{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QAWYSO7HWVF5WKCMSFYJVTAW42","short_pith_number":"pith:QAWYSO7H","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"},"canonical_sha256":"802d893be7b54bdb284c91709acc16e6b69df4f88796308cfe4eefad0f8829de","source":{"kind":"arxiv","id":"2109.09700","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09700","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09700v1","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09700","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"QAWYSO7HWVF5","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"QAWYSO7HWVF5WKCM","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"QAWYSO7H","created_at":"2026-07-05T03:15:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QAWYSO7HWVF5WKCMSFYJVTAW42","target":"record","payload":{"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"},"canonical_sha256":"802d893be7b54bdb284c91709acc16e6b69df4f88796308cfe4eefad0f8829de","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"},"source_kind":"arxiv","source_id":"2109.09700","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bBLqbTrGmDD3U/TPgEcVtl6Bf4WqsRD6zYcLEzLnWl2LqUjgCAdmWGANKQNgHkqMVr7Z8OEWJ9cXQkSh6kJgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:11:04.581918Z"},"content_sha256":"6213e0e74f75989a84279ec1365a4f8a0869381d71a5584600dab79774ae4aa0","schema_version":"1.0","event_id":"sha256:6213e0e74f75989a84279ec1365a4f8a0869381d71a5584600dab79774ae4aa0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QAWYSO7HWVF5WKCMSFYJVTAW42","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wbk3P9tXZ/H+ycUceuEy4WSY9mCJU7qu6OwkwimmEvGIte8JqZbVFtZ6PEstuspVY3zJ9qF+1TciglVOoeGFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:11:04.582530Z"},"content_sha256":"015b54a2af47a3de87f1de38d61a5a658cb728d0de40d06e0f3943e4aa89edc5","schema_version":"1.0","event_id":"sha256:015b54a2af47a3de87f1de38d61a5a658cb728d0de40d06e0f3943e4aa89edc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/bundle.json","state_url":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T20:11:04Z","links":{"resolver":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42","bundle":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/bundle.json","state":"https://pith.science/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QAWYSO7HWVF5WKCMSFYJVTAW42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QAWYSO7HWVF5WKCMSFYJVTAW42","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2a05069762e451907381d8aa64eb4d57982748a2a0dc6daac71698e52f7376e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:10:49Z","title_canon_sha256":"bd854a293d5b8b656b1aaaeec79aa694e2024f05782c733771453c7cf14b66e3"},"schema_version":"1.0","source":{"id":"2109.09700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09700","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09700v1","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09700","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"QAWYSO7HWVF5","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"QAWYSO7HWVF5WKCM","created_at":"2026-07-05T03:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"QAWYSO7H","created_at":"2026-07-05T03:15:48Z"}],"graph_snapshots":[{"event_id":"sha256:015b54a2af47a3de87f1de38d61a5a658cb728d0de40d06e0f3943e4aa89edc5","target":"graph","created_at":"2026-07-05T03:15:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.09700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Antonis Maronikolakis, Hinrich Sch\\\"utze, Philipp Dufter","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:10:49Z","title":"BERT Cannot Align Characters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09700","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6213e0e74f75989a84279ec1365a4f8a0869381d71a5584600dab79774ae4aa0","target":"record","created_at":"2026-07-05T03:15:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2a05069762e451907381d8aa64eb4d57982748a2a0dc6daac71698e52f7376e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:10:49Z","title_canon_sha256":"bd854a293d5b8b656b1aaaeec79aa694e2024f05782c733771453c7cf14b66e3"},"schema_version":"1.0","source":{"id":"2109.09700","kind":"arxiv","version":1}},"canonical_sha256":"802d893be7b54bdb284c91709acc16e6b69df4f88796308cfe4eefad0f8829de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"802d893be7b54bdb284c91709acc16e6b69df4f88796308cfe4eefad0f8829de","first_computed_at":"2026-07-05T03:15:48.954325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:48.954325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YoBOO4vvS6nChbLanqHXhMXOS05uLM0zhfy35LtVn/4YuSEgoKRV1sr6oTkXydTAzeN/OpInQbQVMzPayfiDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:48.954745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6213e0e74f75989a84279ec1365a4f8a0869381d71a5584600dab79774ae4aa0","sha256:015b54a2af47a3de87f1de38d61a5a658cb728d0de40d06e0f3943e4aa89edc5"],"state_sha256":"466a8daf1ece55cfb9309dc1cec7f93b4692ce780fad2ca820c983aba36bec12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"13IesFy/qRJUKiuZf9YRx1995AJXKJBQUj4uEn36GoAu3pzJsWtGZd/cnaee24dzKWKGlVvjtHHqR6qbYag0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:11:04.587695Z","bundle_sha256":"a17c1af59e086a201cd1396f75b14a762eb4267e1cd643857572993861355080"}}