{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FDTA5BZ667KWUCQ37K3IDHCE6K","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":"84cee9154dd1bdd68be5782d0cd14fb7551d56c916c98dd68cb4c6252befe52c","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2025-05-19T17:53:15Z","title_canon_sha256":"0eefb624958a66a02490eeb07e8916ba33c86d53263ed3236ee837e5b151bbcd"},"schema_version":"1.0","source":{"id":"2505.13422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13422","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13422v1","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13422","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"FDTA5BZ667KW","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"FDTA5BZ667KWUCQ3","created_at":"2026-07-05T11:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"FDTA5BZ6","created_at":"2026-07-05T11:05:29Z"}],"graph_snapshots":[{"event_id":"sha256:b90b62fad70a212ddf5af2b5904485c82d6d0f94321304034f54c2d518b6bef4","target":"graph","created_at":"2026-07-05T11:05:29Z","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/2505.13422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning (ML) primarily evolved to solve \"prediction problems.\" The first stage of two-stage least squares (2SLS) is a prediction problem, suggesting potential gains from ML first-stage assistance. However, little guidance exists on when ML helps 2SLS$\\unicode{x2014}$or when it hurts. We investigate the implications of inserting ML into 2SLS, decomposing the bias into three informative components. Mechanically, ML-in-2SLS procedures face issues common to prediction and causal-inference settings$\\unicode{x2014}$and their interaction. Through simulation, we show linear ML methods (e.g., ","authors_text":"Connor Lennon, Edward Rubin, Glen Waddell","cross_cats":["cs.LG","stat.AP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2025-05-19T17:53:15Z","title":"Machine learning the first stage in 2SLS: Practical guidance from bias decomposition and simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13422","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":"sha256:383035c5d75faeea80f1224685ab5afdc775703645605ae31e6d11553c93b7f7","target":"record","created_at":"2026-07-05T11:05:29Z","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":"84cee9154dd1bdd68be5782d0cd14fb7551d56c916c98dd68cb4c6252befe52c","cross_cats_sorted":["cs.LG","stat.AP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2025-05-19T17:53:15Z","title_canon_sha256":"0eefb624958a66a02490eeb07e8916ba33c86d53263ed3236ee837e5b151bbcd"},"schema_version":"1.0","source":{"id":"2505.13422","kind":"arxiv","version":1}},"canonical_sha256":"28e60e873ef7d56a0a1bfab6819c44f2bde2775ea39d25b4d2699a35e84841bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28e60e873ef7d56a0a1bfab6819c44f2bde2775ea39d25b4d2699a35e84841bb","first_computed_at":"2026-07-05T11:05:29.875395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:29.875395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XX8Ze44Fj5NxUdADl6P2Zw9Fty6gtlCDHUK2HwA0/PdV7qCX0RgpvRviiOYxpknOniss+LMIgH+Zu/YH8FzdAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:29.875878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:383035c5d75faeea80f1224685ab5afdc775703645605ae31e6d11553c93b7f7","sha256:b90b62fad70a212ddf5af2b5904485c82d6d0f94321304034f54c2d518b6bef4"],"state_sha256":"ae075a963e51b46d5174d5d869fad1e15394712a063f958843ec60653f8cf1f1"}