{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PLNQBVNIKOTNSUOSH5OV7SZ2IS","short_pith_number":"pith:PLNQBVNI","canonical_record":{"source":{"id":"1905.05526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T11:39:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e0669b8ff835d6c5b7fb4842b53b87595b34d321f6c1aa930367a6f329c3e32","abstract_canon_sha256":"a85f0a638f070de107380fcbbaabeb43efd8bb8bd48e8455f2bfab1ba85c63ff"},"schema_version":"1.0"},"canonical_sha256":"7adb00d5a853a6d951d23f5d5fcb3a44b61d5f0949edf05a65fe77c57d73493f","source":{"kind":"arxiv","id":"1905.05526","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05526","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05526v2","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05526","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"PLNQBVNIKOTN","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"PLNQBVNIKOTNSUOS","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"PLNQBVNI","created_at":"2026-07-05T00:10:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PLNQBVNIKOTNSUOSH5OV7SZ2IS","target":"record","payload":{"canonical_record":{"source":{"id":"1905.05526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T11:39:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e0669b8ff835d6c5b7fb4842b53b87595b34d321f6c1aa930367a6f329c3e32","abstract_canon_sha256":"a85f0a638f070de107380fcbbaabeb43efd8bb8bd48e8455f2bfab1ba85c63ff"},"schema_version":"1.0"},"canonical_sha256":"7adb00d5a853a6d951d23f5d5fcb3a44b61d5f0949edf05a65fe77c57d73493f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:01.397786Z","signature_b64":"Z280klKFXpIGObylkOlUCvav5jWPRnv5wcZbKf01J0f1Ai334jgJ460dK4neu+HM5Y0fCuSNUnUkFIhemxswBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7adb00d5a853a6d951d23f5d5fcb3a44b61d5f0949edf05a65fe77c57d73493f","last_reissued_at":"2026-07-05T00:10:01.397393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:01.397393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.05526","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8W6s9DRyBSZ35IEZwJY9Hjs7oBWTm1FAdwoaNg2tGZtpNASR1mCCABhd7pf0UN8j3++lR+6MbJDMbfq/S6jLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T22:13:17.436747Z"},"content_sha256":"d6233b9eaa040cbd6ee637773f7e56efb0b8bacce6b95b5607c7dd278543380f","schema_version":"1.0","event_id":"sha256:d6233b9eaa040cbd6ee637773f7e56efb0b8bacce6b95b5607c7dd278543380f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PLNQBVNIKOTNSUOSH5OV7SZ2IS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is Word Segmentation Necessary for Deep Learning of Chinese Representations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arianna Yuan, Jiwei Li, Qinghong Han, Xiaofei Sun, Xiaoya Li, Yuxian Meng","submitted_at":"2019-05-14T11:39:43Z","abstract_excerpt":"Segmenting a chunk of text into words is usually the first step of processing Chinese text, but its necessity has rarely been explored. In this paper, we ask the fundamental question of whether Chinese word segmentation (CWS) is necessary for deep learning-based Chinese Natural Language Processing. We benchmark neural word-based models which rely on word segmentation against neural char-based models which do not involve word segmentation in four end-to-end NLP benchmark tasks: language modeling, machine translation, sentence matching/paraphrase and text classification. Through direct compariso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05526","kind":"arxiv","version":2},"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/1905.05526/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":"2026-07-05T00:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O/0cNS1r8CSDZuN2LiduB2a0jlbvzkKtx0i+W0RrvaJD/+h9CykPbbI6pnf4fLIikPaBlHQOphgaljtK+Xs6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T22:13:17.437119Z"},"content_sha256":"a6098645b47c4c40af92f21ba8241a4367d2cd3d97263241e5e70a2c6bff8329","schema_version":"1.0","event_id":"sha256:a6098645b47c4c40af92f21ba8241a4367d2cd3d97263241e5e70a2c6bff8329"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLNQBVNIKOTNSUOSH5OV7SZ2IS/bundle.json","state_url":"https://pith.science/pith/PLNQBVNIKOTNSUOSH5OV7