{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4OQV5DUC2UYJ4QDFVQC5LWKHAJ","short_pith_number":"pith:4OQV5DUC","schema_version":"1.0","canonical_sha256":"e3a15e8e82d5309e4065ac05d5d947026d2f7397ce0cd6b6da8161119cdab2ef","source":{"kind":"arxiv","id":"2407.00256","version":1},"attestation_state":"computed","paper":{"title":"One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Cho-Jui Hsieh, Minhao Cheng, Ruochen Wang, Sohyun An, Sung Ju Hwang, Tianyi Zhou","submitted_at":"2024-06-28T23:05:08Z","abstract_excerpt":"Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and in-context demos. Since this ability sensitively depends on the quality of prompts, various methods have been explored to automate the instruction design. While these methods demonstrated promising results, they also restricted the searched prompt to one instruction. Such simplification significantly limits their capacity, as a single demo-free instruction might not be able to cover the entire complex problem space of the targeted task. To alleviate this issue, we"},"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":"2407.00256","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-28T23:05:08Z","cross_cats_sorted":["cs.CL","cs.LG","stat.ML"],"title_canon_sha256":"bee8b8973de4edd7641c3eab8dd44a1540db71f83df97b8cd3225e9998b06532","abstract_canon_sha256":"02143a38e000c473aebb83d13ab4818859bacf7a1115c1e89653c51ba8174b52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:16.731339Z","signature_b64":"5RhtV0qslpKJ9gQWc6MiS8rWH5d/QBCY8o2sIzpAkwecgovZ8QiDibxiZysJorZQ0jAQiEFNf6lSXL7ZFDlHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3a15e8e82d5309e4065ac05d5d947026d2f7397ce0cd6b6da8161119cdab2ef","last_reissued_at":"2026-07-05T08:38:16.730898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:16.730898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Cho-Jui Hsieh, Minhao Cheng, Ruochen Wang, Sohyun An, Sung Ju Hwang, Tianyi Zhou","submitted_at":"2024-06-28T23:05:08Z","abstract_excerpt":"Large Language Models (LLMs) exhibit strong generalization capabilities to novel tasks when prompted with language instructions and in-context demos. Since this ability sensitively depends on the quality of prompts, various methods have been explored to automate the instruction design. While these methods demonstrated promising results, they also restricted the searched prompt to one instruction. Such simplification significantly limits their capacity, as a single demo-free instruction might not be able to cover the entire complex problem space of the targeted task. To alleviate this issue, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00256","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/2407.00256/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":"2407.00256","created_at":"2026-07-05T08:38:16.730954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00256v1","created_at":"2026-07-05T08:38:16.730954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00256","created_at":"2026-07-05T08:38:16.730954+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OQV5DUC2UYJ","created_at":"2026-07-05T08:38:16.730954+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OQV5DUC2UYJ4QDF","created_at":"2026-07-05T08:38:16.730954+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OQV5DUC","created_at":"2026-07-05T08:38:16.730954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24004","citing_title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00427","citing_title":"BT-APE: A Computationally Light Backtracking Approach to Automatic Prompt Engineering for Requirements Classification","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24004","citing_title":"Towards Spec Learning: Inference-Time Alignment from Preference Pairs","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17577","citing_title":"TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ","json":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ.json","graph_json":"https://pith.science/api/pith-number/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/graph.json","events_json":"https://pith.science/api/pith-number/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/events.json","paper":"https://pith.science/paper/4OQV5DUC"},"agent_actions":{"view_html":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ","download_json":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ.json","view_paper":"https://pith.science/paper/4OQV5DUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00256&json=true","fetch_graph":"https://pith.science/api/pith-number/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/action/storage_attestation","attest_author":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/action/author_attestation","sign_citation":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/action/citation_signature","submit_replication":"https://pith.science/pith/4OQV5DUC2UYJ4QDFVQC5LWKHAJ/action/replication_record"}},"created_at":"2026-07-05T08:38:16.730954+00:00","updated_at":"2026-07-05T08:38:16.730954+00:00"}