{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EDWO2H7XOYOJNPPAA654Y7UIRV","short_pith_number":"pith:EDWO2H7X","canonical_record":{"source":{"id":"2202.12607","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-25T10:52:00Z","cross_cats_sorted":[],"title_canon_sha256":"07c83516f26550f764c626b284a30f5dd8396cca92ce8d033c4b0f73e8bee0f2","abstract_canon_sha256":"5c864bd60aed5e578a4bb08db83099dfb6e283a5958173113021c6c3599f52e8"},"schema_version":"1.0"},"canonical_sha256":"20eced1ff7761c96bde007bbcc7e888d7d5b2d59c6022b5b718b1f1025e24eb0","source":{"kind":"arxiv","id":"2202.12607","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.12607","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2202.12607v2","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12607","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"EDWO2H7XOYOJ","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"EDWO2H7XOYOJNPPA","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"EDWO2H7X","created_at":"2026-07-05T04:00:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EDWO2H7XOYOJNPPAA654Y7UIRV","target":"record","payload":{"canonical_record":{"source":{"id":"2202.12607","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-25T10:52:00Z","cross_cats_sorted":[],"title_canon_sha256":"07c83516f26550f764c626b284a30f5dd8396cca92ce8d033c4b0f73e8bee0f2","abstract_canon_sha256":"5c864bd60aed5e578a4bb08db83099dfb6e283a5958173113021c6c3599f52e8"},"schema_version":"1.0"},"canonical_sha256":"20eced1ff7761c96bde007bbcc7e888d7d5b2d59c6022b5b718b1f1025e24eb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:23.731222Z","signature_b64":"rXM/pj6t+xXJdB743wvyAv0/N6pcigRAKZNMwin5gV0CTdBbR6fJqp6oGPNxq/Ob703q/ij72rpA3InMvX7/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20eced1ff7761c96bde007bbcc7e888d7d5b2d59c6022b5b718b1f1025e24eb0","last_reissued_at":"2026-07-05T04:00:23.730733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:23.730733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.12607","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gmy2eS1BeBBUtZBhaCtLMFEHq466rb0OFLpMCb7N0o8i9G5FoDJsjeK17l+tzzp+jpXRWlbye5jHbtjD6JvnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:49:08.589283Z"},"content_sha256":"da0d775c08ac3214d4929f073859142ba52b97276064734276a6ee688669f3a9","schema_version":"1.0","event_id":"sha256:da0d775c08ac3214d4929f073859142ba52b97276064734276a6ee688669f3a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EDWO2H7XOYOJNPPAA654Y7UIRV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Suzuki, Katsuki Chousa, Makoto Morishita, Masaaki Nagata","submitted_at":"2022-02-25T10:52:00Z","abstract_excerpt":"Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora. Although there are billions of parallel sentences for a few language pairs, effectively dealing with most language pairs is difficult due to a lack of publicly available parallel corpora. This paper creates a large parallel corpus for English-Japanese, a language pair for which only limited resources are available, compared to such resource-rich languages as English-German. It introduces a new web-based English-Japanese par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12607","kind":"arxiv","version":2},"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/2202.12607/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":"2026-07-05T04:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STAFdIEWkpDSzoZf2W6uj7KFFbMgSaY/0HL9fM3jQdUApkRCUn+QjVHwxKEkqyih3PsQykTaBva+CaDpufDWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:49:08.589845Z"},"content_sha256":"ec42173721a9cbc96106f83d7e7f5ca17c4e42a648c3032f8f0c25968a0eb2d6","schema_version":"1.0","event_id":"sha256:ec42173721a9cbc96106f83d7e7f5ca17c4e42a648c3032f8f0c25968a0eb2d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDWO2H7XOYOJNPPAA654Y7UIRV/bundle.json","state_url":"https://pith.science/pith/EDWO2H7XOYOJNPPAA654Y7UIRV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDWO2H7XOYOJNPPAA654Y7UIRV/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