{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TQCJO6LFU7GH4B4TLQH3HMVWIQ","short_pith_number":"pith:TQCJO6LF","schema_version":"1.0","canonical_sha256":"9c04977965a7cc7e07935c0fb3b2b6441fb452931beb6072d1e4afee371899f7","source":{"kind":"arxiv","id":"2405.09017","version":1},"attestation_state":"computed","paper":{"title":"A Japanese-Chinese Parallel Corpus Using Crowdsourcing for Web Mining","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katsuki Chousa, Makoto Morishita, Masaaki Nagata, Norihito Yasuda","submitted_at":"2024-05-15T00:54:40Z","abstract_excerpt":"Using crowdsourcing, we collected more than 10,000 URL pairs (parallel top page pairs) of bilingual websites that contain parallel documents and created a Japanese-Chinese parallel corpus of 4.6M sentence pairs from these websites. We used a Japanese-Chinese bilingual dictionary of 160K word pairs for document and sentence alignment. We then used high-quality 1.2M Japanese-Chinese sentence pairs to train a parallel corpus filter based on statistical language models and word translation probabilities. We compared the translation accuracy of the model trained on these 4.6M sentence pairs with th"},"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":"2405.09017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-15T00:54:40Z","cross_cats_sorted":[],"title_canon_sha256":"6a1f3acb372e810cdb6f99499f99248cbd9569df52d5b53b4f1f41dd6f25a8e6","abstract_canon_sha256":"cc4f2a553a8b8497dac93491d6752283340b80accd96f9b22376238c6a9de638"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:11.832383Z","signature_b64":"e9dEyV/v1AhwNtejspWQh+FIqATJ+ZZCc7d7r2xpabUlvIkpZ2N61UHvo8d8VarEqZRN5dAP8obx9bNp6FkrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c04977965a7cc7e07935c0fb3b2b6441fb452931beb6072d1e4afee371899f7","last_reissued_at":"2026-07-05T08:19:11.831946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:11.831946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Japanese-Chinese Parallel Corpus Using Crowdsourcing for Web Mining","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katsuki Chousa, Makoto Morishita, Masaaki Nagata, Norihito Yasuda","submitted_at":"2024-05-15T00:54:40Z","abstract_excerpt":"Using crowdsourcing, we collected more than 10,000 URL pairs (parallel top page pairs) of bilingual websites that contain parallel documents and created a Japanese-Chinese parallel corpus of 4.6M sentence pairs from these websites. We used a Japanese-Chinese bilingual dictionary of 160K word pairs for document and sentence alignment. We then used high-quality 1.2M Japanese-Chinese sentence pairs to train a parallel corpus filter based on statistical language models and word translation probabilities. We compared the translation accuracy of the model trained on these 4.6M sentence pairs with th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09017","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/2405.09017/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":"2405.09017","created_at":"2026-07-05T08:19:11.832005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.09017v1","created_at":"2026-07-05T08:19:11.832005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09017","created_at":"2026-07-05T08:19:11.832005+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQCJO6LFU7GH","created_at":"2026-07-05T08:19:11.832005+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQCJO6LFU7GH4B4T","created_at":"2026-07-05T08:19:11.832005+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQCJO6LF","created_at":"2026-07-05T08:19:11.832005+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/TQCJO6LFU7GH4B4TLQH3HMVWIQ","json":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ.json","graph_json":"https://pith.science/api/pith-number/TQCJO6LFU7GH4B4TLQH3HMVWIQ/graph.json","events_json":"https://pith.science/api/pith-number/TQCJO6LFU7GH4B4TLQH3HMVWIQ/events.json","paper":"https://pith.science/paper/TQCJO6LF"},"agent_actions":{"view_html":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ","download_json":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ.json","view_paper":"https://pith.science/paper/TQCJO6LF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.09017&json=true","fetch_graph":"https://pith.science/api/pith-number/TQCJO6LFU7GH4B4TLQH3HMVWIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TQCJO6LFU7GH4B4TLQH3HMVWIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ/action/storage_attestation","attest_author":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ/action/author_attestation","sign_citation":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ/action/citation_signature","submit_replication":"https://pith.science/pith/TQCJO6LFU7GH4B4TLQH3HMVWIQ/action/replication_record"}},"created_at":"2026-07-05T08:19:11.832005+00:00","updated_at":"2026-07-05T08:19:11.832005+00:00"}