{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:M6RYFXKDGBGDK3NSMXO5RCSOSK","short_pith_number":"pith:M6RYFXKD","canonical_record":{"source":{"id":"1911.00359","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T13:09:28Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"b85aa8002d6f4320c037393d5e03d4602a98643ddb0ff6fb729d16a34867ce6d","abstract_canon_sha256":"0c7a67afeb1ab202c2bfca94cd710939ef58c6d94982086800a2a4405bc10d5e"},"schema_version":"1.0"},"canonical_sha256":"67a382dd43304c356db265ddd88a4e92b4f0a4e0c325fc60b9adca7b21d17f43","source":{"kind":"arxiv","id":"1911.00359","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.00359","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"1911.00359v2","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00359","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"M6RYFXKDGBGD","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"M6RYFXKDGBGDK3NS","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"M6RYFXKD","created_at":"2026-07-05T00:19:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:M6RYFXKDGBGDK3NSMXO5RCSOSK","target":"record","payload":{"canonical_record":{"source":{"id":"1911.00359","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T13:09:28Z","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"title_canon_sha256":"b85aa8002d6f4320c037393d5e03d4602a98643ddb0ff6fb729d16a34867ce6d","abstract_canon_sha256":"0c7a67afeb1ab202c2bfca94cd710939ef58c6d94982086800a2a4405bc10d5e"},"schema_version":"1.0"},"canonical_sha256":"67a382dd43304c356db265ddd88a4e92b4f0a4e0c325fc60b9adca7b21d17f43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:22.102121Z","signature_b64":"5Uno3k/nHyK2eXvNYWQAsDbH/lXs9hvMTKlXtbo85+T7nQuD5V1o8XztWKmjGmSI6a1esCXQh8IlkyTI0tlsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67a382dd43304c356db265ddd88a4e92b4f0a4e0c325fc60b9adca7b21d17f43","last_reissued_at":"2026-07-05T00:19:22.101667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:22.101667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.00359","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":"2026-07-05T00:19:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OX90iUVKFUR0X2K+pnz409V22au0VNAbJ6dim6JB0dRwrxbcNe82Fukr5qBeszLp/7GF+Ze8+BRcQh5JzQVgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:43:29.208711Z"},"content_sha256":"14bec965779c4f1af2f66df26cab2fb55a44302b072fdf494902ee30afcca0c1","schema_version":"1.0","event_id":"sha256:14bec965779c4f1af2f66df26cab2fb55a44302b072fdf494902ee30afcca0c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:M6RYFXKDGBGDK3NSMXO5RCSOSK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Armand Joulin, Edouard Grave, Francisco Guzm\\'an, Guillaume Wenzek, Marie-Anne Lachaux, Vishrav Chaudhary","submitted_at":"2019-11-01T13:09:28Z","abstract_excerpt":"Pre-training text representations have led to significant improvements in many areas of natural language processing. The quality of these models benefits greatly from the size of the pretraining corpora as long as its quality is preserved. In this paper, we describe an automatic pipeline to extract massive high-quality monolingual datasets from Common Crawl for a variety of languages. Our pipeline follows the data processing introduced in fastText (Mikolov et al., 2017; Grave et al., 2018), that deduplicates documents and identifies their language. We augment this pipeline with a filtering ste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00359","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/1911.00359/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":"2026-07-05T00:19:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AE7rgKtm3s8PHWQlHcZ4awGTIJdz2c5nnkylUpgAPfzzBS46+2f/0khiIX7GEnrbXJ3MOX1YtWkJ3HFHEh5xBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:43:29.209090Z"},"content_sha256":"528f373051e3a1227e48da2d45d15fab9a1702b8af857528a7d38fa74d35c661","schema_version":"1.0","event_id":"sha256:528f373051e3a1227e48da2d45d15fab9a1702b8af857528a7d38fa74d35c661"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/bundle.json","state_url":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/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":"2026-08-04T01:43:29Z","links":{"resolver":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK","bundle":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/bundle.json","state":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:M6RYFXKDGBGDK3NSMXO5RCSOSK","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":"0c7a67afeb1ab202c2bfca94cd710939ef58c6d94982086800a2a4405bc10d5e","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T13:09:28Z","title_canon_sha256":"b85aa8002d6f4320c037393d5e03d4602a98643ddb0ff6fb729d16a34867ce6d"},"schema_version":"1.0","source":{"id":"1911.00359","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.00359","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"arxiv_version","alias_value":"1911.00359v2","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00359","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"pith_short_12","alias_value":"M6RYFXKDGBGD","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"pith_short_16","alias_value":"M6RYFXKDGBGDK3NS","created_at":"2026-07-05T00:19:22Z"},{"alias_kind":"pith_short_8","alias_value":"M6RYFXKD","created_at":"2026-07-05T00:19:22Z"}],"graph_snapshots":[{"event_id":"sha256:528f373051e3a1227e48da2d45d15fab9a1702b8af857528a7d38fa74d35c661","target":"graph","created_at":"2026-07-05T00:19:22Z","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/1911.00359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training text representations have led to significant improvements in many areas of natural language processing. The quality of these models benefits greatly from the size of the pretraining corpora as long as its quality is preserved. In this paper, we describe an automatic pipeline to extract massive high-quality monolingual datasets from Common Crawl for a variety of languages. Our pipeline follows the data processing introduced in fastText (Mikolov et al., 2017; Grave et al., 2018), that deduplicates documents and identifies their language. We augment this pipeline with a filtering ste","authors_text":"Alexis Conneau, Armand Joulin, Edouard Grave, Francisco Guzm\\'an, Guillaume Wenzek, Marie-Anne Lachaux, Vishrav Chaudhary","cross_cats":["cs.IR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T13:09:28Z","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00359","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":"sha256:14bec965779c4f1af2f66df26cab2fb55a44302b072fdf494902ee30afcca0c1","target":"record","created_at":"2026-07-05T00:19:22Z","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":"0c7a67afeb1ab202c2bfca94cd710939ef58c6d94982086800a2a4405bc10d5e","cross_cats_sorted":["cs.IR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-01T13:09:28Z","title_canon_sha256":"b85aa8002d6f4320c037393d5e03d4602a98643ddb0ff6fb729d16a34867ce6d"},"schema_version":"1.0","source":{"id":"1911.00359","kind":"arxiv","version":2}},"canonical_sha256":"67a382dd43304c356db265ddd88a4e92b4f0a4e0c325fc60b9adca7b21d17f43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67a382dd43304c356db265ddd88a4e92b4f0a4e0c325fc60b9adca7b21d17f43","first_computed_at":"2026-07-05T00:19:22.101667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:19:22.101667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Uno3k/nHyK2eXvNYWQAsDbH/lXs9hvMTKlXtbo85+T7nQuD5V1o8XztWKmjGmSI6a1esCXQh8IlkyTI0tlsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:19:22.102121Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.00359","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14bec965779c4f1af2f66df26cab2fb55a44302b072fdf494902ee30afcca0c1","sha256:528f373051e3a1227e48da2d45d15fab9a1702b8af857528a7d38fa74d35c661"],"state_sha256":"2f113cd19426a1cfa887f45ba38c68c600649bcb6b4ba0cb5cda0f6ba77decc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iDsc3GlpYKti0ZhI2S2EmpnJVTJmJxmbADK6eTxCnKnK/6I0jugmvrlB7pu8vdC8M4NX7r+JN2KU3TF37JxPAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:43:29.211959Z","bundle_sha256":"b8853bbd3844d414c1fb9d86ae4d0d62cfcd5474f12cb026a3987970bb9bdea3"}}