{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4IUL6ECMP4XXNSNEV4FSRDCKVP","short_pith_number":"pith:4IUL6ECM","canonical_record":{"source":{"id":"2605.30157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-28T16:16:53Z","cross_cats_sorted":[],"title_canon_sha256":"54e7238622026284e0063af68a282a743a6082e7938d2db54305ae8514748eb7","abstract_canon_sha256":"17f710e45804dbddadb2492f7ab9de5a8b2eac0fa514189e74b040fe136f98ee"},"schema_version":"1.0"},"canonical_sha256":"e228bf104c7f2f76c9a4af0b288c4aabc81c08f0897395ff14d1363a39823aa4","source":{"kind":"arxiv","id":"2605.30157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30157","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30157v1","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30157","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_12","alias_value":"4IUL6ECMP4XX","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_16","alias_value":"4IUL6ECMP4XXNSNE","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_8","alias_value":"4IUL6ECM","created_at":"2026-05-29T02:06:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4IUL6ECMP4XXNSNEV4FSRDCKVP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-28T16:16:53Z","cross_cats_sorted":[],"title_canon_sha256":"54e7238622026284e0063af68a282a743a6082e7938d2db54305ae8514748eb7","abstract_canon_sha256":"17f710e45804dbddadb2492f7ab9de5a8b2eac0fa514189e74b040fe136f98ee"},"schema_version":"1.0"},"canonical_sha256":"e228bf104c7f2f76c9a4af0b288c4aabc81c08f0897395ff14d1363a39823aa4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:11.307757Z","signature_b64":"EDiLfEz3CSKyrwlBlszm//CKN5u9PQPDmNukAexGm/yFCLXAPrlul5QHGtAw6K8Bu3Proatu0u6AmgqWMqHQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e228bf104c7f2f76c9a4af0b288c4aabc81c08f0897395ff14d1363a39823aa4","last_reissued_at":"2026-05-29T02:06:11.307336Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:11.307336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30157","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":"2026-05-29T02:06:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPxYD5/MeibYCov0l5r9ooTuh2RxFEtgHFmeofwmdwsfYYJ65sAdDL0ERyW2MI0WpZvYoSDYbsueCELkfU/JDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:08:36.330632Z"},"content_sha256":"4604b4de8fe49ad1bcca39fd4b5077f75eb3c9281844c78a03c878641b9f267c","schema_version":"1.0","event_id":"sha256:4604b4de8fe49ad1bcca39fd4b5077f75eb3c9281844c78a03c878641b9f267c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4IUL6ECMP4XXNSNEV4FSRDCKVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models to Improve Precision in Randomized Controlled Trials","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Adam Sales, Jaylin Lowe, Johann A. Gagnon-Bartsch","submitted_at":"2026-05-28T16:16:53Z","abstract_excerpt":"Large language models (LLMs) are increasingly used in statistical research and applications. However,they are also notorious for unreliable or biased information. Here, we explore whether LLMs can be used to improve the precision of randomized controlled trials (RCTs) in a safe and rigorous way. Following similar work on leveraging observational data, we incorporate LLM predictions into an RCT analysis. While incorporating external predictions to improve precision is not new, the value of using LLM predictions in this manner is an open question. We develop a pipeline for best leveraging LLM pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30157","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/2605.30157/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":"2026-05-29T02:06:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28jTVS8+CiUbZnvg/W/+9ThpRTDlm4n5D+oC3cjlng1upMWjtoYHl3uDiemeRZVQyLWf09DOznkUSREZ7IhBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:08:36.331337Z"},"content_sha256":"c5b905fe933a881d4efe9dea26080909741de1c601760851d183fa54e5c81986","schema_version":"1.0","event_id":"sha256:c5b905fe933a881d4efe9dea26080909741de1c601760851d183fa54e5c81986"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4IUL6ECMP4XXNSNEV4FSRDCKVP/bundle.json","state_url":"https://pith.science