{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:1995:C4UAOS3XJLUI7TJ6RA4Q6TLLPM","short_pith_number":"pith:C4UAOS3X","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"},"canonical_sha256":"1728074b774ae88fcd3e88390f4d6b7b26ea3b02e55e9c5dbf11a80446a6460c","source":{"kind":"arxiv","id":"cmp-lg/9503011","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:1995:C4UAOS3XJLUI7TJ6RA4Q6TLLPM","target":"record","payload":{"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"},"canonical_sha256":"1728074b774ae88fcd3e88390f4d6b7b26ea3b02e55e9c5dbf11a80446a6460c","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"},"source_kind":"arxiv","source_id":"cmp-lg/9503011","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/t/YntfpXpPYeVhg7ZU2vwZ1hakd/x0tN5JhT6/3iqLdnc290IRCcM/PST8eXML0M31cichS/mHI7F9fS2UCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:17:40.755231Z"},"content_sha256":"698b8dfcefb5eefaca498187f6fb07478b5c772eb22da922f9d6493000598290","schema_version":"1.0","event_id":"sha256:698b8dfcefb5eefaca498187f6fb07478b5c772eb22da922f9d6493000598290"},{"event_type":"graph_snapshot","subject_pith_number":"pith:1995:C4UAOS3XJLUI7TJ6RA4Q6TLLPM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Kh/uxBiT2Z510DxC35Sf9I0lJ1mTTwu2ZHMBDEPimaD3hjdWFUHhs5huvEKYjg2IYKn+4lZWZFlYVrwwEbsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T21:17:40.755601Z"},"content_sha256":"0db7a938534c17128e93f6bc0bf238ce655710b3fdfa8f283e72583945cdc0d6","schema_version":"1.0","event_id":"sha256:0db7a938534c17128e93f6bc0bf238ce655710b3fdfa8f283e72583945cdc0d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/bundle.json","state_url":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T21:17:40Z","links":{"resolver":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM","bundle":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/bundle.json","state":"https://pith.science/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4UAOS3XJLUI7TJ6RA4Q6TLLPM/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EqfJLHbKHz9PP/sGYyPw4LmUjXO/LfqIy04LefOKDvKHlk3TXIUbzJbqy6vV/jr0zt2lB/hXXbfDiiheYykZAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T21:17:40.758428Z","bundle_sha256":"7002048055a65494544d223d12016f57669c6397e7f807d16e84ee7a491aa05c"}}