SZ2IS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLNQBVNIKOTNSUOSH5OV7SZ2IS/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":"2026-07-18T22:13:17Z","links":{"resolver":"https://pith.science/pith/PLNQBVNIKOTNSUOSH5OV7SZ2IS","bundle":"https://pith.science/pith/PLNQBVNIKOTNSUOSH5OV7SZ2IS/bundle.json","state":"https://pith.science/pith/PLNQBVNIKOTNSUOSH5OV7SZ2IS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLNQBVNIKOTNSUOSH5OV7SZ2IS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PLNQBVNIKOTNSUOSH5OV7SZ2IS","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":"a85f0a638f070de107380fcbbaabeb43efd8bb8bd48e8455f2bfab1ba85c63ff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T11:39:43Z","title_canon_sha256":"2e0669b8ff835d6c5b7fb4842b53b87595b34d321f6c1aa930367a6f329c3e32"},"schema_version":"1.0","source":{"id":"1905.05526","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05526","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05526v2","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05526","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"PLNQBVNIKOTN","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"PLNQBVNIKOTNSUOS","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"PLNQBVNI","created_at":"2026-07-05T00:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:a6098645b47c4c40af92f21ba8241a4367d2cd3d97263241e5e70a2c6bff8329","target":"graph","created_at":"2026-07-05T00:10:01Z","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/1905.05526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Segmenting a chunk of text into words is usually the first step of processing Chinese text, but its necessity has rarely been explored. In this paper, we ask the fundamental question of whether Chinese word segmentation (CWS) is necessary for deep learning-based Chinese Natural Language Processing. We benchmark neural word-based models which rely on word segmentation against neural char-based models which do not involve word segmentation in four end-to-end NLP benchmark tasks: language modeling, machine translation, sentence matching/paraphrase and text classification. Through direct compariso","authors_text":"Arianna Yuan, Jiwei Li, Qinghong Han, Xiaofei Sun, Xiaoya Li, Yuxian Meng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T11:39:43Z","title":"Is Word Segmentation Necessary for Deep Learning of Chinese Representations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05526","kind":"arxiv","version":2},"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:d6233b9eaa040cbd6ee637773f7e56efb0b8bacce6b95b5607c7dd278543380f","target":"record","created_at":"2026-07-05T00:10:01Z","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":"a85f0a638f070de107380fcbbaabeb43efd8bb8bd48e8455f2bfab1ba85c63ff","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T11:39:43Z","title_canon_sha256":"2e0669b8ff835d6c5b7fb4842b53b87595b34d321f6c1aa930367a6f329c3e32"},"schema_version":"1.0","source":{"id":"1905.05526","kind":"arxiv","version":2}},"canonical_sha256":"7adb00d5a853a6d951d23f5d5fcb3a44b61d5f0949edf05a65fe77c57d73493f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7adb00d5a853a6d951d23f5d5fcb3a44b61d5f0949edf05a65fe77c57d73493f","first_computed_at":"2026-07-05T00:10:01.397393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:01.397393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z280klKFXpIGObylkOlUCvav5jWPRnv5wcZbKf01J0f1Ai334jgJ460dK4neu+HM5Y0fCuSNUnUkFIhemxswBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:01.397786Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05526","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6233b9eaa040cbd6ee637773f7e56efb0b8bacce6b95b5607c7dd278543380f","sha256:a6098645b47c4c40af92f21ba8241a4367d2cd3d97263241e5e70a2c6bff8329"],"state_sha256":"9a73a253c79763660790ba8c571e5e6ffa88abcb0b03cb7ac75ae08e8fc631de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vlvc+KkAHgFIcmwehDXIJFcEV7FXab5XxN5+CHjRwggw7Bp4wzyHUCFAmo3UopEtzgy0HkkhYHmw9qgeWMFRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T22:13:17.439738Z","bundle_sha256":"370148d8ceae75d0f5b399b98ca2c1933fc4ae836074d93eb362962537a3001c"}}