{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UMFA3MLXBOS4CV2THWQPCK43SS","short_pith_number":"pith:UMFA3MLX","schema_version":"1.0","canonical_sha256":"a30a0db1770ba5c157533da0f12b9b94aa8475fde1080729d570854bc1b41875","source":{"kind":"arxiv","id":"1902.10339","version":4},"attestation_state":"computed","paper":{"title":"How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Wenhu Chen, William Wang, Xifeng Yan, Yilin Shen, Yu Su, Zhiyu Chen","submitted_at":"2019-02-27T05:57:13Z","abstract_excerpt":"With the rapid development in deep learning, deep neural networks have been widely adopted in many real-life natural language applications. Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs. The canonical approach to select pre-defined vocabulary is based on the word frequency, where a threshold is selected to cut off the long tail distribution. However, we observed that such simple approach could easily lead to under-sized vocabulary or over-sized vocabulary issues. Therefore, we are interested in understanding how the end-task classification accuracy i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1902.10339","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T05:57:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1507fd0406f7a46be304852b7c39ea6cdf81450a9bc32ad9c550e6ac6fbd387e","abstract_canon_sha256":"a82b8c23980ee39cf33d69476c4750b31a92889b7289506f86bafe7a8ab7e75e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:27.053465Z","signature_b64":"R09aE3c1QMiDONL05i9/d8PCoFFaTyoW3hTGHBBUnQJCt3XjxY1aYvDRIhffaCcv6/bbpksWciYdgFut9TRNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30a0db1770ba5c157533da0f12b9b94aa8475fde1080729d570854bc1b41875","last_reissued_at":"2026-05-17T23:49:27.052843Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:27.052843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Wenhu Chen, William Wang, Xifeng Yan, Yilin Shen, Yu Su, Zhiyu Chen","submitted_at":"2019-02-27T05:57:13Z","abstract_excerpt":"With the rapid development in deep learning, deep neural networks have been widely adopted in many real-life natural language applications. Under deep neural networks, a pre-defined vocabulary is required to vectorize text inputs. The canonical approach to select pre-defined vocabulary is based on the word frequency, where a threshold is selected to cut off the long tail distribution. However, we observed that such simple approach could easily lead to under-sized vocabulary or over-sized vocabulary issues. Therefore, we are interested in understanding how the end-task classification accuracy i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10339","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1902.10339","created_at":"2026-05-17T23:49:27.052968+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.10339v4","created_at":"2026-05-17T23:49:27.052968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10339","created_at":"2026-05-17T23:49:27.052968+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMFA3MLXBOS4","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMFA3MLXBOS4CV2T","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMFA3MLX","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS","json":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS.json","graph_json":"https://pith.science/api/pith-number/UMFA3MLXBOS4CV2THWQPCK43SS/graph.json","events_json":"https://pith.science/api/pith-number/UMFA3MLXBOS4CV2THWQPCK43SS/events.json","paper":"https://pith.science/paper/UMFA3MLX"},"agent_actions":{"view_html":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS","download_json":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS.json","view_paper":"https://pith.science/paper/UMFA3MLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.10339&json=true","fetch_graph":"https://pith.science/api/pith-number/UMFA3MLXBOS4CV2THWQPCK43SS/graph.json","fetch_events":"https://pith.science/api/pith-number/UMFA3MLXBOS4CV2THWQPCK43SS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS/action/storage_attestation","attest_author":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS/action/author_attestation","sign_citation":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS/action/citation_signature","submit_replication":"https://pith.science/pith/UMFA3MLXBOS4CV2THWQPCK43SS/action/replication_record"}},"created_at":"2026-05-17T23:49:27.052968+00:00","updated_at":"2026-05-17T23:49:27.052968+00:00"}