{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O254DF26PAOFISF4DN37UAQR3D","short_pith_number":"pith:O254DF26","schema_version":"1.0","canonical_sha256":"76bbc1975e781c5448bc1b77fa0211d8f400bb8ef070527729e50ce03f822d18","source":{"kind":"arxiv","id":"2505.08303","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingyuan Yang, Rongjun Li, Yihang Wu, Zhan Xiao, Ziyu Zhou","submitted_at":"2025-05-13T07:26:56Z","abstract_excerpt":"Black-Box prompt optimization methods have emerged as a promising strategy for refining input prompts to better align large language models (LLMs), thereby enhancing their task performance. Although these methods have demonstrated encouraging results, most studies and experiments have primarily focused on smaller-scale models (e.g., 7B, 14B) or earlier versions (e.g., GPT-3.5) of LLMs. As the scale of LLMs continues to increase, such as with DeepSeek V3 (671B), it remains an open question whether these black-box optimization techniques will continue to yield significant performance improvement"},"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":"2505.08303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T07:26:56Z","cross_cats_sorted":[],"title_canon_sha256":"4c8ed5a0cc4b416486f126d7c2819c50f25de679c2a88fc4cd0ef61b630cd36b","abstract_canon_sha256":"07e61c5c2afee468662eb119d33ed7107cc4b133d984573af8ba573a1d69fa6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:28.467081Z","signature_b64":"QQpddgFAUYsgKBmh3/rd6JD6DP5gEhV0sRVdwVNBakgcj+bgBgntGW9qncaFBQbcV+3+AHD5sjWYaffkMoRLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76bbc1975e781c5448bc1b77fa0211d8f400bb8ef070527729e50ce03f822d18","last_reissued_at":"2026-07-05T11:02:28.466621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:28.466621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingyuan Yang, Rongjun Li, Yihang Wu, Zhan Xiao, Ziyu Zhou","submitted_at":"2025-05-13T07:26:56Z","abstract_excerpt":"Black-Box prompt optimization methods have emerged as a promising strategy for refining input prompts to better align large language models (LLMs), thereby enhancing their task performance. Although these methods have demonstrated encouraging results, most studies and experiments have primarily focused on smaller-scale models (e.g., 7B, 14B) or earlier versions (e.g., GPT-3.5) of LLMs. As the scale of LLMs continues to increase, such as with DeepSeek V3 (671B), it remains an open question whether these black-box optimization techniques will continue to yield significant performance improvement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08303","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/2505.08303/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":"2505.08303","created_at":"2026-07-05T11:02:28.466678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08303v1","created_at":"2026-07-05T11:02:28.466678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08303","created_at":"2026-07-05T11:02:28.466678+00:00"},{"alias_kind":"pith_short_12","alias_value":"O254DF26PAOF","created_at":"2026-07-05T11:02:28.466678+00:00"},{"alias_kind":"pith_short_16","alias_value":"O254DF26PAOFISF4","created_at":"2026-07-05T11:02:28.466678+00:00"},{"alias_kind":"pith_short_8","alias_value":"O254DF26","created_at":"2026-07-05T11:02:28.466678+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/O254DF26PAOFISF4DN37UAQR3D","json":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D.json","graph_json":"https://pith.science/api/pith-number/O254DF26PAOFISF4DN37UAQR3D/graph.json","events_json":"https://pith.science/api/pith-number/O254DF26PAOFISF4DN37UAQR3D/events.json","paper":"https://pith.science/paper/O254DF26"},"agent_actions":{"view_html":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D","download_json":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D.json","view_paper":"https://pith.science/paper/O254DF26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08303&json=true","fetch_graph":"https://pith.science/api/pith-number/O254DF26PAOFISF4DN37UAQR3D/graph.json","fetch_events":"https://pith.science/api/pith-number/O254DF26PAOFISF4DN37UAQR3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D/action/storage_attestation","attest_author":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D/action/author_attestation","sign_citation":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D/action/citation_signature","submit_replication":"https://pith.science/pith/O254DF26PAOFISF4DN37UAQR3D/action/replication_record"}},"created_at":"2026-07-05T11:02:28.466678+00:00","updated_at":"2026-07-05T11:02:28.466678+00:00"}