{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1995:C4UAOS3XJLUI7TJ6RA4Q6TLLPM","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":"d6aab514b369d9e63b4b4bba007182ffc6321e451f9aa7e94b5a6a17fca762d5","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1995-03-09T21:07:06Z","title_canon_sha256":"1c7664befc9908341c8df461a535abcf7a84d47276b8782ac59345cb6a161dd7"},"schema_version":"1.0","source":{"id":"cmp-lg/9503011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9503011","created_at":"2026-05-18T01:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9503011v1","created_at":"2026-05-18T01:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9503011","created_at":"2026-05-18T01:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"C4UAOS3XJLUI","created_at":"2026-05-18T12:25:47Z"},{"alias_kind":"pith_short_16","alias_value":"C4UAOS3XJLUI7TJ6","created_at":"2026-05-18T12:25:47Z"},{"alias_kind":"pith_short_8","alias_value":"C4UAOS3X","created_at":"2026-05-18T12:25:47Z"}],"graph_snapshots":[{"event_id":"sha256:0db7a938534c17128e93f6bc0bf238ce655710b3fdfa8f283e72583945cdc0d6","target":"graph","created_at":"2026-05-18T01:07:24Z","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":"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","authors_text":"Belfast), F.J.Smith (Queen's University, John McMahon","cross_cats":["cs.CL"],"headline":"","license":"","primary_cat":"cmp-lg","submitted_at":"1995-03-09T21:07:06Z","title":"Improving Statistical Language Model Performance with Automatically Generated Word Hierarchies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9503011","kind":"arxiv","version":1},"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":"sha256:698b8dfcefb5eefaca498187f6fb07478b5c772eb22da922f9d6493000598290","target":"record","created_at":"2026-05-18T01:07:24Z","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":"d6aab514b369d9e63b4b4bba007182ffc6321e451f9aa7e94b5a6a17fca762d5","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1995-03-09T21:07:06Z","title_canon_sha256":"1c7664befc9908341c8df461a535abcf7a84d47276b8782ac59345cb6a161dd7"},"schema_version":"1.0","source":{"id":"cmp-lg/9503011","kind":"arxiv","version":1}},"canonical_sha256":"1728074b774ae88fcd3e88390f4d6b7b26ea3b02e55e9c5dbf11a80446a6460c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1728074b774ae88fcd3e88390f4d6b7b26ea3b02e55e9c5dbf11a80446a6460c","first_computed_at":"2026-05-18T01:07:24.007665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:07:24.007665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tFDwWdY60Hw+cNA5U/SiMXliEGeKtlXllsGn21KRWIf5X4zwaNhcmoQNf0GEhlDLdgp/Pfquivf9OwS3TkORBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:07:24.008038Z","signed_message":"canonical_sha256_bytes"},"source_id":"cmp-lg/9503011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:698b8dfcefb5eefaca498187f6fb07478b5c772eb22da922f9d6493000598290","sha256:0db7a938534c17128e93f6bc0bf238ce655710b3fdfa8f283e72583945cdc0d6"],"state_sha256":"abb037d78089f602e6ea2ca54ad9a3382ab38f73728de89aadb9c4a0ff247fdd"}