{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6L5NTIDCRM7KCPJXQNCWHZICIA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fff79d0aff3d3399920c9ecf180eb8cacda50ea00391e1a0bf7ac55dde46f067","cross_cats_sorted":["cs.LG","math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"econ.EM","submitted_at":"2026-07-20T17:57:20Z","title_canon_sha256":"f41838ad9bbf994ae679639d9c5aa591aabd261e12759190033823f61fe2b05f"},"schema_version":"1.0","source":{"id":"2607.18225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18225","created_at":"2026-07-21T02:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18225v1","created_at":"2026-07-21T02:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18225","created_at":"2026-07-21T02:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"6L5NTIDCRM7K","created_at":"2026-07-21T02:22:28Z"},{"alias_kind":"pith_short_16","alias_value":"6L5NTIDCRM7KCPJX","created_at":"2026-07-21T02:22:28Z"},{"alias_kind":"pith_short_8","alias_value":"6L5NTIDC","created_at":"2026-07-21T02:22:28Z"}],"graph_snapshots":[{"event_id":"sha256:18170ee965186bcc54f7a544a217a2034a9b0905333abf0c93ee01c02c56ab31","target":"graph","created_at":"2026-07-21T02:22:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.18225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose one-step and two-step methods for policy learning with retrieval-augmented generation (RAG). We formulate RAG-based action selection under the potential outcome framework. In the two-step method, vector search retrieves action-specific neighboring evidence in an embedding space, the generator estimates conditional expected outcomes or their contrasts, and a plug-in rule selects an action. This formulation connects action-specific vector search with nearest-neighbor matching in causal inference. We decompose the regret of the two-step method into candidate-generation regret and withi","authors_text":"Masahiro Kato, Taka Kato","cross_cats":["cs.LG","math.ST","stat.ME","stat.ML","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"econ.EM","submitted_at":"2026-07-20T17:57:20Z","title":"Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18225","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:252603c96d06903842a48ecb6373cad0aaa70f30766034a85e22960fad32429c","target":"record","created_at":"2026-07-21T02:22:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fff79d0aff3d3399920c9ecf180eb8cacda50ea00391e1a0bf7ac55dde46f067","cross_cats_sorted":["cs.LG","math.ST","stat.ME","stat.ML","stat.TH"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"econ.EM","submitted_at":"2026-07-20T17:57:20Z","title_canon_sha256":"f41838ad9bbf994ae679639d9c5aa591aabd261e12759190033823f61fe2b05f"},"schema_version":"1.0","source":{"id":"2607.18225","kind":"arxiv","version":1}},"canonical_sha256":"f2fad9a0628b3ea13d37834563e50240372f6aefe39a337d1d9d7e7956ab1913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2fad9a0628b3ea13d37834563e50240372f6aefe39a337d1d9d7e7956ab1913","first_computed_at":"2026-07-21T02:22:28.740438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:28.740438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O7OjCGHvuYeDjTQsBEKL/16RF0g8xTpcnQUIC6W9NGW1BLeESXMBJJf9aiIYJ43NAhbO6gy0A3IrGxxfkzXFCg==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:28.741272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:252603c96d06903842a48ecb6373cad0aaa70f30766034a85e22960fad32429c","sha256:18170ee965186bcc54f7a544a217a2034a9b0905333abf0c93ee01c02c56ab31"],"state_sha256":"b63c79785008a12c9b30db23985b07977fb60273f345ab216800ac9d11636478"}