{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:VNG6AKJSTPFUZH35KFZUOTFU3I","short_pith_number":"pith:VNG6AKJS","canonical_record":{"source":{"id":"2004.14516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"3f9522a8947001da0743aa289146fba34c47194fd72fa9433304cef27433003b","abstract_canon_sha256":"b57775defd1380acadc074ac46a70c2d284aa78b48af43a2acf341c9ee23bbe4"},"schema_version":"1.0"},"canonical_sha256":"ab4de029329bcb4c9f7d5173474cb4da3a9a4746a110c395e3da3d9c029c350e","source":{"kind":"arxiv","id":"2004.14516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14516","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14516v1","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14516","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"VNG6AKJSTPFU","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"VNG6AKJSTPFUZH35","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"VNG6AKJS","created_at":"2026-07-05T00:59:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:VNG6AKJSTPFUZH35KFZUOTFU3I","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"3f9522a8947001da0743aa289146fba34c47194fd72fa9433304cef27433003b","abstract_canon_sha256":"b57775defd1380acadc074ac46a70c2d284aa78b48af43a2acf341c9ee23bbe4"},"schema_version":"1.0"},"canonical_sha256":"ab4de029329bcb4c9f7d5173474cb4da3a9a4746a110c395e3da3d9c029c350e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:27.003763Z","signature_b64":"5GismmEWuoMIxCcavIdSfDj6pBKjhRi504nl0oxy0qJx+xNRadgihETBgG7kMtAbLMPTUuCjqMY69Bgn2Ci2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab4de029329bcb4c9f7d5173474cb4da3a9a4746a110c395e3da3d9c029c350e","last_reissued_at":"2026-07-05T00:59:27.003423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:27.003423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14516","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":"2026-07-05T00:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubnhBcsDwIqDwNzdDJdnlnuD7sOCY3lcGstxR9WIbM5C+hGI2+tmCZHZyx7QDqeUXtClTKReqRHsOpUyWVEKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:00:19.029329Z"},"content_sha256":"6048092febbf72d906948d60e02885116933ed5ed613f5c03a314fc07016f556","schema_version":"1.0","event_id":"sha256:6048092febbf72d906948d60e02885116933ed5ed613f5c03a314fc07016f556"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:VNG6AKJSTPFUZH35KFZUOTFU3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chousa Katsuki, Masaaki Nagata, Masaaki Nishino","submitted_at":"2020-04-29T23:40:08Z","abstract_excerpt":"We present a novel supervised word alignment method based on cross-language span prediction. We first formalize a word alignment problem as a collection of independent predictions from a token in the source sentence to a span in the target sentence. As this is equivalent to a SQuAD v2.0 style question answering task, we then solve this problem by using multilingual BERT, which is fine-tuned on a manually created gold word alignment data. We greatly improved the word alignment accuracy by adding the context of the token to the question. In the experiments using five word alignment datasets amon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14516","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/2004.14516/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":"2026-07-05T00:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+hRREY10w/JLCmVpsX+SS3L69LwvVOa1lcNDQ9zs4t3N+Rhhdox0iNEeBsDmWQJ/RdS7JsDn4dZ5FW8VKSxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:00:19.029862Z"},"content_sha256":"56c5bb5e89e687474f5671efba8ddcd4b3b6d72511819675d9063042bb13478b","schema_version":"1.0","event_id":"sha256:56c5bb5e89e687474f5671efba8ddcd4b3b6d72511819675d9063042bb13478b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNG6AKJSTPFUZH35KFZUOTFU3I/bundle.json","state_url":"https://pith.science/pith/VNG6AKJSTPFUZH35KFZUOTFU3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNG6AKJSTPFUZH35KFZUOTFU3I/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":"2026-08-19T08:00:19Z","links":{"resolver":"https://pith.science/pith/VNG6AKJSTPFUZH35KFZUOTFU3I","bundle":"https://pith.science/pith/VNG6AKJSTPFUZH35KFZUOTFU3I/bundle.json","state":"https://pith.science/pith/VNG6AKJSTPFUZH35KFZUOTFU3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNG6AKJSTPFUZH35KFZUOTFU3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VNG6AKJSTPFUZH35KFZUOTFU3I","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":"b57775defd1380acadc074ac46a70c2d284aa78b48af43a2acf341c9ee23bbe4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:40:08Z","title_canon_sha256":"3f9522a8947001da0743aa289146fba34c47194fd72fa9433304cef27433003b"},"schema_version":"1.0","source":{"id":"2004.14516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14516","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14516v1","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14516","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"VNG6AKJSTPFU","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"VNG6AKJSTPFUZH35","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"VNG6AKJS","created_at":"2026-07-05T00:59:27Z"}],"graph_snapshots":[{"event_id":"sha256:56c5bb5e89e687474f5671efba8ddcd4b3b6d72511819675d9063042bb13478b","target":"graph","created_at":"2026-07-05T00:59:27Z","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/2004.14516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel supervised word alignment method based on cross-language span prediction. We first formalize a word alignment problem as a collection of independent predictions from a token in the source sentence to a span in the target sentence. As this is equivalent to a SQuAD v2.0 style question answering task, we then solve this problem by using multilingual BERT, which is fine-tuned on a manually created gold word alignment data. We greatly improved the word alignment accuracy by adding the context of the token to the question. In the experiments using five word alignment datasets amon","authors_text":"Chousa Katsuki, Masaaki Nagata, Masaaki Nishino","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:40:08Z","title":"A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14516","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":"sha256:6048092febbf72d906948d60e02885116933ed5ed613f5c03a314fc07016f556","target":"record","created_at":"2026-07-05T00:59:27Z","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":"b57775defd1380acadc074ac46a70c2d284aa78b48af43a2acf341c9ee23bbe4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:40:08Z","title_canon_sha256":"3f9522a8947001da0743aa289146fba34c47194fd72fa9433304cef27433003b"},"schema_version":"1.0","source":{"id":"2004.14516","kind":"arxiv","version":1}},"canonical_sha256":"ab4de029329bcb4c9f7d5173474cb4da3a9a4746a110c395e3da3d9c029c350e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab4de029329bcb4c9f7d5173474cb4da3a9a4746a110c395e3da3d9c029c350e","first_computed_at":"2026-07-05T00:59:27.003423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:27.003423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5GismmEWuoMIxCcavIdSfDj6pBKjhRi504nl0oxy0qJx+xNRadgihETBgG7kMtAbLMPTUuCjqMY69Bgn2Ci2DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:27.003763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6048092febbf72d906948d60e02885116933ed5ed613f5c03a314fc07016f556","sha256:56c5bb5e89e687474f5671efba8ddcd4b3b6d72511819675d9063042bb13478b"],"state_sha256":"1c6c4afca6199e2aaf24193b4b4ac22db3822c90758b7aee6835b3f980d7bb40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2M65UHxWQJFlmU/J34eo3LMACw8LsmnLDjowdIkkTzeagQwax5wyX/15aFwVyjqTa5w2vC6g/GAhS8Q7DDyFAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:00:19.035268Z","bundle_sha256":"60b00205d7d815311a8f112c6d7b3c5318952cdd5c9b3880c175225a42bc4712"}}