{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UMFA3MLXBOS4CV2THWQPCK43SS","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":"a82b8c23980ee39cf33d69476c4750b31a92889b7289506f86bafe7a8ab7e75e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T05:57:13Z","title_canon_sha256":"1507fd0406f7a46be304852b7c39ea6cdf81450a9bc32ad9c550e6ac6fbd387e"},"schema_version":"1.0","source":{"id":"1902.10339","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10339","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10339v4","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10339","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"UMFA3MLXBOS4","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UMFA3MLXBOS4CV2T","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UMFA3MLX","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:6a1f3cab88d846bca91313a0aad032db99173c6b3bd3a1c1d0b0aacee94d3e23","target":"graph","created_at":"2026-05-17T23:49:27Z","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":"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","authors_text":"Wenhu Chen, William Wang, Xifeng Yan, Yilin Shen, Yu Su, Zhiyu Chen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T05:57:13Z","title":"How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10339","kind":"arxiv","version":4},"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":"sha256:90c1bc1e5bb9a35e47e38636577ebab1a1d907fe639589fdcc6bc0f7a1ea9b40","target":"record","created_at":"2026-05-17T23:49:27Z","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":"a82b8c23980ee39cf33d69476c4750b31a92889b7289506f86bafe7a8ab7e75e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-27T05:57:13Z","title_canon_sha256":"1507fd0406f7a46be304852b7c39ea6cdf81450a9bc32ad9c550e6ac6fbd387e"},"schema_version":"1.0","source":{"id":"1902.10339","kind":"arxiv","version":4}},"canonical_sha256":"a30a0db1770ba5c157533da0f12b9b94aa8475fde1080729d570854bc1b41875","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a30a0db1770ba5c157533da0f12b9b94aa8475fde1080729d570854bc1b41875","first_computed_at":"2026-05-17T23:49:27.052843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:27.052843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R09aE3c1QMiDONL05i9/d8PCoFFaTyoW3hTGHBBUnQJCt3XjxY1aYvDRIhffaCcv6/bbpksWciYdgFut9TRNDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:27.053465Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10339","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90c1bc1e5bb9a35e47e38636577ebab1a1d907fe639589fdcc6bc0f7a1ea9b40","sha256:6a1f3cab88d846bca91313a0aad032db99173c6b3bd3a1c1d0b0aacee94d3e23"],"state_sha256":"8275d7db6818ca967b2915e7fa5ae4bb64d59a932a929582c0b2bd4208d69306"}