{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:2EMU7SCBMOJGYYLWW5QTLXLZOZ","short_pith_number":"pith:2EMU7SCB","canonical_record":{"source":{"id":"1305.5918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.CL","submitted_at":"2013-05-25T13:20:31Z","cross_cats_sorted":[],"title_canon_sha256":"bf9cffde812cf6ddc73107191741e7e1b978761ef0a0249eae2f89745845816c","abstract_canon_sha256":"cbd5dac193aa3d50214ad3a4969c76fd16b9560b75e412945f9eca974e95ec38"},"schema_version":"1.0"},"canonical_sha256":"d1194fc84163926c6176b76135dd79764d00cd81b4da8ad60afbba4fe92af19f","source":{"kind":"arxiv","id":"1305.5918","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.5918","created_at":"2026-05-18T03:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"1305.5918v1","created_at":"2026-05-18T03:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.5918","created_at":"2026-05-18T03:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"2EMU7SCBMOJG","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"2EMU7SCBMOJGYYLW","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"2EMU7SCB","created_at":"2026-05-18T12:27:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:2EMU7SCBMOJGYYLWW5QTLXLZOZ","target":"record","payload":{"canonical_record":{"source":{"id":"1305.5918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.CL","submitted_at":"2013-05-25T13:20:31Z","cross_cats_sorted":[],"title_canon_sha256":"bf9cffde812cf6ddc73107191741e7e1b978761ef0a0249eae2f89745845816c","abstract_canon_sha256":"cbd5dac193aa3d50214ad3a4969c76fd16b9560b75e412945f9eca974e95ec38"},"schema_version":"1.0"},"canonical_sha256":"d1194fc84163926c6176b76135dd79764d00cd81b4da8ad60afbba4fe92af19f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:24:53.343960Z","signature_b64":"zAOxbCXAMlJUcN0wDc+dC5vjhuLm4cFn/Zydw8Qbe7EUvclfJBNLXxcZCOelFjaMXfVEcqQ5oEwW6fag1yw/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1194fc84163926c6176b76135dd79764d00cd81b4da8ad60afbba4fe92af19f","last_reissued_at":"2026-05-18T03:24:53.343301Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:24:53.343301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1305.5918","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":"2026-05-18T03:24:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sYDwZnXSxZGSprxIUj+DRDUmpYjs5OwHdfN+uIylkQXNP0t7sf/3GYXPYcl1QI7w8NKVSE8tM7xXpN/wr2U1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:48:01.501835Z"},"content_sha256":"e2a6d6d804c4c1618abb8c3408e33dde961c0128238ab62eea6dfd57e2bfa6ca","schema_version":"1.0","event_id":"sha256:e2a6d6d804c4c1618abb8c3408e33dde961c0128238ab62eea6dfd57e2bfa6ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:2EMU7SCBMOJGYYLWW5QTLXLZOZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reduce Meaningless Words for Joint Chinese Word Segmentation and Part-of-speech Tagging","license":"http://creativecommons.org/licenses/by/3.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaixu Zhang, Maosong Sun","submitted_at":"2013-05-25T13:20:31Z","abstract_excerpt":"Conventional statistics-based methods for joint Chinese word segmentation and part-of-speech tagging (S&T) have generalization ability to recognize new words that do not appear in the training data. An undesirable side effect is that a number of meaningless words will be incorrectly created. We propose an effective and efficient framework for S&T that introduces features to significantly reduce meaningless words generation. A general lexicon, Wikepedia and a large-scale raw corpus of 200 billion characters are used to generate word-based features for the wordhood. The word-lattice based framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.5918","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":"2026-05-18T03:24:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQ5txLHxHp+wu0Scdouuu2ZF0W1WEqcvkiNg7M153Wd65SOyGWHcXvCQeK0UVZZgjPxl5LjdoZ7oub+3J/KPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:48:01.502175Z"},"content_sha256":"3281e63d811dbbd4ed09fddad9c6d3ca81aff3b922494b21ee2e48005b1e61ad","schema_version":"1.0","event_id":"sha256:3281e63d811dbbd4ed09fddad9c6d3ca81aff3b922494b21ee2e48005b1e61ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/bundle.json","state_url":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/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":"2026-06-03T20:48:01Z","links":{"resolver":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ","bundle":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/bundle.json","state":"https://pith.science/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2EMU7SCBMOJGYYLWW5QTLXLZOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:2EMU7SCBMOJGYYLWW5QTLXLZOZ","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":"cbd5dac193aa3d50214ad3a4969c76fd16b9560b75e412945f9eca974e95ec38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.CL","submitted_at":"2013-05-25T13:20:31Z","title_canon_sha256":"bf9cffde812cf6ddc73107191741e7e1b978761ef0a0249eae2f89745845816c"},"schema_version":"1.0","source":{"id":"1305.5918","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1305.5918","created_at":"2026-05-18T03:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"1305.5918v1","created_at":"2026-05-18T03:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1305.5918","created_at":"2026-05-18T03:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"2EMU7SCBMOJG","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"2EMU7SCBMOJGYYLW","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"2EMU7SCB","created_at":"2026-05-18T12:27:30Z"}],"graph_snapshots":[{"event_id":"sha256:3281e63d811dbbd4ed09fddad9c6d3ca81aff3b922494b21ee2e48005b1e61ad","target":"graph","created_at":"2026-05-18T03:24:53Z","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":"Conventional statistics-based methods for joint Chinese word segmentation and part-of-speech tagging (S&T) have generalization ability to recognize new words that do not appear in the training data. An undesirable side effect is that a number of meaningless words will be incorrectly created. We propose an effective and efficient framework for S&T that introduces features to significantly reduce meaningless words generation. A general lexicon, Wikepedia and a large-scale raw corpus of 200 billion characters are used to generate word-based features for the wordhood. The word-lattice based framew","authors_text":"Kaixu Zhang, Maosong Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.CL","submitted_at":"2013-05-25T13:20:31Z","title":"Reduce Meaningless Words for Joint Chinese Word Segmentation and Part-of-speech Tagging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1305.5918","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:e2a6d6d804c4c1618abb8c3408e33dde961c0128238ab62eea6dfd57e2bfa6ca","target":"record","created_at":"2026-05-18T03:24:53Z","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":"cbd5dac193aa3d50214ad3a4969c76fd16b9560b75e412945f9eca974e95ec38","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/3.0/","primary_cat":"cs.CL","submitted_at":"2013-05-25T13:20:31Z","title_canon_sha256":"bf9cffde812cf6ddc73107191741e7e1b978761ef0a0249eae2f89745845816c"},"schema_version":"1.0","source":{"id":"1305.5918","kind":"arxiv","version":1}},"canonical_sha256":"d1194fc84163926c6176b76135dd79764d00cd81b4da8ad60afbba4fe92af19f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1194fc84163926c6176b76135dd79764d00cd81b4da8ad60afbba4fe92af19f","first_computed_at":"2026-05-18T03:24:53.343301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:24:53.343301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zAOxbCXAMlJUcN0wDc+dC5vjhuLm4cFn/Zydw8Qbe7EUvclfJBNLXxcZCOelFjaMXfVEcqQ5oEwW6fag1yw/BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:24:53.343960Z","signed_message":"canonical_sha256_bytes"},"source_id":"1305.5918","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2a6d6d804c4c1618abb8c3408e33dde961c0128238ab62eea6dfd57e2bfa6ca","sha256:3281e63d811dbbd4ed09fddad9c6d3ca81aff3b922494b21ee2e48005b1e61ad"],"state_sha256":"e1f23c107e78be15d24de9ce8d0f978516f1f9928af065403dda441a57170da8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lgUG518gJ+GKidXpeiCIeLCg67DpxSKLyD2VKFVrWuj65oBunUC/qUnHaSG7C1PTlsKGOwmdXTfqfaSDA7VnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:48:01.504199Z","bundle_sha256":"ab691e02d62006be912d583db3192c0bfad3e647421349d6c9cdfc4cd1771b5c"}}