{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BKPKZ7WKIHTJWRPVC7H3NZIXOH","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":"bc065ace7a0ed66cf278d8afa162a5f6103f735045786277e7f28803e6533359","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-10-04T19:42:37Z","title_canon_sha256":"8ec2e100843a41c538b2003ece163e09d87e946b891f3bd01430502248fb20a8"},"schema_version":"1.0","source":{"id":"1710.01779","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.01779","created_at":"2026-05-18T00:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"1710.01779v2","created_at":"2026-05-18T00:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.01779","created_at":"2026-05-18T00:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"BKPKZ7WKIHTJ","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BKPKZ7WKIHTJWRPV","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BKPKZ7WK","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:b28ef5f2d8da17328ec0970ea2d99eabe1acc12a614634fee600a5ab013e215b","target":"graph","created_at":"2026-05-18T00:22:20Z","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"},"paper":{"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","authors_text":"Alexander Panchenko, Chris Biemann, Eugen Ruppert, Simone Paolo Ponzetto, Stefano Faralli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-10-04T19:42:37Z","title":"Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.01779","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:e31b1c3af0a2ce6301ba7dc94ea8635b53054a454da6ed5ad40b44c3bb289a38","target":"record","created_at":"2026-05-18T00:22:20Z","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":"bc065ace7a0ed66cf278d8afa162a5f6103f735045786277e7f28803e6533359","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2017-10-04T19:42:37Z","title_canon_sha256":"8ec2e100843a41c538b2003ece163e09d87e946b891f3bd01430502248fb20a8"},"schema_version":"1.0","source":{"id":"1710.01779","kind":"arxiv","version":2}},"canonical_sha256":"0a9eacfeca41e69b45f517cfb6e51771c1940945f39e5be7622da3dfffcd0d5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a9eacfeca41e69b45f517cfb6e51771c1940945f39e5be7622da3dfffcd0d5d","first_computed_at":"2026-05-18T00:22:20.684841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:20.684841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n5vESOOyqp1nQ1zE9bT0WSbwBhBwa5v227YcJsOw7N8OGUqwt35DwDdFjiqcGQ+xXTt6nYizInvStvVI/xMDCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:20.685377Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.01779","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e31b1c3af0a2ce6301ba7dc94ea8635b53054a454da6ed5ad40b44c3bb289a38","sha256:b28ef5f2d8da17328ec0970ea2d99eabe1acc12a614634fee600a5ab013e215b"],"state_sha256":"279705fe8552fcc3536f6c4d79453332f46cff4a0ff244968be8c3877cde2b50"}