{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HSLBHAKQSF4AQYNND2UPHOKVBE","short_pith_number":"pith:HSLBHAKQ","schema_version":"1.0","canonical_sha256":"3c9613815091780861ad1ea8f3b955093bf727dfee85d7430d5a8a04bb0c35a4","source":{"kind":"arxiv","id":"2112.09400","version":1},"attestation_state":"computed","paper":{"title":"Quality of Data in Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antti Kariluoto, Arto P\\\"arn\\\"anen, Joni Kultanen, Jukka Soininen, Pekka Abrahamsson","submitted_at":"2021-12-17T09:22:46Z","abstract_excerpt":"A common assumption exists according to which machine learning models improve their performance when they have more data to learn from. In this study, the authors wished to clarify the dilemma by performing an empirical experiment utilizing novel vocational student data. The experiment compared different machine learning algorithms while varying the number of data and feature combinations available for training and testing the models. The experiment revealed that the increase of data records or their sample frequency does not immediately lead to significant increases in the model accuracies or"},"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":"2112.09400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-17T09:22:46Z","cross_cats_sorted":[],"title_canon_sha256":"0760c2437ed6606a27676e9ac4dc91e82c1aead7fa4687674c43758112440c95","abstract_canon_sha256":"e2cae846e3ad0608cea8993a09129a7ee1a8fc7f20d20d35a009c179addc8d67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:45.917960Z","signature_b64":"9h6yfpjHN3eLXn7+FnS+CjGuZ5FOMWkbci9To6us6FuFjmRqXoXy/GTkTM0KhN1PsomcX5LfTHeE2jd7GSgJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c9613815091780861ad1ea8f3b955093bf727dfee85d7430d5a8a04bb0c35a4","last_reissued_at":"2026-07-05T03:41:45.917468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:45.917468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quality of Data in Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antti Kariluoto, Arto P\\\"arn\\\"anen, Joni Kultanen, Jukka Soininen, Pekka Abrahamsson","submitted_at":"2021-12-17T09:22:46Z","abstract_excerpt":"A common assumption exists according to which machine learning models improve their performance when they have more data to learn from. In this study, the authors wished to clarify the dilemma by performing an empirical experiment utilizing novel vocational student data. The experiment compared different machine learning algorithms while varying the number of data and feature combinations available for training and testing the models. The experiment revealed that the increase of data records or their sample frequency does not immediately lead to significant increases in the model accuracies or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09400","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/2112.09400/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":"2112.09400","created_at":"2026-07-05T03:41:45.917541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.09400v1","created_at":"2026-07-05T03:41:45.917541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09400","created_at":"2026-07-05T03:41:45.917541+00:00"},{"alias_kind":"pith_short_12","alias_value":"HSLBHAKQSF4A","created_at":"2026-07-05T03:41:45.917541+00:00"},{"alias_kind":"pith_short_16","alias_value":"HSLBHAKQSF4AQYNN","created_at":"2026-07-05T03:41:45.917541+00:00"},{"alias_kind":"pith_short_8","alias_value":"HSLBHAKQ","created_at":"2026-07-05T03:41:45.917541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17847","citing_title":"A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE","json":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE.json","graph_json":"https://pith.science/api/pith-number/HSLBHAKQSF4AQYNND2UPHOKVBE/graph.json","events_json":"https://pith.science/api/pith-number/HSLBHAKQSF4AQYNND2UPHOKVBE/events.json","paper":"https://pith.science/paper/HSLBHAKQ"},"agent_actions":{"view_html":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE","download_json":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE.json","view_paper":"https://pith.science/paper/HSLBHAKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.09400&json=true","fetch_graph":"https://pith.science/api/pith-number/HSLBHAKQSF4AQYNND2UPHOKVBE/graph.json","fetch_events":"https://pith.science/api/pith-number/HSLBHAKQSF4AQYNND2UPHOKVBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE/action/storage_attestation","attest_author":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE/action/author_attestation","sign_citation":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE/action/citation_signature","submit_replication":"https://pith.science/pith/HSLBHAKQSF4AQYNND2UPHOKVBE/action/replication_record"}},"created_at":"2026-07-05T03:41:45.917541+00:00","updated_at":"2026-07-05T03:41:45.917541+00:00"}