{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5B4VJRAJ2U6PUHLNS4V4YUPR5V","short_pith_number":"pith:5B4VJRAJ","schema_version":"1.0","canonical_sha256":"e87954c409d53cfa1d6d972bcc51f1ed4753b5439dc516284698a1f8bea16f78","source":{"kind":"arxiv","id":"2310.01260","version":1},"attestation_state":"computed","paper":{"title":"SPELL: Semantic Prompt Evolution based on a LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kai Wu, Yujian Betterest Li","submitted_at":"2023-10-02T14:51:16Z","abstract_excerpt":"Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks the fluency or could not globally adjust a prompt. Since large language models (LLMs) have powerful ability of generating coherent texts token by token, can we utilize LLMs for improving prompts? Based on this motivation, in this paper, considering a trained LLM as a text generator, we attempt to design a black-box evolution algorithm for automatically opti"},"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":"2310.01260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-02T14:51:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ff40a0803935ba8dea3113065878f3456cb60d9ed181d4efdbd0b18b4bde9e0","abstract_canon_sha256":"778a7ba2219662c7190cd3b276265dc51a1db858115dfb83ca6396a34548d98a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:24.720987Z","signature_b64":"8khfA7gVnqNhTFYhmIONhdchiaCiln+NmoXzIBoSteX1KmFmvYsYWlzLwV/0yNRWKUpaERU4FW1cJuc6bY3cCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e87954c409d53cfa1d6d972bcc51f1ed4753b5439dc516284698a1f8bea16f78","last_reissued_at":"2026-07-05T06:56:24.720589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:24.720589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPELL: Semantic Prompt Evolution based on a LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kai Wu, Yujian Betterest Li","submitted_at":"2023-10-02T14:51:16Z","abstract_excerpt":"Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks the fluency or could not globally adjust a prompt. Since large language models (LLMs) have powerful ability of generating coherent texts token by token, can we utilize LLMs for improving prompts? Based on this motivation, in this paper, considering a trained LLM as a text generator, we attempt to design a black-box evolution algorithm for automatically opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01260","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/2310.01260/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":"2310.01260","created_at":"2026-07-05T06:56:24.720645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01260v1","created_at":"2026-07-05T06:56:24.720645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01260","created_at":"2026-07-05T06:56:24.720645+00:00"},{"alias_kind":"pith_short_12","alias_value":"5B4VJRAJ2U6P","created_at":"2026-07-05T06:56:24.720645+00:00"},{"alias_kind":"pith_short_16","alias_value":"5B4VJRAJ2U6PUHLN","created_at":"2026-07-05T06:56:24.720645+00:00"},{"alias_kind":"pith_short_8","alias_value":"5B4VJRAJ","created_at":"2026-07-05T06:56:24.720645+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17298","citing_title":"Prompting in the Wild: An Empirical Study of Prompt Evolution in Software Repositories","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V","json":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V.json","graph_json":"https://pith.science/api/pith-number/5B4VJRAJ2U6PUHLNS4V4YUPR5V/graph.json","events_json":"https://pith.science/api/pith-number/5B4VJRAJ2U6PUHLNS4V4YUPR5V/events.json","paper":"https://pith.science/paper/5B4VJRAJ"},"agent_actions":{"view_html":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V","download_json":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V.json","view_paper":"https://pith.science/paper/5B4VJRAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01260&json=true","fetch_graph":"https://pith.science/api/pith-number/5B4VJRAJ2U6PUHLNS4V4YUPR5V/graph.json","fetch_events":"https://pith.science/api/pith-number/5B4VJRAJ2U6PUHLNS4V4YUPR5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V/action/storage_attestation","attest_author":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V/action/author_attestation","sign_citation":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V/action/citation_signature","submit_replication":"https://pith.science/pith/5B4VJRAJ2U6PUHLNS4V4YUPR5V/action/replication_record"}},"created_at":"2026-07-05T06:56:24.720645+00:00","updated_at":"2026-07-05T06:56:24.720645+00:00"}