{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M4S4SU6WLXW72RTFN4DQAV2MS6","short_pith_number":"pith:M4S4SU6W","schema_version":"1.0","canonical_sha256":"6725c953d65dedfd46656f0700574c978efc62fedc71aed4fac24dec81af2043","source":{"kind":"arxiv","id":"2407.12865","version":1},"attestation_state":"computed","paper":{"title":"GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek Austin, Elliott Chartock","submitted_at":"2024-07-12T19:11:21Z","abstract_excerpt":"Prompt engineering for large language models (LLMs) is often a manual time-intensive process that involves generating, evaluating, and refining prompts iteratively to ensure high-quality outputs. While there has been work on automating prompt engineering, the solutions generally are either tuned to specific tasks with given answers or are quite costly. We introduce GRAD-SUM, a scalable and flexible method for automatic prompt engineering that builds on gradient-based optimization techniques. Our approach incorporates user-defined task descriptions and evaluation criteria, and features a novel "},"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":"2407.12865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-12T19:11:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55d7cd8a0b04becdba402c651111a8f57aba9e1ada91b3868ee4b574c54344cd","abstract_canon_sha256":"27e3398d93b65c5e32a611bbbbde181ff3dfd4cf51ce912b993acf4a954019cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:12.784858Z","signature_b64":"6esP38yHzv2h80zAL3IOue6Pp4iEkw7UbGYP0sstNGINAHXuWdy+8am1iH0SFyc4M1OeQ0jbXmd90LNwdKf5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6725c953d65dedfd46656f0700574c978efc62fedc71aed4fac24dec81af2043","last_reissued_at":"2026-07-05T08:45:12.784395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:12.784395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Derek Austin, Elliott Chartock","submitted_at":"2024-07-12T19:11:21Z","abstract_excerpt":"Prompt engineering for large language models (LLMs) is often a manual time-intensive process that involves generating, evaluating, and refining prompts iteratively to ensure high-quality outputs. While there has been work on automating prompt engineering, the solutions generally are either tuned to specific tasks with given answers or are quite costly. We introduce GRAD-SUM, a scalable and flexible method for automatic prompt engineering that builds on gradient-based optimization techniques. Our approach incorporates user-defined task descriptions and evaluation criteria, and features a novel "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12865","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/2407.12865/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":"2407.12865","created_at":"2026-07-05T08:45:12.784451+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12865v1","created_at":"2026-07-05T08:45:12.784451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12865","created_at":"2026-07-05T08:45:12.784451+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4S4SU6WLXW7","created_at":"2026-07-05T08:45:12.784451+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4S4SU6WLXW72RTF","created_at":"2026-07-05T08:45:12.784451+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4S4SU6W","created_at":"2026-07-05T08:45:12.784451+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6","json":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6.json","graph_json":"https://pith.science/api/pith-number/M4S4SU6WLXW72RTFN4DQAV2MS6/graph.json","events_json":"https://pith.science/api/pith-number/M4S4SU6WLXW72RTFN4DQAV2MS6/events.json","paper":"https://pith.science/paper/M4S4SU6W"},"agent_actions":{"view_html":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6","download_json":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6.json","view_paper":"https://pith.science/paper/M4S4SU6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12865&json=true","fetch_graph":"https://pith.science/api/pith-number/M4S4SU6WLXW72RTFN4DQAV2MS6/graph.json","fetch_events":"https://pith.science/api/pith-number/M4S4SU6WLXW72RTFN4DQAV2MS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/action/storage_attestation","attest_author":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/action/author_attestation","sign_citation":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/action/citation_signature","submit_replication":"https://pith.science/pith/M4S4SU6WLXW72RTFN4DQAV2MS6/action/replication_record"}},"created_at":"2026-07-05T08:45:12.784451+00:00","updated_at":"2026-07-05T08:45:12.784451+00:00"}