{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VAS6LAWNGSV57LZRRSM2KTS6XM","short_pith_number":"pith:VAS6LAWN","schema_version":"1.0","canonical_sha256":"a825e582cd34abdfaf318c99a54e5ebb36902381cee02b8250346b8ea41967e7","source":{"kind":"arxiv","id":"2411.17709","version":1},"attestation_state":"computed","paper":{"title":"Quantity versus Diversity: Influence of Data on Detecting EEG Pathology with Advanced ML Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Jacek Rogala, Jaros{\\l}aw \\.Zygierewicz, Joanna Zych, Marian Dovgialo, Martyna Poziomska, Pawe{\\l} Niedbalski, Pawe{\\l} Ogniewski, Przemys{\\l}aw Olbratowski","submitted_at":"2024-11-13T16:15:48Z","abstract_excerpt":"This study investigates the impact of quantity and diversity of data on the performance of various machine-learning models for detecting general EEG pathology. We utilized an EEG dataset of 2,993 recordings from Temple University Hospital and a dataset of 55,787 recordings from Elmiko Biosignals sp. z o.o. The latter contains data from 39 hospitals and a diverse patient set with varied conditions. Thus, we introduce the Elmiko dataset - the largest publicly available EEG corpus. Our findings show that small and consistent datasets enable a wide range of models to achieve high accuracy; however"},"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":"2411.17709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2024-11-13T16:15:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"67305b6ac9f228ff3838e4e313143ed6c0e65f4054ebdc1524ab7028ae112d09","abstract_canon_sha256":"4a938358899834950c5ae07f6dd914211abace2a4fb5b262bffecb632477f93b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:05.433282Z","signature_b64":"HtXOG1HqMlLkoSRDelAc6GZX4t0lmuo4uQwNyagxnIhay3EIYxqR5i7Xy3VvfacHIDLO07zvRfqXpTAUS2CcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a825e582cd34abdfaf318c99a54e5ebb36902381cee02b8250346b8ea41967e7","last_reissued_at":"2026-07-05T09:41:05.432916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:05.432916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantity versus Diversity: Influence of Data on Detecting EEG Pathology with Advanced ML Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.SP","authors_text":"Jacek Rogala, Jaros{\\l}aw \\.Zygierewicz, Joanna Zych, Marian Dovgialo, Martyna Poziomska, Pawe{\\l} Niedbalski, Pawe{\\l} Ogniewski, Przemys{\\l}aw Olbratowski","submitted_at":"2024-11-13T16:15:48Z","abstract_excerpt":"This study investigates the impact of quantity and diversity of data on the performance of various machine-learning models for detecting general EEG pathology. We utilized an EEG dataset of 2,993 recordings from Temple University Hospital and a dataset of 55,787 recordings from Elmiko Biosignals sp. z o.o. The latter contains data from 39 hospitals and a diverse patient set with varied conditions. Thus, we introduce the Elmiko dataset - the largest publicly available EEG corpus. Our findings show that small and consistent datasets enable a wide range of models to achieve high accuracy; however"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17709","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/2411.17709/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":"2411.17709","created_at":"2026-07-05T09:41:05.432971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17709v1","created_at":"2026-07-05T09:41:05.432971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17709","created_at":"2026-07-05T09:41:05.432971+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAS6LAWNGSV5","created_at":"2026-07-05T09:41:05.432971+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAS6LAWNGSV57LZR","created_at":"2026-07-05T09:41:05.432971+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAS6LAWN","created_at":"2026-07-05T09:41:05.432971+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/VAS6LAWNGSV57LZRRSM2KTS6XM","json":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM.json","graph_json":"https://pith.science/api/pith-number/VAS6LAWNGSV57LZRRSM2KTS6XM/graph.json","events_json":"https://pith.science/api/pith-number/VAS6LAWNGSV57LZRRSM2KTS6XM/events.json","paper":"https://pith.science/paper/VAS6LAWN"},"agent_actions":{"view_html":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM","download_json":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM.json","view_paper":"https://pith.science/paper/VAS6LAWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17709&json=true","fetch_graph":"https://pith.science/api/pith-number/VAS6LAWNGSV57LZRRSM2KTS6XM/graph.json","fetch_events":"https://pith.science/api/pith-number/VAS6LAWNGSV57LZRRSM2KTS6XM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM/action/storage_attestation","attest_author":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM/action/author_attestation","sign_citation":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM/action/citation_signature","submit_replication":"https://pith.science/pith/VAS6LAWNGSV57LZRRSM2KTS6XM/action/replication_record"}},"created_at":"2026-07-05T09:41:05.432971+00:00","updated_at":"2026-07-05T09:41:05.432971+00:00"}