{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:7BLATMUINRS6AGCKZFI4DDIFEK","short_pith_number":"pith:7BLATMUI","schema_version":"1.0","canonical_sha256":"f85609b2886c65e0184ac951c18d0522bbc60816d0eaf7168d1fafab81d695bd","source":{"kind":"arxiv","id":"1301.2857","version":1},"attestation_state":"computed","paper":{"title":"SpeedRead: A Fast Named Entity Recognition Pipeline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rami Al-Rfou', Steven Skiena","submitted_at":"2013-01-14T04:01:25Z","abstract_excerpt":"Online content analysis employs algorithmic methods to identify entities in unstructured text. Both machine learning and knowledge-base approaches lie at the foundation of contemporary named entities extraction systems. However, the progress in deploying these approaches on web-scale has been been hampered by the computational cost of NLP over massive text corpora. We present SpeedRead (SR), a named entity recognition pipeline that runs at least 10 times faster than Stanford NLP pipeline. This pipeline consists of a high performance Penn Treebank- compliant tokenizer, close to state-of-art par"},"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":"1301.2857","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2013-01-14T04:01:25Z","cross_cats_sorted":[],"title_canon_sha256":"0e57d7496e8522a5e274e5a8c3b95f99b894b82ffd53bc872e8b0332cb3ef8f0","abstract_canon_sha256":"1efb1717556afdca86fdbf48f75d5624af284b10c4f2fd0b0fd1f854cee5a3d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:34.948078Z","signature_b64":"3dNSjnT6g9m9ufn8Mrk2Zs+aBmX6L56mBDNHZ19CgWWGwSSV22OLZiZLvEOL+ynWwGOZnMk7/SE/WW3ucAvtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f85609b2886c65e0184ac951c18d0522bbc60816d0eaf7168d1fafab81d695bd","last_reissued_at":"2026-05-18T03:36:34.947217Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:34.947217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeedRead: A Fast Named Entity Recognition Pipeline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Rami Al-Rfou', Steven Skiena","submitted_at":"2013-01-14T04:01:25Z","abstract_excerpt":"Online content analysis employs algorithmic methods to identify entities in unstructured text. Both machine learning and knowledge-base approaches lie at the foundation of contemporary named entities extraction systems. However, the progress in deploying these approaches on web-scale has been been hampered by the computational cost of NLP over massive text corpora. We present SpeedRead (SR), a named entity recognition pipeline that runs at least 10 times faster than Stanford NLP pipeline. This pipeline consists of a high performance Penn Treebank- compliant tokenizer, close to state-of-art par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.2857","kind":"arxiv","version":1},"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":"1301.2857","created_at":"2026-05-18T03:36:34.947351+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.2857v1","created_at":"2026-05-18T03:36:34.947351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.2857","created_at":"2026-05-18T03:36:34.947351+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BLATMUINRS6","created_at":"2026-05-18T12:27:36.564083+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BLATMUINRS6AGCK","created_at":"2026-05-18T12:27:36.564083+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BLATMUI","created_at":"2026-05-18T12:27:36.564083+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/7BLATMUINRS6AGCKZFI4DDIFEK","json":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK.json","graph_json":"https://pith.science/api/pith-number/7BLATMUINRS6AGCKZFI4DDIFEK/graph.json","events_json":"https://pith.science/api/pith-number/7BLATMUINRS6AGCKZFI4DDIFEK/events.json","paper":"https://pith.science/paper/7BLATMUI"},"agent_actions":{"view_html":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK","download_json":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK.json","view_paper":"https://pith.science/paper/7BLATMUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.2857&json=true","fetch_graph":"https://pith.science/api/pith-number/7BLATMUINRS6AGCKZFI4DDIFEK/graph.json","fetch_events":"https://pith.science/api/pith-number/7BLATMUINRS6AGCKZFI4DDIFEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK/action/storage_attestation","attest_author":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK/action/author_attestation","sign_citation":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK/action/citation_signature","submit_replication":"https://pith.science/pith/7BLATMUINRS6AGCKZFI4DDIFEK/action/replication_record"}},"created_at":"2026-05-18T03:36:34.947351+00:00","updated_at":"2026-05-18T03:36:34.947351+00:00"}