{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YWSTWI5IAUAFB6NNNBQL7JSJEI","short_pith_number":"pith:YWSTWI5I","schema_version":"1.0","canonical_sha256":"c5a53b23a8050050f9ad6860bfa649223a4876cf156bc335b46e80d0f49eccac","source":{"kind":"arxiv","id":"1806.06950","version":1},"attestation_state":"computed","paper":{"title":"GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Cho-Jui Hsieh, Ciprian Chelba, Patrick H. Chen, Si Si, Yang Li","submitted_at":"2018-06-18T23:08:15Z","abstract_excerpt":"Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more recurrent layers sandwiched between an embedding layer used for representing input tokens and a softmax layer for generating output tokens. For problems with a very large vocabulary size, the embedding and the softmax matrices can account for more than half of the model size. For instance, the bigLSTM model achieves state-of- the-art performance on the One-B"},"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":"1806.06950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-18T23:08:15Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"0b6a2d37589e2cfc9ed2db2b9bf7810d552434cc333b49f826f5907a7cea6ad1","abstract_canon_sha256":"8f2ae4f63dc7927f3b55a7cf4ecf8262781c23db011b3114053b2d6d9f837b46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:57.959464Z","signature_b64":"k9eSuYLjj0UJAQdubWwlfEGr6x5bPr9sWHnbwxp8osuWA/niVhsbNPjNAvirenBrG2hoOndlDiNhh61tJRanCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5a53b23a8050050f9ad6860bfa649223a4876cf156bc335b46e80d0f49eccac","last_reissued_at":"2026-05-18T00:12:57.958827Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:57.958827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Cho-Jui Hsieh, Ciprian Chelba, Patrick H. Chen, Si Si, Yang Li","submitted_at":"2018-06-18T23:08:15Z","abstract_excerpt":"Model compression is essential for serving large deep neural nets on devices with limited resources or applications that require real-time responses. As a case study, a state-of-the-art neural language model usually consists of one or more recurrent layers sandwiched between an embedding layer used for representing input tokens and a softmax layer for generating output tokens. For problems with a very large vocabulary size, the embedding and the softmax matrices can account for more than half of the model size. For instance, the bigLSTM model achieves state-of- the-art performance on the One-B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06950","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.06950","created_at":"2026-05-18T00:12:57.958909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.06950v1","created_at":"2026-05-18T00:12:57.958909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06950","created_at":"2026-05-18T00:12:57.958909+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWSTWI5IAUAF","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWSTWI5IAUAFB6NN","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWSTWI5I","created_at":"2026-05-18T12:33:04.347982+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/YWSTWI5IAUAFB6NNNBQL7JSJEI","json":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI.json","graph_json":"https://pith.science/api/pith-number/YWSTWI5IAUAFB6NNNBQL7JSJEI/graph.json","events_json":"https://pith.science/api/pith-number/YWSTWI5IAUAFB6NNNBQL7JSJEI/events.json","paper":"https://pith.science/paper/YWSTWI5I"},"agent_actions":{"view_html":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI","download_json":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI.json","view_paper":"https://pith.science/paper/YWSTWI5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.06950&json=true","fetch_graph":"https://pith.science/api/pith-number/YWSTWI5IAUAFB6NNNBQL7JSJEI/graph.json","fetch_events":"https://pith.science/api/pith-number/YWSTWI5IAUAFB6NNNBQL7JSJEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI/action/storage_attestation","attest_author":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI/action/author_attestation","sign_citation":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI/action/citation_signature","submit_replication":"https://pith.science/pith/YWSTWI5IAUAFB6NNNBQL7JSJEI/action/replication_record"}},"created_at":"2026-05-18T00:12:57.958909+00:00","updated_at":"2026-05-18T00:12:57.958909+00:00"}