{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:1994:JXYAOGVSGTWVJP7X4TICIZZSNY","short_pith_number":"pith:JXYAOGVS","canonical_record":{"source":{"id":"cmp-lg/9406015","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1994-06-07T18:17:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"37670da2d23dc3abc9f9e65a22120bd7725fba8f51d8dfbe38fbcf4a0194f9c2","abstract_canon_sha256":"c30ce899dfac6b0ffb43b14ef065d3eb6cf47d2e050a4575fb3e4b6691385d35"},"schema_version":"1.0"},"canonical_sha256":"4df0071ab234ed54bff7e4d02467326e21cf798dd9c106ca4ab3b435bdef9d66","source":{"kind":"arxiv","id":"cmp-lg/9406015","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9406015","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9406015v1","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9406015","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"JXYAOGVSGTWV","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"JXYAOGVSGTWVJP7X","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"JXYAOGVS","created_at":"2026-07-04T15:08:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:1994:JXYAOGVSGTWVJP7X4TICIZZSNY","target":"record","payload":{"canonical_record":{"source":{"id":"cmp-lg/9406015","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cmp-lg","submitted_at":"1994-06-07T18:17:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"37670da2d23dc3abc9f9e65a22120bd7725fba8f51d8dfbe38fbcf4a0194f9c2","abstract_canon_sha256":"c30ce899dfac6b0ffb43b14ef065d3eb6cf47d2e050a4575fb3e4b6691385d35"},"schema_version":"1.0"},"canonical_sha256":"4df0071ab234ed54bff7e4d02467326e21cf798dd9c106ca4ab3b435bdef9d66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T15:08:22.187419Z","signature_b64":"M4yPE6ihGi7P5KZ2pd/A5fGvysdI2y0qnfM7sHIkCUmU9RyUT3ebcX7g6TG6mz6DlK1wKIruq1rPKsMRGN1LAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4df0071ab234ed54bff7e4d02467326e21cf798dd9c106ca4ab3b435bdef9d66","last_reissued_at":"2026-07-04T15:08:22.187027Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T15:08:22.187027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"cmp-lg/9406015","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":"2026-07-04T15:08:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eXDSAjFdUP0S/T9PevYtEAv2+RASmoatQIleBUx2jLEV4wxk2FI7cA6/oJkBCkQo1ONXqFNO8MXonzARSsHgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:12:03.384530Z"},"content_sha256":"f4854b5375bcffcb615d82cf628684937aa73fc750d4bb1a4dc1dcf0690cfae3","schema_version":"1.0","event_id":"sha256:f4854b5375bcffcb615d82cf628684937aa73fc750d4bb1a4dc1dcf0690cfae3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:1994:JXYAOGVSGTWVJP7X4TICIZZSNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistical Augmentation of a Chinese Machine-Readable Dictionary","license":"","headline":"","cross_cats":["cs.CL"],"primary_cat":"cmp-lg","authors_text":"Dekai Wu (Hong Kong University of Science & Technology), Pascale Fung (Columbia University)","submitted_at":"1994-06-07T18:17:15Z","abstract_excerpt":"We describe a method of using statistically-collected Chinese character groups from a corpus to augment a Chinese dictionary. The method is particularly useful for extracting domain-specific and regional words not readily available in machine-readable dictionaries. Output was evaluated both using human evaluators and against a previously available dictionary. We also evaluated performance improvement in automatic Chinese tokenization. Results show that our method outputs legitimate words, acronymic constructions, idioms, names and titles, as well as technical compounds, many of which were lack"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9406015","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/cmp-lg/9406015/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-04T15:08:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"noOI+KnC/WDX9Xl7C5kj0p42KgIFbFmI0CeYXazuVkv6RDGFIz2FLLxkFbjTx9Th0UzaLbAemvG5Qeil/UyWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:12:03.386406Z"},"content_sha256":"1eae01154baa5965c9b220e1e4ef762cc1674e15d87bd9cae7daba01504d2087","schema_version":"1.0","event_id":"sha256:1eae01154baa5965c9b220e1e4ef762cc1674e15d87bd9cae7daba01504d2087"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JXYAOGVSGTWVJP7X4TICIZZSNY/bundle.json","state_url":"https://pith.science/pith/JXYAOGVSGTWVJP7X4TICIZZSNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