{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6WOJKTA2ZKX5RWQ2IYKJH53WG5","short_pith_number":"pith:6WOJKTA2","canonical_record":{"source":{"id":"1911.04944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T12:09:46Z","cross_cats_sorted":[],"title_canon_sha256":"83710c6228cab645a4903186ff8353d31272445296ad41a818e58c52d1846af4","abstract_canon_sha256":"dab367d1031c9d34eed189ef0b8226f82c57edef34f6a6c9d5c6fb7d24616987"},"schema_version":"1.0"},"canonical_sha256":"f59c954c1acaafd8da1a461493f7763757fb60ea1ddda6b2eaa55ddc14265a35","source":{"kind":"arxiv","id":"1911.04944","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.04944","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"1911.04944v2","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04944","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"6WOJKTA2ZKX5","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"6WOJKTA2ZKX5RWQ2","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"6WOJKTA2","created_at":"2026-07-05T00:59:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6WOJKTA2ZKX5RWQ2IYKJH53WG5","target":"record","payload":{"canonical_record":{"source":{"id":"1911.04944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T12:09:46Z","cross_cats_sorted":[],"title_canon_sha256":"83710c6228cab645a4903186ff8353d31272445296ad41a818e58c52d1846af4","abstract_canon_sha256":"dab367d1031c9d34eed189ef0b8226f82c57edef34f6a6c9d5c6fb7d24616987"},"schema_version":"1.0"},"canonical_sha256":"f59c954c1acaafd8da1a461493f7763757fb60ea1ddda6b2eaa55ddc14265a35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:34.562838Z","signature_b64":"MKZpBUh9Rp70MNHzR8eV3vwyO9l6NAUupm3gI1vWnb8WJqmhFLH7ZIahM4RK7ANdDuz9wR6CmCdJ1D+vGnpUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f59c954c1acaafd8da1a461493f7763757fb60ea1ddda6b2eaa55ddc14265a35","last_reissued_at":"2026-07-05T00:59:34.562378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:34.562378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.04944","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":"2026-07-05T00:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uKQFEkNU1RZcFxJFtgBlR4FczwMuty1FTwMGY/i357vct5/AU2BiSODiGuw2Z1ksrZ/+d3xaJpfrUxPMRk0KBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:30:38.459744Z"},"content_sha256":"e470fcc121285dc4279ffcce5db985f559d2568a353bf8c6ab3ab1c6165cb591","schema_version":"1.0","event_id":"sha256:e470fcc121285dc4279ffcce5db985f559d2568a353bf8c6ab3ab1c6165cb591"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6WOJKTA2ZKX5RWQ2IYKJH53WG5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armand Joulin, Edouard Grave, Guillaume Wenzek, Holger Schwenk, Sergey Edunov","submitted_at":"2019-11-10T12:09:46Z","abstract_excerpt":"We show that margin-based bitext mining in a multilingual sentence space can be applied to monolingual corpora of billions of sentences. We are using ten snapshots of a curated common crawl corpus (Wenzek et al., 2019) totalling 32.7 billion unique sentences. Using one unified approach for 38 languages, we were able to mine 4.5 billions parallel sentences, out of which 661 million are aligned with English. 20 language pairs have more then 30 million parallel sentences, 112 more then 10 million, and most more than one million, including direct alignments between many European or Asian languages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04944","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/1911.04944/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":"2026-07-05T00:59:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5P/1JgBpAU+0XUKQgpAUTR51IjeTeH/Om2v7AU7c8wWwMPwNMeo0Q67aY0mY9KT+D/jnc2ZD/TJdbiku4sOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:30:38.460368Z"},"content_sha256":"805248e04eaf7eb06923c25ca6ff3c93c7409ca10c087b4476324cda14fbfc5f","schema_version":"1.0","event_id":"sha256:805248e04eaf7eb06923c25ca6ff3c93c7409ca10c087b4476324cda14fbfc5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WOJKTA2ZKX5RWQ2IYKJH53WG5/bundle.json","state_url":"https://pith.science/pith/6WOJKTA2ZKX5RWQ2IYKJH53WG5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