{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JMJ4VBHYFG7I456GCGLJIWGRRL","short_pith_number":"pith:JMJ4VBHY","schema_version":"1.0","canonical_sha256":"4b13ca84f829be8e77c611969458d18ad36ff2c5a4f35af97f62649e8454f30d","source":{"kind":"arxiv","id":"2310.12774","version":1},"attestation_state":"computed","paper":{"title":"Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Han Zhou, Ivan Vuli\\'c, Xingchen Wan","submitted_at":"2023-10-19T14:25:06Z","abstract_excerpt":"Prompt-based learning has been an effective paradigm for large pretrained language models (LLM), enabling few-shot or even zero-shot learning. Black-box prompt search has received growing interest recently for its distinctive properties of gradient-free optimization, proven particularly useful and powerful for model-as-a-service usage. However, the discrete nature and the complexity of combinatorial optimization hinder the efficiency of modern black-box approaches. Despite extensive research on search algorithms, the crucial aspect of search space design and optimization has been largely overl"},"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":"2310.12774","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T14:25:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9d09fbdeada7939d28cbc578afbf7058cfa8d188a84823ef8011f8d33a8ba78f","abstract_canon_sha256":"687c42c1848a46c71240f39184ccf282aadeeb8c563712e1716249571f37dd30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:42.663039Z","signature_b64":"ihFNaaWt/dq2o7HCWuOoyr9rIcNjzcllc4Ejhpo8l9lpLNNUzhefi+opluFTroOOh4VKFOrIPwaYKaHg6iDHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b13ca84f829be8e77c611969458d18ad36ff2c5a4f35af97f62649e8454f30d","last_reissued_at":"2026-07-05T07:02:42.662660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:42.662660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Han Zhou, Ivan Vuli\\'c, Xingchen Wan","submitted_at":"2023-10-19T14:25:06Z","abstract_excerpt":"Prompt-based learning has been an effective paradigm for large pretrained language models (LLM), enabling few-shot or even zero-shot learning. Black-box prompt search has received growing interest recently for its distinctive properties of gradient-free optimization, proven particularly useful and powerful for model-as-a-service usage. However, the discrete nature and the complexity of combinatorial optimization hinder the efficiency of modern black-box approaches. Despite extensive research on search algorithms, the crucial aspect of search space design and optimization has been largely overl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12774","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/2310.12774/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":"2310.12774","created_at":"2026-07-05T07:02:42.662723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12774v1","created_at":"2026-07-05T07:02:42.662723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12774","created_at":"2026-07-05T07:02:42.662723+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMJ4VBHYFG7I","created_at":"2026-07-05T07:02:42.662723+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMJ4VBHYFG7I456G","created_at":"2026-07-05T07:02:42.662723+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMJ4VBHY","created_at":"2026-07-05T07:02:42.662723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17700","citing_title":"The Evolution of Natural Language Processing: How Prompt Optimization and Language Models are Shaping the Future","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL","json":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL.json","graph_json":"https://pith.science/api/pith-number/JMJ4VBHYFG7I456GCGLJIWGRRL/graph.json","events_json":"https://pith.science/api/pith-number/JMJ4VBHYFG7I456GCGLJIWGRRL/events.json","paper":"https://pith.science/paper/JMJ4VBHY"},"agent_actions":{"view_html":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL","download_json":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL.json","view_paper":"https://pith.science/paper/JMJ4VBHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12774&json=true","fetch_graph":"https://pith.science/api/pith-number/JMJ4VBHYFG7I456GCGLJIWGRRL/graph.json","fetch_events":"https://pith.science/api/pith-number/JMJ4VBHYFG7I456GCGLJIWGRRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL/action/storage_attestation","attest_author":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL/action/author_attestation","sign_citation":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL/action/citation_signature","submit_replication":"https://pith.science/pith/JMJ4VBHYFG7I456GCGLJIWGRRL/action/replication_record"}},"created_at":"2026-07-05T07:02:42.662723+00:00","updated_at":"2026-07-05T07:02:42.662723+00:00"}