{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6L5NTIDCRM7KCPJXQNCWHZICIA","short_pith_number":"pith:6L5NTIDC","canonical_record":{"source":{"id":"2607.18225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"econ.EM","submitted_at":"2026-07-20T17:57:20Z","cross_cats_sorted":["cs.LG","math.ST","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"f41838ad9bbf994ae679639d9c5aa591aabd261e12759190033823f61fe2b05f","abstract_canon_sha256":"fff79d0aff3d3399920c9ecf180eb8cacda50ea00391e1a0bf7ac55dde46f067"},"schema_version":"1.0"},"canonical_sha256":"f2fad9a0628b3ea13d37834563e50240372f6aefe39a337d1d9d7e7956ab1913","source":{"kind":"arxiv","id":"2607.18225","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6L5NTIDCRM7KCPJXQNCWHZICIA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"econ.EM","submitted_at":"2026-07-20T17:57:20Z","cross_cats_sorted":["cs.LG","math.ST","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"f41838ad9bbf994ae679639d9c5aa591aabd261e12759190033823f61fe2b05f","abstract_canon_sha256":"fff79d0aff3d3399920c9ecf180eb8cacda50ea00391e1a0bf7ac55dde46f067"},"schema_version":"1.0"},"canonical_sha256":"f2fad9a0628b3ea13d37834563e50240372f6aefe39a337d1d9d7e7956ab1913","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:28.741272Z","signature_b64":"O7OjCGHvuYeDjTQsBEKL/16RF0g8xTpcnQUIC6W9NGW1BLeESXMBJJf9aiIYJ43NAhbO6gy0A3IrGxxfkzXFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2fad9a0628b3ea13d37834563e50240372f6aefe39a337d1d9d7e7956ab1913","last_reissued_at":"2026-07-21T02:22:28.740438Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:28.740438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18225","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T02:22:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHBATdRIHBk3iC75mC2gVdRS7fBuHFkjNxj6fkfMgqTxHqMULq9mNM7T5WpTDfbSTRsQaW6iXMb/vMSQOergBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:37:59.155129Z"},"content_sha256":"252603c96d06903842a48ecb6373cad0aaa70f30766034a85e22960fad32429c","schema_version":"1.0","event_id":"sha256:252603c96d06903842a48ecb6373cad0aaa70f30766034a85e22960fad32429c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6L5NTIDCRM7KCPJXQNCWHZICIA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ME","stat.ML","stat.TH"],"primary_cat":"econ.EM","authors_text":"Masahiro Kato, Taka Kato","submitted_at":"2026-07-20T17:57:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18225","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/2607.18225/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T02:22:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wo//NhLXSw7oE3c5G8Gs/AC/BIVMofDEvc6fdbDWQyDG+VsSzssLx9klno3vaEqFJFlbq7O06TZJCtT55S3zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:37:59.155694Z"},"content_sha256":"18170ee965186bcc54f7a544a217a2034a9b0905333abf0c93ee01c02c56ab31","schema_version":"1.0","event_id":"sha256:18170ee965186bcc54f7a544a217a2034a9b0905333abf0c93ee01c02c56ab31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6L5NTIDCRM7KCPJXQNCWHZICIA/bundle.json","state_url":"https://pith.science/pith/6L5NTIDCRM7KCPJXQNCWHZICIA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6L5NTIDCRM7KCPJXQNCWHZICIA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T22:37:59Z","links":{"resolver":"https://pith.science/pith/6L5NTIDCRM7KCPJXQNCWHZICIA","bundle":"https://pith.science/pith/6L5NTIDCRM7KCPJXQNCWHZICIA/bundle.json","state":"https://pith.science/pith/6L5NTIDCRM7KCPJXQNCWHZICIA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6L5NTIDCRM7KCPJXQNCWHZICIA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ucjHpenyWLsPA+00g63XFGGctj0vOPDn9otK3jzHUo1DTiZnwDV4AE02JHzBUqQ1HJUYjkpR/SLmaKtQd/7QBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:37:59.159324Z","bundle_sha256":"0380e1f0a366047552d3fb07f727229495989053f5d29901cc999413d62e5329"}}