{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WVEGMW53IEKVFWEUQ4NI7ODQG6","short_pith_number":"pith:WVEGMW53","schema_version":"1.0","canonical_sha256":"b548665bbb411552d894871a8fb87037bb5fc6d0eb4f382b8c2726c3e6ae20e2","source":{"kind":"arxiv","id":"1902.08856","version":1},"attestation_state":"computed","paper":{"title":"ABI Neural Ensemble Model for Gender Prediction Adapt Bar-Ilan Submission for the CLIN29 Shared Task on Gender Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Amit Moryossef, Andy Way, Dimitar Shterionov, Eva Vanmassenhove","submitted_at":"2019-02-23T22:17:08Z","abstract_excerpt":"We present our system for the CLIN29 shared task on cross-genre gender detection for Dutch. We experimented with a multitude of neural models (CNN, RNN, LSTM, etc.), more \"traditional\" models (SVM, RF, LogReg, etc.), different feature sets as well as data pre-processing. The final results suggested that using tokenized, non-lowercased data works best for most of the neural models, while a combination of word clusters, character trigrams and word lists showed to be most beneficial for the majority of the more \"traditional\" (that is, non-neural) models, beating features used in previous tasks su"},"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":"1902.08856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-02-23T22:17:08Z","cross_cats_sorted":[],"title_canon_sha256":"5a5f3ed72f245c432248195048264e849b70bd5d717ef730cebd876ed018e645","abstract_canon_sha256":"ebd5737f797349cf8ca265bbfe4e27c8d12b5f8046f57d4ea66cd11d4e1a5f99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:49.679267Z","signature_b64":"LtN9WjoNAf9m7LcQuzyypxfCIQRZ3qT6/807P75AB8CGIp5SI08/yOSCEqKUp0B6zXMMs48zvrEWZk41/KNrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b548665bbb411552d894871a8fb87037bb5fc6d0eb4f382b8c2726c3e6ae20e2","last_reissued_at":"2026-05-17T23:52:49.678553Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:49.678553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ABI Neural Ensemble Model for Gender Prediction Adapt Bar-Ilan Submission for the CLIN29 Shared Task on Gender Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Amit Moryossef, Andy Way, Dimitar Shterionov, Eva Vanmassenhove","submitted_at":"2019-02-23T22:17:08Z","abstract_excerpt":"We present our system for the CLIN29 shared task on cross-genre gender detection for Dutch. We experimented with a multitude of neural models (CNN, RNN, LSTM, etc.), more \"traditional\" models (SVM, RF, LogReg, etc.), different feature sets as well as data pre-processing. The final results suggested that using tokenized, non-lowercased data works best for most of the neural models, while a combination of word clusters, character trigrams and word lists showed to be most beneficial for the majority of the more \"traditional\" (that is, non-neural) models, beating features used in previous tasks su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.08856","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":"1902.08856","created_at":"2026-05-17T23:52:49.678668+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.08856v1","created_at":"2026-05-17T23:52:49.678668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.08856","created_at":"2026-05-17T23:52:49.678668+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVEGMW53IEKV","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVEGMW53IEKVFWEU","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVEGMW53","created_at":"2026-05-18T12:33:33.725879+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/WVEGMW53IEKVFWEUQ4NI7ODQG6","json":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6.json","graph_json":"https://pith.science/api/pith-number/WVEGMW53IEKVFWEUQ4NI7ODQG6/graph.json","events_json":"https://pith.science/api/pith-number/WVEGMW53IEKVFWEUQ4NI7ODQG6/events.json","paper":"https://pith.science/paper/WVEGMW53"},"agent_actions":{"view_html":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6","download_json":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6.json","view_paper":"https://pith.science/paper/WVEGMW53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.08856&json=true","fetch_graph":"https://pith.science/api/pith-number/WVEGMW53IEKVFWEUQ4NI7ODQG6/graph.json","fetch_events":"https://pith.science/api/pith-number/WVEGMW53IEKVFWEUQ4NI7ODQG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6/action/storage_attestation","attest_author":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6/action/author_attestation","sign_citation":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6/action/citation_signature","submit_replication":"https://pith.science/pith/WVEGMW53IEKVFWEUQ4NI7ODQG6/action/replication_record"}},"created_at":"2026-05-17T23:52:49.678668+00:00","updated_at":"2026-05-17T23:52:49.678668+00:00"}