{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ACZWYH6J7DDQNV2BXI3VDWTRLF","short_pith_number":"pith:ACZWYH6J","canonical_record":{"source":{"id":"2402.15585","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2024-02-23T19:52:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"094e1d819edc4ad4d9dfc0c5198a64621339cb0e9d77a5670db94d755711c3df","abstract_canon_sha256":"0cc72379be1a0658f7f63bc96141b2d98f829f7a3bd60ae56cd8016765888570"},"schema_version":"1.0"},"canonical_sha256":"00b36c1fc9f8c706d741ba3751da715946de823761e6ac3b6d659889fd8b3d66","source":{"kind":"arxiv","id":"2402.15585","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15585","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15585v5","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15585","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"ACZWYH6J7DDQ","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"pith_short_16","alias_value":"ACZWYH6J7DDQNV2B","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"pith_short_8","alias_value":"ACZWYH6J","created_at":"2026-07-05T10:56:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ACZWYH6J7DDQNV2BXI3VDWTRLF","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15585","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2024-02-23T19:52:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"094e1d819edc4ad4d9dfc0c5198a64621339cb0e9d77a5670db94d755711c3df","abstract_canon_sha256":"0cc72379be1a0658f7f63bc96141b2d98f829f7a3bd60ae56cd8016765888570"},"schema_version":"1.0"},"canonical_sha256":"00b36c1fc9f8c706d741ba3751da715946de823761e6ac3b6d659889fd8b3d66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:05.262889Z","signature_b64":"odRB5Jp1EwwmVc236v7eWQe5JffUVWXWwl1Gao0fvboabJSkclHKFqfTFLt677NqSXkMVHi+HFm/Uy1qfdhBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00b36c1fc9f8c706d741ba3751da715946de823761e6ac3b6d659889fd8b3d66","last_reissued_at":"2026-07-05T10:56:05.262356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:05.262356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15585","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5GA4mlLVuNPnevYyaNHrrg3nTj+S1z7O0foyQHvidQ1RV46qGwAdPzlv76IkH3+20m4J/JixT7ynI7rGfaM7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:06:54.315235Z"},"content_sha256":"eab56b5c0ce996e6dd3c0b084b16ffa461dff481eeaeed9506dfa68ac32162a8","schema_version":"1.0","event_id":"sha256:eab56b5c0ce996e6dd3c0b084b16ffa461dff481eeaeed9506dfa68ac32162a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ACZWYH6J7DDQNV2BXI3VDWTRLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inference for Regression with Variables Generated by AI or Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"econ.EM","authors_text":"Laura Battaglia, Stephen Hansen, Szymon Sacher, Timothy Christensen","submitted_at":"2024-02-23T19:52:09Z","abstract_excerpt":"Researchers now routinely use AI or other machine learning methods to estimate latent variables of economic interest, then plug-in the estimates as covariates in a regression. We show both theoretically and empirically that naively treating AI/ML-generated variables as \"data\" leads to biased estimates and invalid inference. To restore valid inference, we propose two methods: (1) an explicit bias correction with bias-corrected confidence intervals, and (2) joint estimation of the regression parameters and latent variables. We illustrate these ideas through applications involving label imputatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15585","kind":"arxiv","version":5},"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/2402.15585/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":"2026-07-05T10:56:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"znv2/vx9/ROxAPNodeuPrAml3xNUc1HS9Xv5jOkuA6+tjlDmy+jmx8SQJQUDtwyQAPPgxarZxYdUTq6Z9AwZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T09:06:54.315786Z"},"content_sha256":"569f2cb755ff8c663230188be9f0dafa6890aeb088cb5e1f5378f79c1bd643d1","schema_version":"1.0","event_id":"sha256:569f2cb755ff8c663230188be9f0dafa6890aeb088cb5e1f5378f79c1bd643d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACZWYH6J7DDQNV2BXI3VDWTRLF/bundle.json","state_url":"https://pith.science/pith/ACZWYH6J7DDQNV2BXI3VDWTRLