{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BKPKZ7WKIHTJWRPVC7H3NZIXOH","short_pith_number":"pith:BKPKZ7WK","schema_version":"1.0","canonical_sha256":"0a9eacfeca41e69b45f517cfb6e51771c1940945f39e5be7622da3dfffcd0d5d","source":{"kind":"arxiv","id":"1710.01779","version":2},"attestation_state":"computed","paper":{"title":"Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Panchenko, Chris Biemann, Eugen Ruppert, Simone Paolo Ponzetto, Stefano Faralli","submitted_at":"2017-10-04T19:42:37Z","abstract_excerpt":"We present DepCC, the largest-to-date linguistically analyzed corpus in English including 365 million documents, composed of 252 billion tokens and 7.5 billion of named entity occurrences in 14.3 billion sentences from a web-scale crawl of the \\textsc{Common Crawl} project. The sentences are processed with a dependency parser and with a named entity tagger and contain provenance information, enabling various applications ranging from training syntax-based word embeddings to open information extraction and question answering. We built an index of all sentences and their linguistic meta-data ena"},"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":"1710.01779","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-10-04T19:42:37Z","cross_cats_sorted":[],"title_canon_sha256":"8ec2e100843a41c538b2003ece163e09d87e946b891f3bd01430502248fb20a8","abstract_canon_sha256":"bc065ace7a0ed66cf278d8afa162a5f6103f735045786277e7f28803e6533359"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:20.685377Z","signature_b64":"n5vESOOyqp1nQ1zE9bT0WSbwBhBwa5v227YcJsOw7N8OGUqwt35DwDdFjiqcGQ+xXTt6nYizInvStvVI/xMDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a9eacfeca41e69b45f517cfb6e51771c1940945f39e5be7622da3dfffcd0d5d","last_reissued_at":"2026-05-18T00:22:20.684841Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:20.684841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Panchenko, Chris Biemann, Eugen Ruppert, Simone Paolo Ponzetto, Stefano Faralli","submitted_at":"2017-10-04T19:42:37Z","abstract_excerpt":"We present DepCC, the largest-to-date linguistically analyzed corpus in English including 365 million documents, composed of 252 billion tokens and 7.5 billion of named entity occurrences in 14.3 billion sentences from a web-scale crawl of the \\textsc{Common Crawl} project. The sentences are processed with a dependency parser and with a named entity tagger and contain provenance information, enabling various applications ranging from training syntax-based word embeddings to open information extraction and question answering. We built an index of all sentences and their linguistic meta-data ena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01779","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":""},"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":"1710.01779","created_at":"2026-05-18T00:22:20.684904+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.01779v2","created_at":"2026-05-18T00:22:20.684904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01779","created_at":"2026-05-18T00:22:20.684904+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKPKZ7WKIHTJ","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKPKZ7WKIHTJWRPV","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKPKZ7WK","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH","json":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH.json","graph_json":"https://pith.science/api/pith-number/BKPKZ7WKIHTJWRPVC7H3NZIXOH/graph.json","events_json":"https://pith.science/api/pith-number/BKPKZ7WKIHTJWRPVC7H3NZIXOH/events.json","paper":"https://pith.science/paper/BKPKZ7WK"},"agent_actions":{"view_html":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH","download_json":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH.json","view_paper":"https://pith.science/paper/BKPKZ7WK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.01779&json=true","fetch_graph":"https://pith.science/api/pith-number/BKPKZ7WKIHTJWRPVC7H3NZIXOH/graph.json","fetch_events":"https://pith.science/api/pith-number/BKPKZ7WKIHTJWRPVC7H3NZIXOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH/action/storage_attestation","attest_author":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH/action/author_attestation","sign_citation":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH/action/citation_signature","submit_replication":"https://pith.science/pith/BKPKZ7WKIHTJWRPVC7H3NZIXOH/action/replication_record"}},"created_at":"2026-05-18T00:22:20.684904+00:00","updated_at":"2026-05-18T00:22:20.684904+00:00"}