{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F2RXRY27XAQYDLZM5QRNQULUV5","short_pith_number":"pith:F2RXRY27","schema_version":"1.0","canonical_sha256":"2ea378e35fb82181af2cec22d85174af6cbbca9faebb7ccb2710728bcd8f5364","source":{"kind":"arxiv","id":"2606.30840","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Reflection for Iterative Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baofen Zheng, Benjamin H. Le, Derek Koh, Jiening Zhan, Jinghui Mo, Jingwei Wu, Kevin Bevis, Lauren Elizabeth Charney, Nathaniel C. Owen, Wenqiong Liu","submitted_at":"2026-06-29T19:16:07Z","abstract_excerpt":"LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation. Improving the prompts that control these agents is an optimization problem, but in applied IR settings it often looks less like blind search and more like debugging. Engineers need to know which behavior failed, which nearby behavior still worked, what distinguishes the two, and whether a prompt edit improves held-out quality without introducing regressions.\n  We present Contrastive Reflection, an iterative prompt-optimization framework"},"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":"2606.30840","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T19:16:07Z","cross_cats_sorted":[],"title_canon_sha256":"2e25da78c7f053156967d6fa6472720c2aa50d20187f2373c9085ca628740ad0","abstract_canon_sha256":"d89e6d4ed1186fd8efdd61f8223e87408a51f854544ace2b6f6e3dd56360d42d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:19.030683Z","signature_b64":"0RsqU4LQ/Cakbi6Ufp6EjQZGDCxkb13yb6v2XJwWXemU/98EDk3FmY4/umJJmFtLqN6RPZw76IGJAWoc6c36AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ea378e35fb82181af2cec22d85174af6cbbca9faebb7ccb2710728bcd8f5364","last_reissued_at":"2026-07-01T00:17:19.030269Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:19.030269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Reflection for Iterative Prompt Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baofen Zheng, Benjamin H. Le, Derek Koh, Jiening Zhan, Jinghui Mo, Jingwei Wu, Kevin Bevis, Lauren Elizabeth Charney, Nathaniel C. Owen, Wenqiong Liu","submitted_at":"2026-06-29T19:16:07Z","abstract_excerpt":"LLM agents are becoming central to information retrieval: they issue retrieval queries, synthesize answers, and increasingly serve as judges for IR evaluation. Improving the prompts that control these agents is an optimization problem, but in applied IR settings it often looks less like blind search and more like debugging. Engineers need to know which behavior failed, which nearby behavior still worked, what distinguishes the two, and whether a prompt edit improves held-out quality without introducing regressions.\n  We present Contrastive Reflection, an iterative prompt-optimization framework"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30840","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/2606.30840/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":"2606.30840","created_at":"2026-07-01T00:17:19.030327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30840v1","created_at":"2026-07-01T00:17:19.030327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30840","created_at":"2026-07-01T00:17:19.030327+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2RXRY27XAQY","created_at":"2026-07-01T00:17:19.030327+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2RXRY27XAQYDLZM","created_at":"2026-07-01T00:17:19.030327+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2RXRY27","created_at":"2026-07-01T00:17:19.030327+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/F2RXRY27XAQYDLZM5QRNQULUV5","json":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5.json","graph_json":"https://pith.science/api/pith-number/F2RXRY27XAQYDLZM5QRNQULUV5/graph.json","events_json":"https://pith.science/api/pith-number/F2RXRY27XAQYDLZM5QRNQULUV5/events.json","paper":"https://pith.science/paper/F2RXRY27"},"agent_actions":{"view_html":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5","download_json":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5.json","view_paper":"https://pith.science/paper/F2RXRY27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30840&json=true","fetch_graph":"https://pith.science/api/pith-number/F2RXRY27XAQYDLZM5QRNQULUV5/graph.json","fetch_events":"https://pith.science/api/pith-number/F2RXRY27XAQYDLZM5QRNQULUV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5/action/storage_attestation","attest_author":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5/action/author_attestation","sign_citation":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5/action/citation_signature","submit_replication":"https://pith.science/pith/F2RXRY27XAQYDLZM5QRNQULUV5/action/replication_record"}},"created_at":"2026-07-01T00:17:19.030327+00:00","updated_at":"2026-07-01T00:17:19.030327+00:00"}