WOJKTA2ZKX5RWQ2IYKJH53WG5/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":"2026-08-06T20:30:38Z","links":{"resolver":"https://pith.science/pith/6WOJKTA2ZKX5RWQ2IYKJH53WG5","bundle":"https://pith.science/pith/6WOJKTA2ZKX5RWQ2IYKJH53WG5/bundle.json","state":"https://pith.science/pith/6WOJKTA2ZKX5RWQ2IYKJH53WG5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WOJKTA2ZKX5RWQ2IYKJH53WG5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6WOJKTA2ZKX5RWQ2IYKJH53WG5","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":"dab367d1031c9d34eed189ef0b8226f82c57edef34f6a6c9d5c6fb7d24616987","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T12:09:46Z","title_canon_sha256":"83710c6228cab645a4903186ff8353d31272445296ad41a818e58c52d1846af4"},"schema_version":"1.0","source":{"id":"1911.04944","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.04944","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"arxiv_version","alias_value":"1911.04944v2","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04944","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"pith_short_12","alias_value":"6WOJKTA2ZKX5","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"pith_short_16","alias_value":"6WOJKTA2ZKX5RWQ2","created_at":"2026-07-05T00:59:34Z"},{"alias_kind":"pith_short_8","alias_value":"6WOJKTA2","created_at":"2026-07-05T00:59:34Z"}],"graph_snapshots":[{"event_id":"sha256:805248e04eaf7eb06923c25ca6ff3c93c7409ca10c087b4476324cda14fbfc5f","target":"graph","created_at":"2026-07-05T00:59:34Z","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/1911.04944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that margin-based bitext mining in a multilingual sentence space can be applied to monolingual corpora of billions of sentences. We are using ten snapshots of a curated common crawl corpus (Wenzek et al., 2019) totalling 32.7 billion unique sentences. Using one unified approach for 38 languages, we were able to mine 4.5 billions parallel sentences, out of which 661 million are aligned with English. 20 language pairs have more then 30 million parallel sentences, 112 more then 10 million, and most more than one million, including direct alignments between many European or Asian languages","authors_text":"Armand Joulin, Edouard Grave, Guillaume Wenzek, Holger Schwenk, Sergey Edunov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T12:09:46Z","title":"CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04944","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:e470fcc121285dc4279ffcce5db985f559d2568a353bf8c6ab3ab1c6165cb591","target":"record","created_at":"2026-07-05T00:59:34Z","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":"dab367d1031c9d34eed189ef0b8226f82c57edef34f6a6c9d5c6fb7d24616987","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T12:09:46Z","title_canon_sha256":"83710c6228cab645a4903186ff8353d31272445296ad41a818e58c52d1846af4"},"schema_version":"1.0","source":{"id":"1911.04944","kind":"arxiv","version":2}},"canonical_sha256":"f59c954c1acaafd8da1a461493f7763757fb60ea1ddda6b2eaa55ddc14265a35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f59c954c1acaafd8da1a461493f7763757fb60ea1ddda6b2eaa55ddc14265a35","first_computed_at":"2026-07-05T00:59:34.562378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:34.562378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MKZpBUh9Rp70MNHzR8eV3vwyO9l6NAUupm3gI1vWnb8WJqmhFLH7ZIahM4RK7ANdDuz9wR6CmCdJ1D+vGnpUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:34.562838Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.04944","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e470fcc121285dc4279ffcce5db985f559d2568a353bf8c6ab3ab1c6165cb591","sha256:805248e04eaf7eb06923c25ca6ff3c93c7409ca10c087b4476324cda14fbfc5f"],"state_sha256":"dc98e4d51f88a42f2ae141259882b60f3f9a42e022231a9de8acda76d85a64dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPm6qR9lT5npDtUMGcMNtenTSYL05h/os41G89r8a39vaWCKKRHiOtdhja4ZaQNATeEEv68JalsaK6nHNrz5BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:30:38.466708Z","bundle_sha256":"30993dc0ca2b4eda3be06328e65878c3e787f77e631565b6bf01df6d51f3fdac"}}