JXYAOGVSGTWVJP7X4TICIZZSNY/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":"2026-08-11T18:12:03Z","links":{"resolver":"https://pith.science/pith/JXYAOGVSGTWVJP7X4TICIZZSNY","bundle":"https://pith.science/pith/JXYAOGVSGTWVJP7X4TICIZZSNY/bundle.json","state":"https://pith.science/pith/JXYAOGVSGTWVJP7X4TICIZZSNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JXYAOGVSGTWVJP7X4TICIZZSNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:1994:JXYAOGVSGTWVJP7X4TICIZZSNY","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":"c30ce899dfac6b0ffb43b14ef065d3eb6cf47d2e050a4575fb3e4b6691385d35","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1994-06-07T18:17:15Z","title_canon_sha256":"37670da2d23dc3abc9f9e65a22120bd7725fba8f51d8dfbe38fbcf4a0194f9c2"},"schema_version":"1.0","source":{"id":"cmp-lg/9406015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cmp-lg/9406015","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"arxiv_version","alias_value":"cmp-lg/9406015v1","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cmp-lg/9406015","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"pith_short_12","alias_value":"JXYAOGVSGTWV","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"pith_short_16","alias_value":"JXYAOGVSGTWVJP7X","created_at":"2026-07-04T15:08:22Z"},{"alias_kind":"pith_short_8","alias_value":"JXYAOGVS","created_at":"2026-07-04T15:08:22Z"}],"graph_snapshots":[{"event_id":"sha256:1eae01154baa5965c9b220e1e4ef762cc1674e15d87bd9cae7daba01504d2087","target":"graph","created_at":"2026-07-04T15:08:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/cmp-lg/9406015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We describe a method of using statistically-collected Chinese character groups from a corpus to augment a Chinese dictionary. The method is particularly useful for extracting domain-specific and regional words not readily available in machine-readable dictionaries. Output was evaluated both using human evaluators and against a previously available dictionary. We also evaluated performance improvement in automatic Chinese tokenization. Results show that our method outputs legitimate words, acronymic constructions, idioms, names and titles, as well as technical compounds, many of which were lack","authors_text":"Dekai Wu (Hong Kong University of Science & Technology), Pascale Fung (Columbia University)","cross_cats":["cs.CL"],"headline":"","license":"","primary_cat":"cmp-lg","submitted_at":"1994-06-07T18:17:15Z","title":"Statistical Augmentation of a Chinese Machine-Readable Dictionary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cmp-lg/9406015","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:f4854b5375bcffcb615d82cf628684937aa73fc750d4bb1a4dc1dcf0690cfae3","target":"record","created_at":"2026-07-04T15:08:22Z","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":"c30ce899dfac6b0ffb43b14ef065d3eb6cf47d2e050a4575fb3e4b6691385d35","cross_cats_sorted":["cs.CL"],"license":"","primary_cat":"cmp-lg","submitted_at":"1994-06-07T18:17:15Z","title_canon_sha256":"37670da2d23dc3abc9f9e65a22120bd7725fba8f51d8dfbe38fbcf4a0194f9c2"},"schema_version":"1.0","source":{"id":"cmp-lg/9406015","kind":"arxiv","version":1}},"canonical_sha256":"4df0071ab234ed54bff7e4d02467326e21cf798dd9c106ca4ab3b435bdef9d66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4df0071ab234ed54bff7e4d02467326e21cf798dd9c106ca4ab3b435bdef9d66","first_computed_at":"2026-07-04T15:08:22.187027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T15:08:22.187027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M4yPE6ihGi7P5KZ2pd/A5fGvysdI2y0qnfM7sHIkCUmU9RyUT3ebcX7g6TG6mz6DlK1wKIruq1rPKsMRGN1LAw==","signature_status":"signed_v1","signed_at":"2026-07-04T15:08:22.187419Z","signed_message":"canonical_sha256_bytes"},"source_id":"cmp-lg/9406015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4854b5375bcffcb615d82cf628684937aa73fc750d4bb1a4dc1dcf0690cfae3","sha256:1eae01154baa5965c9b220e1e4ef762cc1674e15d87bd9cae7daba01504d2087"],"state_sha256":"fed251ff592c41406494cf8517cfbb2c508ff249aecccfc2ea80d5b191e685ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MUEe4+R1WQhhmuiqmy1cUWwnJHyQib5KArZpaTjBOJxP8SaT/l8LG0/NYQsCm362RER+1hjbvVzIatbntTOBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:12:03.399106Z","bundle_sha256":"312bb7cab4cedbe2f05806618959b571f54aaf4f19002e1d0ea4347bc049e79a"}}