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACZWYH6J7DDQNV2BXI3VDWTRLF/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":"2026-08-15T09:06:54Z","links":{"resolver":"https://pith.science/pith/ACZWYH6J7DDQNV2BXI3VDWTRLF","bundle":"https://pith.science/pith/ACZWYH6J7DDQNV2BXI3VDWTRLF/bundle.json","state":"https://pith.science/pith/ACZWYH6J7DDQNV2BXI3VDWTRLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACZWYH6J7DDQNV2BXI3VDWTRLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ACZWYH6J7DDQNV2BXI3VDWTRLF","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":"0cc72379be1a0658f7f63bc96141b2d98f829f7a3bd60ae56cd8016765888570","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2024-02-23T19:52:09Z","title_canon_sha256":"094e1d819edc4ad4d9dfc0c5198a64621339cb0e9d77a5670db94d755711c3df"},"schema_version":"1.0","source":{"id":"2402.15585","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15585","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15585v5","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15585","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"pith_short_12","alias_value":"ACZWYH6J7DDQ","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"pith_short_16","alias_value":"ACZWYH6J7DDQNV2B","created_at":"2026-07-05T10:56:05Z"},{"alias_kind":"pith_short_8","alias_value":"ACZWYH6J","created_at":"2026-07-05T10:56:05Z"}],"graph_snapshots":[{"event_id":"sha256:569f2cb755ff8c663230188be9f0dafa6890aeb088cb5e1f5378f79c1bd643d1","target":"graph","created_at":"2026-07-05T10:56:05Z","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/2402.15585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Researchers now routinely use AI or other machine learning methods to estimate latent variables of economic interest, then plug-in the estimates as covariates in a regression. We show both theoretically and empirically that naively treating AI/ML-generated variables as \"data\" leads to biased estimates and invalid inference. To restore valid inference, we propose two methods: (1) an explicit bias correction with bias-corrected confidence intervals, and (2) joint estimation of the regression parameters and latent variables. We illustrate these ideas through applications involving label imputatio","authors_text":"Laura Battaglia, Stephen Hansen, Szymon Sacher, Timothy Christensen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2024-02-23T19:52:09Z","title":"Inference for Regression with Variables Generated by AI or Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15585","kind":"arxiv","version":5},"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:eab56b5c0ce996e6dd3c0b084b16ffa461dff481eeaeed9506dfa68ac32162a8","target":"record","created_at":"2026-07-05T10:56:05Z","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":"0cc72379be1a0658f7f63bc96141b2d98f829f7a3bd60ae56cd8016765888570","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2024-02-23T19:52:09Z","title_canon_sha256":"094e1d819edc4ad4d9dfc0c5198a64621339cb0e9d77a5670db94d755711c3df"},"schema_version":"1.0","source":{"id":"2402.15585","kind":"arxiv","version":5}},"canonical_sha256":"00b36c1fc9f8c706d741ba3751da715946de823761e6ac3b6d659889fd8b3d66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00b36c1fc9f8c706d741ba3751da715946de823761e6ac3b6d659889fd8b3d66","first_computed_at":"2026-07-05T10:56:05.262356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:05.262356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"odRB5Jp1EwwmVc236v7eWQe5JffUVWXWwl1Gao0fvboabJSkclHKFqfTFLt677NqSXkMVHi+HFm/Uy1qfdhBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:05.262889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15585","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eab56b5c0ce996e6dd3c0b084b16ffa461dff481eeaeed9506dfa68ac32162a8","sha256:569f2cb755ff8c663230188be9f0dafa6890aeb088cb5e1f5378f79c1bd643d1"],"state_sha256":"26c8403f734708f6817fa7d602663b1c87a8ee8e28f56a4a046207e4cca77a91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vnGP7+1TmLXC8O/UGMiF8jsJeekbxf8AcDGAnw3A80+4S/LaoIEcp6xIrKujMUlbJ16WyK8trjWVSFekIxfbAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T09:06:54.319373Z","bundle_sha256":"f5251231aa0f93bf3869727ca2d908bbc83ddb59b78e423223b8100f8e7281da"}}