{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FGEJZKUEHEBOMJCG7XGMXFETWZ","short_pith_number":"pith:FGEJZKUE","schema_version":"1.0","canonical_sha256":"29889caa843902e62446fdcccb9493b658e4b07b7fca022a55938a0876ca7642","source":{"kind":"arxiv","id":"2412.03092","version":2},"attestation_state":"computed","paper":{"title":"REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haibo Jin, Haohan Wang, Leyang Hu, Liying Kang, Man Luo, Peiyan Zhang, Xinnuo Li, Yangqiu Song","submitted_at":"2024-12-04T07:44:35Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems for specific tasks remains challenging, often requiring manual interventions like prompt engineering and hyperparameter tuning. Existing automatic optimization methods, such as textual feedback-based techniques (e.g., TextGrad), tend to focus on immediate feedback, analogous to using immediate derivatives in traditional numerical gradient descent. However, r"},"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":"2412.03092","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T07:44:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"50593ca3b9bd71b48b76ce986144b3da5c99885e2d704a72085291e19f7c9f6e","abstract_canon_sha256":"215e7cf95be797b5f4d8b361434ddd3e1b302262fff55d5c3d699272ae8da8ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:20.374487Z","signature_b64":"fcA+osfYGSi1G4wUeRqmpUE/WxgAb2OWhS6OHGX7VmddFZ3SHT+gZqRZ3UKSRbauGw14/qzEprPOkt/6i9AlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29889caa843902e62446fdcccb9493b658e4b07b7fca022a55938a0876ca7642","last_reissued_at":"2026-07-05T11:23:20.373927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:20.373927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haibo Jin, Haohan Wang, Leyang Hu, Liying Kang, Man Luo, Peiyan Zhang, Xinnuo Li, Yangqiu Song","submitted_at":"2024-12-04T07:44:35Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems for specific tasks remains challenging, often requiring manual interventions like prompt engineering and hyperparameter tuning. Existing automatic optimization methods, such as textual feedback-based techniques (e.g., TextGrad), tend to focus on immediate feedback, analogous to using immediate derivatives in traditional numerical gradient descent. However, r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03092","kind":"arxiv","version":2},"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/2412.03092/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":"2412.03092","created_at":"2026-07-05T11:23:20.374010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03092v2","created_at":"2026-07-05T11:23:20.374010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03092","created_at":"2026-07-05T11:23:20.374010+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGEJZKUEHEBO","created_at":"2026-07-05T11:23:20.374010+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGEJZKUEHEBOMJCG","created_at":"2026-07-05T11:23:20.374010+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGEJZKUE","created_at":"2026-07-05T11:23:20.374010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21318","citing_title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":180,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ","json":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ.json","graph_json":"https://pith.science/api/pith-number/FGEJZKUEHEBOMJCG7XGMXFETWZ/graph.json","events_json":"https://pith.science/api/pith-number/FGEJZKUEHEBOMJCG7XGMXFETWZ/events.json","paper":"https://pith.science/paper/FGEJZKUE"},"agent_actions":{"view_html":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ","download_json":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ.json","view_paper":"https://pith.science/paper/FGEJZKUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03092&json=true","fetch_graph":"https://pith.science/api/pith-number/FGEJZKUEHEBOMJCG7XGMXFETWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FGEJZKUEHEBOMJCG7XGMXFETWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ/action/storage_attestation","attest_author":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ/action/author_attestation","sign_citation":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ/action/citation_signature","submit_replication":"https://pith.science/pith/FGEJZKUEHEBOMJCG7XGMXFETWZ/action/replication_record"}},"created_at":"2026-07-05T11:23:20.374010+00:00","updated_at":"2026-07-05T11:23:20.374010+00:00"}