{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:1995:C4UAOS3XJLUI7TJ6RA4Q6TLLPM","short_pith_number":"pith:C4UAOS3X","schema_version":"1.0","canonical_sha256":"1728074b774ae88fcd3e88390f4d6b7b26ea3b02e55e9c5dbf11a80446a6460c","source":{"kind":"arxiv","id":"cmp-lg/9503011","version":1},"attestation_state":"computed","paper":{"title":"Improving Statistical Language Model Performance with Automatically Generated Word Hierarchies","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Belfast), F.J.Smith (Queen's University, John McMahon","submitted_at":"1995-03-09T21:07:06Z","abstract_excerpt":"An automatic word classification system has been designed which processes word unigram and bigram frequency statistics extracted from a corpus of natural language utterances. The system implements a binary top-down form of word clustering which employs an average class mutual information metric. Resulting classifications are hierarchical, allowing variable class granularity. Words are represented as structural tags --- unique $n$-bit numbers the most significant bit-patterns of which incorporate class information. Access to a structural tag immediately provides access to all classification lev"},"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":"cmp-lg/9503011","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1995-03-09T21:07:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1c7664befc9908341c8df461a535abcf7a84d47276b8782ac59345cb6a161dd7","abstract_canon_sha256":"d6aab514b369d9e63b4b4bba007182ffc6321e451f9aa7e94b5a6a17fca762d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:07:24.008038Z","signature_b64":"tFDwWdY60Hw+cNA5U/SiMXliEGeKtlXllsGn21KRWIf5X4zwaNhcmoQNf0GEhlDLdgp/Pfquivf9OwS3TkORBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1728074b774ae88fcd3e88390f4d6b7b26ea3b02e55e9c5dbf11a80446a6460c","last_reissued_at":"2026-05-18T01:07:24.007665Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:07:24.007665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Statistical Language Model Performance with Automatically Generated Word Hierarchies","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Belfast), F.J.Smith (Queen's University, John McMahon","submitted_at":"1995-03-09T21:07:06Z","abstract_excerpt":"An automatic word classification system has been designed which processes word unigram and bigram frequency statistics extracted from a corpus of natural language utterances. The system implements a binary top-down form of word clustering which employs an average class mutual information metric. Resulting classifications are hierarchical, allowing variable class granularity. Words are represented as structural tags --- unique $n$-bit numbers the most significant bit-patterns of which incorporate class information. Access to a structural tag immediately provides access to all classification lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9503011","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":"cmp-lg/9503011","created_at":"2026-05-18T01:07:24.007722+00:00"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9503011v1","created_at":"2026-05-18T01:07:24.007722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9503011","created_at":"2026-05-18T01:07:24.007722+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4UAOS3XJLUI","created_at":"2026-05-18T12:25:47.700082+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4UAOS3XJLUI7TJ6","created_at":"2026-05-18T12:25:47.700082+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4UAOS3X","created_at":"2026-05-18T12:25:47.700082+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/C4UAOS3XJLUI7TJ6RA4Q6TLLPM","json":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM.json","graph_json":"https://pith.science/api/pith-number/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/graph.json","events_json":"https://pith.science/api/pith-number/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/events.json","paper":"https://pith.science/paper/C4UAOS3X"},"agent_actions":{"view_html":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM","download_json":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM.json","view_paper":"https://pith.science/paper/C4UAOS3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cmp-lg/9503011&json=true","fetch_graph":"https://pith.science/api/pith-number/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/graph.json","fetch_events":"https://pith.science/api/pith-number/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/action/storage_attestation","attest_author":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/action/author_attestation","sign_citation":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/action/citation_signature","submit_replication":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/action/replication_record"}},"created_at":"2026-05-18T01:07:24.007722+00:00","updated_at":"2026-05-18T01:07:24.007722+00:00"}