{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:FCRWODSO6RTLWXSGHAKYO57DPT","short_pith_number":"pith:FCRWODSO","schema_version":"1.0","canonical_sha256":"28a3670e4ef466bb5e4638158777e37ce119f013d14ad8117c60c466d2fd5c3c","source":{"kind":"arxiv","id":"1403.3342","version":1},"attestation_state":"computed","paper":{"title":"The Potential Benefits of Filtering Versus Hyper-Parameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christophe Giraud-Carrier, Michael R. Smith, Tony Martinez","submitted_at":"2014-03-13T17:48:19Z","abstract_excerpt":"The quality of an induced model by a learning algorithm is dependent on the quality of the training data and the hyper-parameters supplied to the learning algorithm. Prior work has shown that improving the quality of the training data (i.e., by removing low quality instances) or tuning the learning algorithm hyper-parameters can significantly improve the quality of an induced model. A comparison of the two methods is lacking though. In this paper, we estimate and compare the potential benefits of filtering and hyper-parameter optimization. Estimating the potential benefit gives an overly optim"},"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":"1403.3342","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-03-13T17:48:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9e30c23ecc8811b284f1c174d73587eac4d6529a2c5f443b29b79e55bde3b99b","abstract_canon_sha256":"c659c43e9b35126922e36614027361f11d4fe0c09036eaaffb4b338b7fa86f2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:21.723516Z","signature_b64":"CT52ztBVyStJBPvTLQFwIF6zEUzG3ZXH9EZcJuVR8RnmXxEwfu71U43K9FaKOmlX99RF36hA4cxhdDuW0ouVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a3670e4ef466bb5e4638158777e37ce119f013d14ad8117c60c466d2fd5c3c","last_reissued_at":"2026-05-18T02:56:21.722767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:21.722767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Potential Benefits of Filtering Versus Hyper-Parameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christophe Giraud-Carrier, Michael R. Smith, Tony Martinez","submitted_at":"2014-03-13T17:48:19Z","abstract_excerpt":"The quality of an induced model by a learning algorithm is dependent on the quality of the training data and the hyper-parameters supplied to the learning algorithm. Prior work has shown that improving the quality of the training data (i.e., by removing low quality instances) or tuning the learning algorithm hyper-parameters can significantly improve the quality of an induced model. A comparison of the two methods is lacking though. In this paper, we estimate and compare the potential benefits of filtering and hyper-parameter optimization. Estimating the potential benefit gives an overly optim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.3342","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":""},"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":"1403.3342","created_at":"2026-05-18T02:56:21.722883+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.3342v1","created_at":"2026-05-18T02:56:21.722883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.3342","created_at":"2026-05-18T02:56:21.722883+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCRWODSO6RTL","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCRWODSO6RTLWXSG","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCRWODSO","created_at":"2026-05-18T12:28:28.263976+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/FCRWODSO6RTLWXSGHAKYO57DPT","json":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT.json","graph_json":"https://pith.science/api/pith-number/FCRWODSO6RTLWXSGHAKYO57DPT/graph.json","events_json":"https://pith.science/api/pith-number/FCRWODSO6RTLWXSGHAKYO57DPT/events.json","paper":"https://pith.science/paper/FCRWODSO"},"agent_actions":{"view_html":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT","download_json":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT.json","view_paper":"https://pith.science/paper/FCRWODSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.3342&json=true","fetch_graph":"https://pith.science/api/pith-number/FCRWODSO6RTLWXSGHAKYO57DPT/graph.json","fetch_events":"https://pith.science/api/pith-number/FCRWODSO6RTLWXSGHAKYO57DPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT/action/storage_attestation","attest_author":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT/action/author_attestation","sign_citation":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT/action/citation_signature","submit_replication":"https://pith.science/pith/FCRWODSO6RTLWXSGHAKYO57DPT/action/replication_record"}},"created_at":"2026-05-18T02:56:21.722883+00:00","updated_at":"2026-05-18T02:56:21.722883+00:00"}