{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HW42DZ3E6EH3EOAMOZXUBDQVXO","short_pith_number":"pith:HW42DZ3E","schema_version":"1.0","canonical_sha256":"3db9a1e764f10fb2380c766f408e15bba71d06758208b0f7fa9e66be14a13072","source":{"kind":"arxiv","id":"1805.03122","version":1},"attestation_state":"computed","paper":{"title":"Bleaching Text: Abstract Features for Cross-lingual Gender Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Ian Matroos, Malvina Nissim, Nikola Ljube\\v{s}i\\'c, Rob van der Goot","submitted_at":"2018-05-08T15:50:32Z","abstract_excerpt":"Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations, but capture gender-specific style less. We propose an alternative: bleaching text, i.e., transforming lexical strings into more abstract features. This study provides evidence that such features allow for better transfer across languages. Moreover, we present a first study on the ability of humans to perform cross-lingual gender prediction. We find that human"},"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":"1805.03122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-08T15:50:32Z","cross_cats_sorted":[],"title_canon_sha256":"5954e32f13cf143681c7b82531662fc7f9d9a7aa267db5e0108a4b4e30eee631","abstract_canon_sha256":"0521cf1563c94ee15a30f7052b4cc63f4778e824ca6ecf3a5fced4caaa93213a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:34.546667Z","signature_b64":"uEVZXUucARW9a7Q5p+cNvSgTrlWfOpI3Vhmh1V8XFY+ua1U8Mf0DLKseq6gEFC6Q6dPkbpYuN1YSd4L6343mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3db9a1e764f10fb2380c766f408e15bba71d06758208b0f7fa9e66be14a13072","last_reissued_at":"2026-05-18T00:16:34.545960Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:34.545960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bleaching Text: Abstract Features for Cross-lingual Gender Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Ian Matroos, Malvina Nissim, Nikola Ljube\\v{s}i\\'c, Rob van der Goot","submitted_at":"2018-05-08T15:50:32Z","abstract_excerpt":"Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations, but capture gender-specific style less. We propose an alternative: bleaching text, i.e., transforming lexical strings into more abstract features. This study provides evidence that such features allow for better transfer across languages. Moreover, we present a first study on the ability of humans to perform cross-lingual gender prediction. We find that human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03122","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":"1805.03122","created_at":"2026-05-18T00:16:34.546065+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.03122v1","created_at":"2026-05-18T00:16:34.546065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03122","created_at":"2026-05-18T00:16:34.546065+00:00"},{"alias_kind":"pith_short_12","alias_value":"HW42DZ3E6EH3","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HW42DZ3E6EH3EOAM","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HW42DZ3E","created_at":"2026-05-18T12:32:28.185984+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/HW42DZ3E6EH3EOAMOZXUBDQVXO","json":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO.json","graph_json":"https://pith.science/api/pith-number/HW42DZ3E6EH3EOAMOZXUBDQVXO/graph.json","events_json":"https://pith.science/api/pith-number/HW42DZ3E6EH3EOAMOZXUBDQVXO/events.json","paper":"https://pith.science/paper/HW42DZ3E"},"agent_actions":{"view_html":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO","download_json":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO.json","view_paper":"https://pith.science/paper/HW42DZ3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.03122&json=true","fetch_graph":"https://pith.science/api/pith-number/HW42DZ3E6EH3EOAMOZXUBDQVXO/graph.json","fetch_events":"https://pith.science/api/pith-number/HW42DZ3E6EH3EOAMOZXUBDQVXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/action/storage_attestation","attest_author":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/action/author_attestation","sign_citation":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/action/citation_signature","submit_replication":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/action/replication_record"}},"created_at":"2026-05-18T00:16:34.546065+00:00","updated_at":"2026-05-18T00:16:34.546065+00:00"}