/pith/4IUL6ECMP4XXNSNEV4FSRDCKVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4IUL6ECMP4XXNSNEV4FSRDCKVP/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":"2026-06-06T08:08:36Z","links":{"resolver":"https://pith.science/pith/4IUL6ECMP4XXNSNEV4FSRDCKVP","bundle":"https://pith.science/pith/4IUL6ECMP4XXNSNEV4FSRDCKVP/bundle.json","state":"https://pith.science/pith/4IUL6ECMP4XXNSNEV4FSRDCKVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4IUL6ECMP4XXNSNEV4FSRDCKVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4IUL6ECMP4XXNSNEV4FSRDCKVP","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":"17f710e45804dbddadb2492f7ab9de5a8b2eac0fa514189e74b040fe136f98ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-28T16:16:53Z","title_canon_sha256":"54e7238622026284e0063af68a282a743a6082e7938d2db54305ae8514748eb7"},"schema_version":"1.0","source":{"id":"2605.30157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30157","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30157v1","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30157","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_12","alias_value":"4IUL6ECMP4XX","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_16","alias_value":"4IUL6ECMP4XXNSNE","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_8","alias_value":"4IUL6ECM","created_at":"2026-05-29T02:06:11Z"}],"graph_snapshots":[{"event_id":"sha256:c5b905fe933a881d4efe9dea26080909741de1c601760851d183fa54e5c81986","target":"graph","created_at":"2026-05-29T02:06:11Z","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/2605.30157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used in statistical research and applications. However,they are also notorious for unreliable or biased information. Here, we explore whether LLMs can be used to improve the precision of randomized controlled trials (RCTs) in a safe and rigorous way. Following similar work on leveraging observational data, we incorporate LLM predictions into an RCT analysis. While incorporating external predictions to improve precision is not new, the value of using LLM predictions in this manner is an open question. We develop a pipeline for best leveraging LLM pr","authors_text":"Adam Sales, Jaylin Lowe, Johann A. Gagnon-Bartsch","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-28T16:16:53Z","title":"Leveraging Large Language Models to Improve Precision in Randomized Controlled Trials"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30157","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":"sha256:4604b4de8fe49ad1bcca39fd4b5077f75eb3c9281844c78a03c878641b9f267c","target":"record","created_at":"2026-05-29T02:06:11Z","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":"17f710e45804dbddadb2492f7ab9de5a8b2eac0fa514189e74b040fe136f98ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-28T16:16:53Z","title_canon_sha256":"54e7238622026284e0063af68a282a743a6082e7938d2db54305ae8514748eb7"},"schema_version":"1.0","source":{"id":"2605.30157","kind":"arxiv","version":1}},"canonical_sha256":"e228bf104c7f2f76c9a4af0b288c4aabc81c08f0897395ff14d1363a39823aa4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e228bf104c7f2f76c9a4af0b288c4aabc81c08f0897395ff14d1363a39823aa4","first_computed_at":"2026-05-29T02:06:11.307336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:11.307336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EDiLfEz3CSKyrwlBlszm//CKN5u9PQPDmNukAexGm/yFCLXAPrlul5QHGtAw6K8Bu3Proatu0u6AmgqWMqHQBw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:11.307757Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4604b4de8fe49ad1bcca39fd4b5077f75eb3c9281844c78a03c878641b9f267c","sha256:c5b905fe933a881d4efe9dea26080909741de1c601760851d183fa54e5c81986"],"state_sha256":"47fe628b3e84f33181eb12b419027aac9b1d857509581d446345ac351fca5a7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cKHJoZL544TC1Rc8p6htE6AmB0R1SMqpgrHbVWP2BCYnbQLCtEkVNMXtOhHoiPNfBtEV/iBKqsoefTmXO0dYAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T08:08:36.334335Z","bundle_sha256":"4f483e2608afeff1d970f05d4253f536b7067fee10bfa2f1203c252434fe23a8"}}