{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NV2X35YXYXPDM2AY5U7M3RVF4D","short_pith_number":"pith:NV2X35YX","schema_version":"1.0","canonical_sha256":"6d757df717c5de366818ed3ecdc6a5e0f77104213dca0ecf787f7c6d3718ba9c","source":{"kind":"arxiv","id":"2501.00034","version":1},"attestation_state":"computed","paper":{"title":"Time Series Feature Redundancy Paradox: An Empirical Study Based on Mortgage Default Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-fin.ST","authors_text":"Chengyue Huang, Yahe Yang","submitted_at":"2024-12-23T21:28:32Z","abstract_excerpt":"With the widespread application of machine learning in financial risk management, conventional wisdom suggests that longer training periods and more feature variables contribute to improved model performance. This paper, focusing on mortgage default prediction, empirically discovers a phenomenon that contradicts traditional knowledge: in time series prediction, increased training data timespan and additional non-critical features actually lead to significant deterioration in prediction effectiveness. Using Fannie Mae's mortgage data, the study compares predictive performance across different t"},"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":"2501.00034","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.ST","submitted_at":"2024-12-23T21:28:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9a971bc6a334f998a94b14c3cdc882d99e0d63d2706defa9be19ee5bd592e7be","abstract_canon_sha256":"5e50b1ddc8a11b0f75d111c6bddb4b100a98dd25d69ef00dfbb30aa238c3eeba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:37.957099Z","signature_b64":"UIR5bhqq2FgKVmOLV400GW8bbXym5oZiSHrxuLp5Qdr97X85gpkeyXNtyuYa+ro04oSAJGCPPWO8wCc9Sj7oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d757df717c5de366818ed3ecdc6a5e0f77104213dca0ecf787f7c6d3718ba9c","last_reissued_at":"2026-07-05T09:55:37.956735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:37.956735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time Series Feature Redundancy Paradox: An Empirical Study Based on Mortgage Default Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-fin.ST","authors_text":"Chengyue Huang, Yahe Yang","submitted_at":"2024-12-23T21:28:32Z","abstract_excerpt":"With the widespread application of machine learning in financial risk management, conventional wisdom suggests that longer training periods and more feature variables contribute to improved model performance. This paper, focusing on mortgage default prediction, empirically discovers a phenomenon that contradicts traditional knowledge: in time series prediction, increased training data timespan and additional non-critical features actually lead to significant deterioration in prediction effectiveness. Using Fannie Mae's mortgage data, the study compares predictive performance across different t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00034","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/2501.00034/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":"2501.00034","created_at":"2026-07-05T09:55:37.956796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00034v1","created_at":"2026-07-05T09:55:37.956796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00034","created_at":"2026-07-05T09:55:37.956796+00:00"},{"alias_kind":"pith_short_12","alias_value":"NV2X35YXYXPD","created_at":"2026-07-05T09:55:37.956796+00:00"},{"alias_kind":"pith_short_16","alias_value":"NV2X35YXYXPDM2AY","created_at":"2026-07-05T09:55:37.956796+00:00"},{"alias_kind":"pith_short_8","alias_value":"NV2X35YX","created_at":"2026-07-05T09:55:37.956796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06847","citing_title":"A Deep Learning Framework Integrating CNN and BiLSTM for Financial Systemic Risk Analysis and Prediction","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D","json":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D.json","graph_json":"https://pith.science/api/pith-number/NV2X35YXYXPDM2AY5U7M3RVF4D/graph.json","events_json":"https://pith.science/api/pith-number/NV2X35YXYXPDM2AY5U7M3RVF4D/events.json","paper":"https://pith.science/paper/NV2X35YX"},"agent_actions":{"view_html":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D","download_json":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D.json","view_paper":"https://pith.science/paper/NV2X35YX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00034&json=true","fetch_graph":"https://pith.science/api/pith-number/NV2X35YXYXPDM2AY5U7M3RVF4D/graph.json","fetch_events":"https://pith.science/api/pith-number/NV2X35YXYXPDM2AY5U7M3RVF4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D/action/storage_attestation","attest_author":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D/action/author_attestation","sign_citation":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D/action/citation_signature","submit_replication":"https://pith.science/pith/NV2X35YXYXPDM2AY5U7M3RVF4D/action/replication_record"}},"created_at":"2026-07-05T09:55:37.956796+00:00","updated_at":"2026-07-05T09:55:37.956796+00:00"}