{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:M6RYFXKDGBGDK3NSMXO5RCSOSK","short_pith_number":"pith:M6RYFXKD","schema_version":"1.0","canonical_sha256":"67a382dd43304c356db265ddd88a4e92b4f0a4e0c325fc60b9adca7b21d17f43","source":{"kind":"arxiv","id":"1911.00359","version":2},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.00359","created_at":"2026-07-05T00:19:22.101720+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.00359v2","created_at":"2026-07-05T00:19:22.101720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00359","created_at":"2026-07-05T00:19:22.101720+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6RYFXKDGBGD","created_at":"2026-07-05T00:19:22.101720+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6RYFXKDGBGDK3NS","created_at":"2026-07-05T00:19:22.101720+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6RYFXKD","created_at":"2026-07-05T00:19:22.101720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01196","citing_title":"Low-Resource Safety Failures Are Action Failures, Not Representation Failures","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2305.07759","citing_title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2502.10248","citing_title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"1911.02116","citing_title":"Unsupervised Cross-lingual Representation Learning at Scale","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2508.00795","citing_title":"Video Generators are Robot Policies","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2002.08910","citing_title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2403.04652","citing_title":"Yi: Open Foundation Models by 01.AI","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2101.00027","citing_title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK","json":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK.json","graph_json":"https://pith.science/api/pith-number/M6RYFXKDGBGDK3NSMXO5RCSOSK/graph.json","events_json":"https://pith.science/api/pith-number/M6RYFXKDGBGDK3NSMXO5RCSOSK/events.json","paper":"https://pith.science/paper/M6RYFXKD"},"agent_actions":{"view_html":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK","download_json":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK.json","view_paper":"https://pith.science/paper/M6RYFXKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.00359&json=true","fetch_graph":"https://pith.science/api/pith-number/M6RYFXKDGBGDK3NSMXO5RCSOSK/graph.json","fetch_events":"https://pith.science/api/pith-number/M6RYFXKDGBGDK3NSMXO5RCSOSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/action/storage_attestation","attest_author":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/action/author_attestation","sign_citation":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/action/citation_signature","submit_replication":"https://pith.science/pith/M6RYFXKDGBGDK3NSMXO5RCSOSK/action/replication_record"}},"created_at":"2026-07-05T00:19:22.101720+00:00","updated_at":"2026-07-05T00:19:22.101720+00:00"}