.797631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:34.797631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Phase Accelerated Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongming Gao, Fuli Feng, Junqi Zhang, Moxin Li, Muchen Yang, Yangyang Li, Yongle Li, Zijun Chen","submitted_at":"2024-06-19T11:08:56Z","abstract_excerpt":"Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of high-quality prompt initialization and the identification of effective optimization directions, thus resulting in substantial optimization steps to obtain satisfactory performance. In this light, we aim to accelerate prompt optimization process to tackle the challenge of low convergence rate. We propose a dual-phase approach which starts with generating high-q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13443","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/2406.13443/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":"2406.13443","created_at":"2026-07-05T09:14:34.797689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13443v2","created_at":"2026-07-05T09:14:34.797689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13443","created_at":"2026-07-05T09:14:34.797689+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTHJ7ZKZZU3A","created_at":"2026-07-05T09:14:34.797689+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTHJ7ZKZZU3ATAYC","created_at":"2026-07-05T09:14:34.797689+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTHJ7ZKZ","created_at":"2026-07-05T09:14:34.797689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22803","citing_title":"Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR","json":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR.json","graph_json":"https://pith.science/api/pith-number/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/graph.json","events_json":"https://pith.science/api/pith-number/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/events.json","paper":"https://pith.science/paper/QTHJ7ZKZ"},"agent_actions":{"view_html":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR","download_json":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR.json","view_paper":"https://pith.science/paper/QTHJ7ZKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13443&json=true","fetch_graph":"https://pith.science/api/pith-number/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/graph.json","fetch_events":"https://pith.science/api/pith-number/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/action/storage_attestation","attest_author":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/action/author_attestation","sign_citation":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/action/citation_signature","submit_replication":"https://pith.science/pith/QTHJ7ZKZZU3ATAYC6PO5O6C5DR/action/replication_record"}},"created_at":"2026-07-05T09:14:34.797689+00:00","updated_at":"2026-07-05T09:14:34.797689+00:00"}