{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z5HBZJHH5N6HTDN3AHK3R2VJ5Z","short_pith_number":"pith:Z5HBZJHH","schema_version":"1.0","canonical_sha256":"cf4e1ca4e7eb7c798dbb01d5b8eaa9ee7a962c02593b529829958e370ec547c3","source":{"kind":"arxiv","id":"2401.07923","version":2},"attestation_state":"computed","paper":{"title":"Word Boundary Information Isn't Useful for Encoder Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aline Villavicencio, Carolina Scarton, Dylan Phelps, Edward Gow-Smith, Harish Tayyar Madabushi","submitted_at":"2024-01-15T19:21:08Z","abstract_excerpt":"All existing transformer-based approaches to NLP using subword tokenisation algorithms encode whitespace (word boundary information) through the use of special space symbols (such as \\#\\# or \\_) forming part of tokens. These symbols have been shown to a) lead to reduced morphological validity of tokenisations, and b) give substantial vocabulary redundancy. As such, removing these symbols has been shown to have a beneficial effect on the processing of morphologically complex words for transformer encoders in the pretrain-finetune paradigm. In this work, we explore whether word boundary informat"},"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":"2401.07923","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T19:21:08Z","cross_cats_sorted":[],"title_canon_sha256":"eccdb85ffc6e6299a08c219b070e39d4da4ec1fba8f3e07675036300c7ecf271","abstract_canon_sha256":"564d42c9417cc422fca2ec2560a1a8954ac561cb8d778afd1b9dcd46c97ad662"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:02.406088Z","signature_b64":"9S6XFzb4VgBgh53708Id/UJhyDNXIs3VfZD5omxmatXsrG+N2wH1RJ7nBPvWeCdgeRR3NzGqR+7x7lDC/PlrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf4e1ca4e7eb7c798dbb01d5b8eaa9ee7a962c02593b529829958e370ec547c3","last_reissued_at":"2026-07-05T10:21:02.405612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:02.405612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Word Boundary Information Isn't Useful for Encoder Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aline Villavicencio, Carolina Scarton, Dylan Phelps, Edward Gow-Smith, Harish Tayyar Madabushi","submitted_at":"2024-01-15T19:21:08Z","abstract_excerpt":"All existing transformer-based approaches to NLP using subword tokenisation algorithms encode whitespace (word boundary information) through the use of special space symbols (such as \\#\\# or \\_) forming part of tokens. These symbols have been shown to a) lead to reduced morphological validity of tokenisations, and b) give substantial vocabulary redundancy. As such, removing these symbols has been shown to have a beneficial effect on the processing of morphologically complex words for transformer encoders in the pretrain-finetune paradigm. In this work, we explore whether word boundary informat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07923","kind":"arxiv","version":2},"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/2401.07923/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":"2401.07923","created_at":"2026-07-05T10:21:02.405666+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07923v2","created_at":"2026-07-05T10:21:02.405666+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07923","created_at":"2026-07-05T10:21:02.405666+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5HBZJHH5N6H","created_at":"2026-07-05T10:21:02.405666+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5HBZJHH5N6HTDN3","created_at":"2026-07-05T10:21:02.405666+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5HBZJHH","created_at":"2026-07-05T10:21:02.405666+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/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z","json":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z.json","graph_json":"https://pith.science/api/pith-number/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/graph.json","events_json":"https://pith.science/api/pith-number/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/events.json","paper":"https://pith.science/paper/Z5HBZJHH"},"agent_actions":{"view_html":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z","download_json":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z.json","view_paper":"https://pith.science/paper/Z5HBZJHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07923&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/action/storage_attestation","attest_author":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/action/author_attestation","sign_citation":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/action/citation_signature","submit_replication":"https://pith.science/pith/Z5HBZJHH5N6HTDN3AHK3R2VJ5Z/action/replication_record"}},"created_at":"2026-07-05T10:21:02.405666+00:00","updated_at":"2026-07-05T10:21:02.405666+00:00"}