":"2026-08-05T08:49:08Z","links":{"resolver":"https://pith.science/pith/EDWO2H7XOYOJNPPAA654Y7UIRV","bundle":"https://pith.science/pith/EDWO2H7XOYOJNPPAA654Y7UIRV/bundle.json","state":"https://pith.science/pith/EDWO2H7XOYOJNPPAA654Y7UIRV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDWO2H7XOYOJNPPAA654Y7UIRV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EDWO2H7XOYOJNPPAA654Y7UIRV","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":"5c864bd60aed5e578a4bb08db83099dfb6e283a5958173113021c6c3599f52e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-25T10:52:00Z","title_canon_sha256":"07c83516f26550f764c626b284a30f5dd8396cca92ce8d033c4b0f73e8bee0f2"},"schema_version":"1.0","source":{"id":"2202.12607","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.12607","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2202.12607v2","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12607","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"EDWO2H7XOYOJ","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"EDWO2H7XOYOJNPPA","created_at":"2026-07-05T04:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"EDWO2H7X","created_at":"2026-07-05T04:00:23Z"}],"graph_snapshots":[{"event_id":"sha256:ec42173721a9cbc96106f83d7e7f5ca17c4e42a648c3032f8f0c25968a0eb2d6","target":"graph","created_at":"2026-07-05T04:00:23Z","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/2202.12607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most current machine translation models are mainly trained with parallel corpora, and their translation accuracy largely depends on the quality and quantity of the corpora. Although there are billions of parallel sentences for a few language pairs, effectively dealing with most language pairs is difficult due to a lack of publicly available parallel corpora. This paper creates a large parallel corpus for English-Japanese, a language pair for which only limited resources are available, compared to such resource-rich languages as English-German. It introduces a new web-based English-Japanese par","authors_text":"Jun Suzuki, Katsuki Chousa, Makoto Morishita, Masaaki Nagata","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-25T10:52:00Z","title":"JParaCrawl v3.0: A Large-scale English-Japanese Parallel Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12607","kind":"arxiv","version":2},"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:da0d775c08ac3214d4929f073859142ba52b97276064734276a6ee688669f3a9","target":"record","created_at":"2026-07-05T04:00:23Z","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":"5c864bd60aed5e578a4bb08db83099dfb6e283a5958173113021c6c3599f52e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-25T10:52:00Z","title_canon_sha256":"07c83516f26550f764c626b284a30f5dd8396cca92ce8d033c4b0f73e8bee0f2"},"schema_version":"1.0","source":{"id":"2202.12607","kind":"arxiv","version":2}},"canonical_sha256":"20eced1ff7761c96bde007bbcc7e888d7d5b2d59c6022b5b718b1f1025e24eb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20eced1ff7761c96bde007bbcc7e888d7d5b2d59c6022b5b718b1f1025e24eb0","first_computed_at":"2026-07-05T04:00:23.730733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:00:23.730733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rXM/pj6t+xXJdB743wvyAv0/N6pcigRAKZNMwin5gV0CTdBbR6fJqp6oGPNxq/Ob703q/ij72rpA3InMvX7/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:00:23.731222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.12607","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da0d775c08ac3214d4929f073859142ba52b97276064734276a6ee688669f3a9","sha256:ec42173721a9cbc96106f83d7e7f5ca17c4e42a648c3032f8f0c25968a0eb2d6"],"state_sha256":"0c6e52de2b08a6b42120a16ffd590c3c088c90d5aa8dcc0f6f5eef56d6d6d98d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CTwGNlWXIrdnDUhLbcXey3Py8cxjKcKDx9gvhXsnVJZW+X4gU4P7jY9Wgq5tTmMdqYUVwZcUBU+FehLVtWlaAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:49:08.594520Z","bundle_sha256":"81994de08a5d5380e75687271e01da18511edbb72e9b61f1c70d8f69d793f177"}}