{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ICSBYDX2Q6OWYL5U42KH3SONX3","short_pith_number":"pith:ICSBYDX2","canonical_record":{"source":{"id":"2606.08853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.EM","submitted_at":"2026-06-07T21:45:17Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"5b897e49fcd748577301784bc54e8d4be0bf91bafa797029dfe0e23cba27862b","abstract_canon_sha256":"d32178a9729e1ec36d6435f0d84c34a1f26df1c2f88c5f7dd5133ae08f7a245a"},"schema_version":"1.0"},"canonical_sha256":"40a41c0efa879d6c2fb4e6947dc9cdbeffd8117873ad0f4d58fe3d78ef7182ca","source":{"kind":"arxiv","id":"2606.08853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08853","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08853v1","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08853","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"pith_short_12","alias_value":"ICSBYDX2Q6OW","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"pith_short_16","alias_value":"ICSBYDX2Q6OWYL5U","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"pith_short_8","alias_value":"ICSBYDX2","created_at":"2026-06-09T02:07:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ICSBYDX2Q6OWYL5U42KH3SONX3","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.EM","submitted_at":"2026-06-07T21:45:17Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"5b897e49fcd748577301784bc54e8d4be0bf91bafa797029dfe0e23cba27862b","abstract_canon_sha256":"d32178a9729e1ec36d6435f0d84c34a1f26df1c2f88c5f7dd5133ae08f7a245a"},"schema_version":"1.0"},"canonical_sha256":"40a41c0efa879d6c2fb4e6947dc9cdbeffd8117873ad0f4d58fe3d78ef7182ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:42.987656Z","signature_b64":"oREeqSDezYfNiPOTHJlCVt6NyINIz/Y+2sa5rd3RNV4bAUunC+JfFrsx9c9ImE/2LnLvUm02K1xuXtLGZUXPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40a41c0efa879d6c2fb4e6947dc9cdbeffd8117873ad0f4d58fe3d78ef7182ca","last_reissued_at":"2026-06-09T02:07:42.986918Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:42.986918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08853","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":"2026-06-09T02:07:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UcYiI+FB/GTzqVkoi01nwI/hdwtNWFuT/gJHtlHSAxp9QHCD5TNOwbWb0mc/VPb73W9xmyqdX99XZcV29lbqCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:43:18.028593Z"},"content_sha256":"7e87118944b55628bd41ead62665f3e0e1b458d656e049bf757084e5a483032d","schema_version":"1.0","event_id":"sha256:7e87118944b55628bd41ead62665f3e0e1b458d656e049bf757084e5a483032d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ICSBYDX2Q6OWYL5U42KH3SONX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AI-Assisted Variance Reduction in Randomized Experiments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"econ.EM","authors_text":"Apoorva Lal, Avi Feller, David Arbour, Eli Ben-Michael, Lo-Hua Yuan","submitted_at":"2026-06-07T21:45:17Z","abstract_excerpt":"Generative AI and large language models can produce realistic predictions of human behavior from rich, unstructured inputs with little to no task-specific training data. Recent work uses these ``digital twin'' predictions to supplement human responses in surveys and experiments. We study the special case of using AI-generated predictions to reduce variance in randomized experiments. We argue that doing so requires no new estimators and that researchers can simply include AI predictions as covariates in standard regression adjustment, analogous to adjusting for a prognostic score. A benefit of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08853","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/2606.08853/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":"2026-06-09T02:07:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgOjcl05xDMMdyy9hmV1jx6jfIGmKp59euu7nhN7CrxHsk+kdgEkQKlDh/qyw81TxvRTwoKrxELmpkJT8qFKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T05:43:18.028989Z"},"content_sha256":"d0dd64c3f430a8bc205854393d41331ebcd0a5478cdb3d8a42f149c050f8de53","schema_version":"1.0","event_id":"sha256:d0dd64c3f430a8bc205854393d41331ebcd0a5478cdb3d8a42f149c050f8de53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICSBYDX2Q6OWYL5U42KH3SONX3/bundle.json","state_url":"https://pith.science/pith/ICSBYDX2Q6OWYL5U42KH3SONX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICSBYDX2Q6OWYL5U42KH3SONX3/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":"2026-06-12T05:43:18Z","links":{"resolver":"https://pith.science/pith/ICSBYDX2Q6OWYL5U42KH3SONX3","bundle":"https://pith.science/pith/ICSBYDX2Q6OWYL5U42KH3SONX3/bundle.json","state":"https://pith.science/pith/ICSBYDX2Q6OWYL5U42KH3SONX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICSBYDX2Q6OWYL5U42KH3SONX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ICSBYDX2Q6OWYL5U42KH3SONX3","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":"d32178a9729e1ec36d6435f0d84c34a1f26df1c2f88c5f7dd5133ae08f7a245a","cross_cats_sorted":["stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.EM","submitted_at":"2026-06-07T21:45:17Z","title_canon_sha256":"5b897e49fcd748577301784bc54e8d4be0bf91bafa797029dfe0e23cba27862b"},"schema_version":"1.0","source":{"id":"2606.08853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08853","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08853v1","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08853","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"pith_short_12","alias_value":"ICSBYDX2Q6OW","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"pith_short_16","alias_value":"ICSBYDX2Q6OWYL5U","created_at":"2026-06-09T02:07:42Z"},{"alias_kind":"pith_short_8","alias_value":"ICSBYDX2","created_at":"2026-06-09T02:07:42Z"}],"graph_snapshots":[{"event_id":"sha256:d0dd64c3f430a8bc205854393d41331ebcd0a5478cdb3d8a42f149c050f8de53","target":"graph","created_at":"2026-06-09T02:07:42Z","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/2606.08853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative AI and large language models can produce realistic predictions of human behavior from rich, unstructured inputs with little to no task-specific training data. Recent work uses these ``digital twin'' predictions to supplement human responses in surveys and experiments. We study the special case of using AI-generated predictions to reduce variance in randomized experiments. We argue that doing so requires no new estimators and that researchers can simply include AI predictions as covariates in standard regression adjustment, analogous to adjusting for a prognostic score. A benefit of ","authors_text":"Apoorva Lal, Avi Feller, David Arbour, Eli Ben-Michael, Lo-Hua Yuan","cross_cats":["stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.EM","submitted_at":"2026-06-07T21:45:17Z","title":"AI-Assisted Variance Reduction in Randomized Experiments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08853","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":"sha256:7e87118944b55628bd41ead62665f3e0e1b458d656e049bf757084e5a483032d","target":"record","created_at":"2026-06-09T02:07:42Z","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":"d32178a9729e1ec36d6435f0d84c34a1f26df1c2f88c5f7dd5133ae08f7a245a","cross_cats_sorted":["stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.EM","submitted_at":"2026-06-07T21:45:17Z","title_canon_sha256":"5b897e49fcd748577301784bc54e8d4be0bf91bafa797029dfe0e23cba27862b"},"schema_version":"1.0","source":{"id":"2606.08853","kind":"arxiv","version":1}},"canonical_sha256":"40a41c0efa879d6c2fb4e6947dc9cdbeffd8117873ad0f4d58fe3d78ef7182ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40a41c0efa879d6c2fb4e6947dc9cdbeffd8117873ad0f4d58fe3d78ef7182ca","first_computed_at":"2026-06-09T02:07:42.986918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:42.986918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oREeqSDezYfNiPOTHJlCVt6NyINIz/Y+2sa5rd3RNV4bAUunC+JfFrsx9c9ImE/2LnLvUm02K1xuXtLGZUXPDg==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:42.987656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e87118944b55628bd41ead62665f3e0e1b458d656e049bf757084e5a483032d","sha256:d0dd64c3f430a8bc205854393d41331ebcd0a5478cdb3d8a42f149c050f8de53"],"state_sha256":"0e405ce3892e8d884e94bd01033341ee08009721b94389a4c6d5c8b1e7677da7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrMWo9/pMmjFZiMDp2KR2H68C15cSEU7I4H7vjKnf1QY2fav/unxaKe9BWFehmmRML/sNT+/zpSPkYsapYIwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T05:43:18.031742Z","bundle_sha256":"71362931a35efc67f7346ef0f3d307fd12f9c7f6a2c5a52c4b2f116749f4b85a"}}