{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:URACZ5MBKXHYLYA3QU455RAFOF","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":"abf9f41d7d4cea11e7e786a06ae0633cd1bd247b4729e3d033985b1a9a926d72","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T20:59:56Z","title_canon_sha256":"3660e74ce8e55a099cfca7dbc2b6e060cf09965983709cfc6f714d268823eab6"},"schema_version":"1.0","source":{"id":"1810.12406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12406","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12406v1","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12406","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"URACZ5MBKXHY","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"URACZ5MBKXHYLYA3","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"URACZ5MB","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:65553926058f7a92f34463f0af05e9f8dcdf413d6386c7738d61924b57ab494f","target":"graph","created_at":"2026-05-18T00:02:02Z","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":"Neural language models have been widely used in various NLP tasks, including machine translation, next word prediction and conversational agents. However, it is challenging to deploy these models on mobile devices due to their slow prediction speed, where the bottleneck is to compute top candidates in the softmax layer. In this paper, we introduce a novel softmax layer approximation algorithm by exploiting the clustering structure of context vectors. Our algorithm uses a light-weight screening model to predict a much smaller set of candidate words based on the given context, and then conducts ","authors_text":"Cho-Jui Hsieh, Patrick H. Chen, Sanjiv Kumar, Si Si, Yang Li","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T20:59:56Z","title":"Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12406","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":"sha256:3b07c4055ff31434eff2725f074ce04927452ca5b9f9635c3cf7dd71e6a2f62b","target":"record","created_at":"2026-05-18T00:02:02Z","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":"abf9f41d7d4cea11e7e786a06ae0633cd1bd247b4729e3d033985b1a9a926d72","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T20:59:56Z","title_canon_sha256":"3660e74ce8e55a099cfca7dbc2b6e060cf09965983709cfc6f714d268823eab6"},"schema_version":"1.0","source":{"id":"1810.12406","kind":"arxiv","version":1}},"canonical_sha256":"a4402cf58155cf85e01b8539dec405716012829b74ac8d9910c4c627ea409ea9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4402cf58155cf85e01b8539dec405716012829b74ac8d9910c4c627ea409ea9","first_computed_at":"2026-05-18T00:02:02.759282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:02.759282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q8C2A4LxusqsRyCf+OGsRENzr917jI17FHcYz9BH8zTlYseqz+PwpD0HfGj3gOKRVnHfkw74uK6NA7UJozPvBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:02.759894Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b07c4055ff31434eff2725f074ce04927452ca5b9f9635c3cf7dd71e6a2f62b","sha256:65553926058f7a92f34463f0af05e9f8dcdf413d6386c7738d61924b57ab494f"],"state_sha256":"ebc8da58eda265b55996d8b66f46d4c5c616fc3028e93f340fb3b0d876ba532b"}