{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QAWYSO7HWVF5WKCMSFYJVTAW42","short_pith_number":"pith:QAWYSO7H","schema_version":"1.0","canonical_sha256":"802d893be7b54bdb284c91709acc16e6b69df4f88796308cfe4eefad0f8829de","source":{"kind":"arxiv","id":"2109.09700","version":1},"attestation_state":"computed","paper":{"title":"BERT Cannot Align Characters","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Antonis Maronikolakis, Hinrich Sch\\\"utze, Philipp Dufter","submitted_at":"2021-09-20T17:10:49Z","abstract_excerpt":"In previous work, it has been shown that BERT can adequately align cross-lingual sentences on the word level. Here we investigate whether BERT can also operate as a char-level aligner. The languages examined are English, Fake-English, German and Greek. We show that the closer two languages are, the better BERT can align them on the character level. BERT indeed works well in English to Fake-English alignment, but this does not generalize to natural languages to the same extent. Nevertheless, the proximity of two languages does seem to be a factor. English is more related to German than to Greek"},"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":"2109.09700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:10:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd854a293d5b8b656b1aaaeec79aa694e2024f05782c733771453c7cf14b66e3","abstract_canon_sha256":"2a05069762e451907381d8aa64eb4d57982748a2a0dc6daac71698e52f7376e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:48.954745Z","signature_b64":"YoBOO4vvS6nChbLanqHXhMXOS05uLM0zhfy35LtVn/4YuSEgoKRV1sr6oTkXydTAzeN/OpInQbQVMzPayfiDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"802d893be7b54bdb284c91709acc16e6b69df4f88796308cfe4eefad0f8829de","last_reissued_at":"2026-07-05T03:15:48.954325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:48.954325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERT Cannot Align Characters","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Antonis Maronikolakis, Hinrich Sch\\\"utze, Philipp Dufter","submitted_at":"2021-09-20T17:10:49Z","abstract_excerpt":"In previous work, it has been shown that BERT can adequately align cross-lingual sentences on the word level. Here we investigate whether BERT can also operate as a char-level aligner. The languages examined are English, Fake-English, German and Greek. We show that the closer two languages are, the better BERT can align them on the character level. BERT indeed works well in English to Fake-English alignment, but this does not generalize to natural languages to the same extent. Nevertheless, the proximity of two languages does seem to be a factor. English is more related to German than to Greek"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09700","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/2109.09700/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":"2109.09700","created_at":"2026-07-05T03:15:48.954381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09700v1","created_at":"2026-07-05T03:15:48.954381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09700","created_at":"2026-07-05T03:15:48.954381+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAWYSO7HWVF5","created_at":"2026-07-05T03:15:48.954381+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAWYSO7HWVF5WKCM","created_at":"2026-07-05T03:15:48.954381+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAWYSO7H","created_at":"2026-07-05T03:15:48.954381+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/QAWYSO7HWVF5WKCMSFYJVTAW42","json":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42.json","graph_json":"https://pith.science/api/pith-number/QAWYSO7HWVF5WKCMSFYJVTAW42/graph.json","events_json":"https://pith.science/api/pith-number/QAWYSO7HWVF5WKCMSFYJVTAW42/events.json","paper":"https://pith.science/paper/QAWYSO7H"},"agent_actions":{"view_html":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42","download_json":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42.json","view_paper":"https://pith.science/paper/QAWYSO7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09700&json=true","fetch_graph":"https://pith.science/api/pith-number/QAWYSO7HWVF5WKCMSFYJVTAW42/graph.json","fetch_events":"https://pith.science/api/pith-number/QAWYSO7HWVF5WKCMSFYJVTAW42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/action/storage_attestation","attest_author":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/action/author_attestation","sign_citation":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/action/citation_signature","submit_replication":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/action/replication_record"}},"created_at":"2026-07-05T03:15:48.954381+00:00","updated_at":"2026-07-05T03:15:48.954381+00:00"}