{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TQCJO6LFU7GH4B4TLQH3HMVWIQ","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":"cc4f2a553a8b8497dac93491d6752283340b80accd96f9b22376238c6a9de638","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-15T00:54:40Z","title_canon_sha256":"6a1f3acb372e810cdb6f99499f99248cbd9569df52d5b53b4f1f41dd6f25a8e6"},"schema_version":"1.0","source":{"id":"2405.09017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09017","created_at":"2026-07-05T08:19:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09017v1","created_at":"2026-07-05T08:19:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09017","created_at":"2026-07-05T08:19:11Z"},{"alias_kind":"pith_short_12","alias_value":"TQCJO6LFU7GH","created_at":"2026-07-05T08:19:11Z"},{"alias_kind":"pith_short_16","alias_value":"TQCJO6LFU7GH4B4T","created_at":"2026-07-05T08:19:11Z"},{"alias_kind":"pith_short_8","alias_value":"TQCJO6LF","created_at":"2026-07-05T08:19:11Z"}],"graph_snapshots":[{"event_id":"sha256:34259625ec2a8817312f5a9b719e2cb078f17d9842e79a065ee9cedf31f474a5","target":"graph","created_at":"2026-07-05T08:19:11Z","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/2405.09017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Katsuki Chousa, Makoto Morishita, Masaaki Nagata, Norihito Yasuda","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-15T00:54:40Z","title":"A Japanese-Chinese Parallel Corpus Using Crowdsourcing for Web Mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09017","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:d41e6cec38847e324be83ea6e513fcc25f1a1b4cb138f2cb70f1f4370683968b","target":"record","created_at":"2026-07-05T08:19:11Z","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":"cc4f2a553a8b8497dac93491d6752283340b80accd96f9b22376238c6a9de638","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-15T00:54:40Z","title_canon_sha256":"6a1f3acb372e810cdb6f99499f99248cbd9569df52d5b53b4f1f41dd6f25a8e6"},"schema_version":"1.0","source":{"id":"2405.09017","kind":"arxiv","version":1}},"canonical_sha256":"9c04977965a7cc7e07935c0fb3b2b6441fb452931beb6072d1e4afee371899f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c04977965a7cc7e07935c0fb3b2b6441fb452931beb6072d1e4afee371899f7","first_computed_at":"2026-07-05T08:19:11.831946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:11.831946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e9dEyV/v1AhwNtejspWQh+FIqATJ+ZZCc7d7r2xpabUlvIkpZ2N61UHvo8d8VarEqZRN5dAP8obx9bNp6FkrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:11.832383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.09017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d41e6cec38847e324be83ea6e513fcc25f1a1b4cb138f2cb70f1f4370683968b","sha256:34259625ec2a8817312f5a9b719e2cb078f17d9842e79a065ee9cedf31f474a5"],"state_sha256":"12b76c17e333a0c26410471ed655501e582415cad422ef11c7aaa7d678a4ed9d"}