{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DRVFGVDTFZQUZOHTWSBCQ2EHU6","short_pith_number":"pith:DRVFGVDT","schema_version":"1.0","canonical_sha256":"1c6a5354732e614cb8f3b482286887a7abc6f32f0f527f1e84a627d3de6d057e","source":{"kind":"arxiv","id":"1703.05706","version":2},"attestation_state":"computed","paper":{"title":"Improving Document Clustering by Eliminating Unnatural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"James Allan, Jinho D. Choi, Myungha Jang","submitted_at":"2017-03-16T16:32:06Z","abstract_excerpt":"Technical documents contain a fair amount of unnatural language, such as tables, formulas, pseudo-codes, etc. Unnatural language can be an important factor of confusing existing NLP tools. This paper presents an effective method of distinguishing unnatural language from natural language, and evaluates the impact of unnatural language detection on NLP tasks such as document clustering. We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories. First, we create a new annotated corpus by collec"},"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":"1703.05706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-03-16T16:32:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5b4b6a565a7dd6029486595e6f1e1a32384ffcc2450a48cb11353515a3b970a1","abstract_canon_sha256":"a27091577acaea45b36d8b05e81435b233104635e088e1949da23ee72e437787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:32.166423Z","signature_b64":"662PyZO87CymZYtY2OEy3kWTizywjV2iZPiwlJn8qJzXCnF8lL0yz6kUkl6uEUPtqrDGN0FbtRtjsv/tvMlACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c6a5354732e614cb8f3b482286887a7abc6f32f0f527f1e84a627d3de6d057e","last_reissued_at":"2026-05-18T00:48:32.165725Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:32.165725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Document Clustering by Eliminating Unnatural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"James Allan, Jinho D. Choi, Myungha Jang","submitted_at":"2017-03-16T16:32:06Z","abstract_excerpt":"Technical documents contain a fair amount of unnatural language, such as tables, formulas, pseudo-codes, etc. Unnatural language can be an important factor of confusing existing NLP tools. This paper presents an effective method of distinguishing unnatural language from natural language, and evaluates the impact of unnatural language detection on NLP tasks such as document clustering. We view this problem as an information extraction task and build a multiclass classification model identifying unnatural language components into four categories. First, we create a new annotated corpus by collec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.05706","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":"1703.05706","created_at":"2026-05-18T00:48:32.165837+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.05706v2","created_at":"2026-05-18T00:48:32.165837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.05706","created_at":"2026-05-18T00:48:32.165837+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRVFGVDTFZQU","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRVFGVDTFZQUZOHT","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRVFGVDT","created_at":"2026-05-18T12:31:12.930513+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/DRVFGVDTFZQUZOHTWSBCQ2EHU6","json":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6.json","graph_json":"https://pith.science/api/pith-number/DRVFGVDTFZQUZOHTWSBCQ2EHU6/graph.json","events_json":"https://pith.science/api/pith-number/DRVFGVDTFZQUZOHTWSBCQ2EHU6/events.json","paper":"https://pith.science/paper/DRVFGVDT"},"agent_actions":{"view_html":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6","download_json":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6.json","view_paper":"https://pith.science/paper/DRVFGVDT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.05706&json=true","fetch_graph":"https://pith.science/api/pith-number/DRVFGVDTFZQUZOHTWSBCQ2EHU6/graph.json","fetch_events":"https://pith.science/api/pith-number/DRVFGVDTFZQUZOHTWSBCQ2EHU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6/action/storage_attestation","attest_author":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6/action/author_attestation","sign_citation":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6/action/citation_signature","submit_replication":"https://pith.science/pith/DRVFGVDTFZQUZOHTWSBCQ2EHU6/action/replication_record"}},"created_at":"2026-05-18T00:48:32.165837+00:00","updated_at":"2026-05-18T00:48:32.165837+00:00"}