{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRIHMLXZIN3WA3JOIHEEPSOQR7","short_pith_number":"pith:WRIHMLXZ","schema_version":"1.0","canonical_sha256":"b450762ef94377606d2e41c847c9d08fdf9016bc7772fd73cd174b559fc3b10b","source":{"kind":"arxiv","id":"2411.09218","version":2},"attestation_state":"computed","paper":{"title":"On the (Mis)Use of Machine Learning with Panel Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"econ.EM","authors_text":"Augusto Cerqua, Gabriele Pinto, Marco Letta","submitted_at":"2024-11-14T06:29:59Z","abstract_excerpt":"We provide the first systematic assessment of data leakage issues in the use of machine learning on panel data. Our organizing framework clarifies why neglecting the cross-sectional and longitudinal structure of these data leads to hard-to-detect data leakage, inflated out-of-sample performance, and an inadvertent overestimation of the real-world usefulness and applicability of machine learning models. We then offer empirical guidelines for practitioners to ensure the correct implementation of supervised machine learning in panel data environments. An empirical application, using data from ove"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.09218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"econ.EM","submitted_at":"2024-11-14T06:29:59Z","cross_cats_sorted":[],"title_canon_sha256":"dec49c2bd23638fbbb9d806b887be2ae11ace03f589f4339462cce51bc21e3f5","abstract_canon_sha256":"a325d228b505d58b13990088447b5847ec09b439ad6ed66b4e65227582d790ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:20.290825Z","signature_b64":"K66c5NkSN4dQkr8NvuMq7qm9SlTdlub6hJlF3/1o0bgepOggECO62+7J7GvA6feOnehKfw26k6idjD4vgEzrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b450762ef94377606d2e41c847c9d08fdf9016bc7772fd73cd174b559fc3b10b","last_reissued_at":"2026-07-05T10:58:20.290256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:20.290256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the (Mis)Use of Machine Learning with Panel Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"econ.EM","authors_text":"Augusto Cerqua, Gabriele Pinto, Marco Letta","submitted_at":"2024-11-14T06:29:59Z","abstract_excerpt":"We provide the first systematic assessment of data leakage issues in the use of machine learning on panel data. Our organizing framework clarifies why neglecting the cross-sectional and longitudinal structure of these data leads to hard-to-detect data leakage, inflated out-of-sample performance, and an inadvertent overestimation of the real-world usefulness and applicability of machine learning models. We then offer empirical guidelines for practitioners to ensure the correct implementation of supervised machine learning in panel data environments. An empirical application, using data from ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09218","kind":"arxiv","version":2},"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/2411.09218/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.09218","created_at":"2026-07-05T10:58:20.290325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09218v2","created_at":"2026-07-05T10:58:20.290325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09218","created_at":"2026-07-05T10:58:20.290325+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRIHMLXZIN3W","created_at":"2026-07-05T10:58:20.290325+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRIHMLXZIN3WA3JO","created_at":"2026-07-05T10:58:20.290325+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRIHMLXZ","created_at":"2026-07-05T10:58:20.290325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7","json":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7.json","graph_json":"https://pith.science/api/pith-number/WRIHMLXZIN3WA3JOIHEEPSOQR7/graph.json","events_json":"https://pith.science/api/pith-number/WRIHMLXZIN3WA3JOIHEEPSOQR7/events.json","paper":"https://pith.science/paper/WRIHMLXZ"},"agent_actions":{"view_html":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7","download_json":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7.json","view_paper":"https://pith.science/paper/WRIHMLXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09218&json=true","fetch_graph":"https://pith.science/api/pith-number/WRIHMLXZIN3WA3JOIHEEPSOQR7/graph.json","fetch_events":"https://pith.science/api/pith-number/WRIHMLXZIN3WA3JOIHEEPSOQR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7/action/storage_attestation","attest_author":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7/action/author_attestation","sign_citation":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7/action/citation_signature","submit_replication":"https://pith.science/pith/WRIHMLXZIN3WA3JOIHEEPSOQR7/action/replication_record"}},"created_at":"2026-07-05T10:58:20.290325+00:00","updated_at":"2026-07-05T10:58:20.290325+00:00"}