{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OVCO3TIYBRZSI4O3HVN5HC2OJN","short_pith_number":"pith:OVCO3TIY","canonical_record":{"source":{"id":"2004.14517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:41:32Z","cross_cats_sorted":[],"title_canon_sha256":"864ca0d9ffb36f391a0c7afc303e3f4c28537713e660addc069557d5fe4ee6f5","abstract_canon_sha256":"a7cdb79dddbcec18015eb5107bf1f9f2d561e1441e3e027b33869d7c93ad3e5a"},"schema_version":"1.0"},"canonical_sha256":"7544edcd180c732471db3d5bd38b4e4b57d4ca9f92791bf5521fd3c0be8d084f","source":{"kind":"arxiv","id":"2004.14517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14517","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14517v1","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14517","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"OVCO3TIYBRZS","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"OVCO3TIYBRZSI4O3","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"OVCO3TIY","created_at":"2026-07-05T00:59:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OVCO3TIYBRZSI4O3HVN5HC2OJN","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:41:32Z","cross_cats_sorted":[],"title_canon_sha256":"864ca0d9ffb36f391a0c7afc303e3f4c28537713e660addc069557d5fe4ee6f5","abstract_canon_sha256":"a7cdb79dddbcec18015eb5107bf1f9f2d561e1441e3e027b33869d7c93ad3e5a"},"schema_version":"1.0"},"canonical_sha256":"7544edcd180c732471db3d5bd38b4e4b57d4ca9f92791bf5521fd3c0be8d084f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:27.022534Z","signature_b64":"UDP/cK0d6im4QiXPxqcfOWyuKh/Jq+4GzE5fPtDnQ+EDM6rlC7A0FJZAAblwODlgEa7yUh32zn08QuA7xhAWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7544edcd180c732471db3d5bd38b4e4b57d4ca9f92791bf5521fd3c0be8d084f","last_reissued_at":"2026-07-05T00:59:27.022190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:27.022190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14517","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":"yj82UNu/2WYNXOo3kxjY/dSvV7wACD4TQi8yKZRwb220BIF27C+uA+xuYSdOeMHHlEJIsBHNIP/wx7g60svoAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:43:57.933967Z"},"content_sha256":"979196ccdf2a2135832716fefe733d423bbaff9ef8230a6d947210f7b6adac01","schema_version":"1.0","event_id":"sha256:979196ccdf2a2135832716fefe733d423bbaff9ef8230a6d947210f7b6adac01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OVCO3TIYBRZSI4O3HVN5HC2OJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bilingual Text Extraction as Reading Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katsuki Chousa, Masaaki Nagata, Masaaki Nishino","submitted_at":"2020-04-29T23:41:32Z","abstract_excerpt":"In this paper, we propose a method to extract bilingual texts automatically from noisy parallel corpora by framing the problem as a token-level span prediction, such as SQuAD-style Reading Comprehension. To extract a span of the target document that is a translation of a given source sentence (span), we use either QANet or multilingual BERT. QANet can be trained for a specific parallel corpus from scratch, while multilingual BERT can utilize pre-trained multilingual representations. For the span prediction method using QANet, we introduce a total optimization method using integer linear progra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14517","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/2004.14517/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":"U869d/wgOxNMNoNM18ma2DqPgZCxL+Xfj4Z+bS3CswLPgbVaIKWhX1iI4p1kCVxfOSsZIIMzRXL9OUTSkIVLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:43:57.934763Z"},"content_sha256":"1f3412fad666154d507a003c3bca91002ece352fb2401e3c496663067d3f35fb","schema_version":"1.0","event_id":"sha256:1f3412fad666154d507a003c3bca91002ece352fb2401e3c496663067d3f35fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVCO3TIYBRZSI4O3HVN5HC2OJN/bundle.json","state_url":"https://pith.science/pith/OVCO3TIYBRZSI4O3HVN5HC2OJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVCO3TIYBRZSI4O3HVN5HC2OJN/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":"2026-08-20T07:43:57Z","links":{"resolver":"https://pith.science/pith/OVCO3TIYBRZSI4O3HVN5HC2OJN","bundle":"https://pith.science/pith/OVCO3TIYBRZSI4O3HVN5HC2OJN/bundle.json","state":"https://pith.science/pith/OVCO3TIYBRZSI4O3HVN5HC2OJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVCO3TIYBRZSI4O3HVN5HC2OJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OVCO3TIYBRZSI4O3HVN5HC2OJN","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":"a7cdb79dddbcec18015eb5107bf1f9f2d561e1441e3e027b33869d7c93ad3e5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:41:32Z","title_canon_sha256":"864ca0d9ffb36f391a0c7afc303e3f4c28537713e660addc069557d5fe4ee6f5"},"schema_version":"1.0","source":{"id":"2004.14517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14517","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14517v1","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14517","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"OVCO3TIYBRZS","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"OVCO3TIYBRZSI4O3","created_at":"2026-07-05T00:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"OVCO3TIY","created_at":"2026-07-05T00:59:27Z"}],"graph_snapshots":[{"event_id":"sha256:1f3412fad666154d507a003c3bca91002ece352fb2401e3c496663067d3f35fb","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/2004.14517/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a method to extract bilingual texts automatically from noisy parallel corpora by framing the problem as a token-level span prediction, such as SQuAD-style Reading Comprehension. To extract a span of the target document that is a translation of a given source sentence (span), we use either QANet or multilingual BERT. QANet can be trained for a specific parallel corpus from scratch, while multilingual BERT can utilize pre-trained multilingual representations. For the span prediction method using QANet, we introduce a total optimization method using integer linear progra","authors_text":"Katsuki Chousa, Masaaki Nagata, Masaaki Nishino","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:41:32Z","title":"Bilingual Text Extraction as Reading Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14517","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":"sha256:979196ccdf2a2135832716fefe733d423bbaff9ef8230a6d947210f7b6adac01","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":"a7cdb79dddbcec18015eb5107bf1f9f2d561e1441e3e027b33869d7c93ad3e5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T23:41:32Z","title_canon_sha256":"864ca0d9ffb36f391a0c7afc303e3f4c28537713e660addc069557d5fe4ee6f5"},"schema_version":"1.0","source":{"id":"2004.14517","kind":"arxiv","version":1}},"canonical_sha256":"7544edcd180c732471db3d5bd38b4e4b57d4ca9f92791bf5521fd3c0be8d084f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7544edcd180c732471db3d5bd38b4e4b57d4ca9f92791bf5521fd3c0be8d084f","first_computed_at":"2026-07-05T00:59:27.022190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:27.022190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UDP/cK0d6im4QiXPxqcfOWyuKh/Jq+4GzE5fPtDnQ+EDM6rlC7A0FJZAAblwODlgEa7yUh32zn08QuA7xhAWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:27.022534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:979196ccdf2a2135832716fefe733d423bbaff9ef8230a6d947210f7b6adac01","sha256:1f3412fad666154d507a003c3bca91002ece352fb2401e3c496663067d3f35fb"],"state_sha256":"3879b3e2a28563f9db62f5062030683ec22492bffbaa3a60be90c06dc706d1b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IWxC1Eqh1rXwS77Ia+L4ev837cu15AOn+s/wKeyacBlerrZxxdKH7Q6+/6tD6jsfbrbXvJl4duMcVnIj5qi8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:43:57.940716Z","bundle_sha256":"90723cf2512b839c23822051e4d8f89e7e8ade048cfdf2c4a0a7949038a0c485"}}