{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:SURNGODMFNSYPQFJRO4OBUEJRU","short_pith_number":"pith:SURNGODM","schema_version":"1.0","canonical_sha256":"9522d3386c2b6587c0a98bb8e0d0898d24e9fd400742d2e3dc231df6b74d2c3c","source":{"kind":"arxiv","id":"1606.09274","version":1},"attestation_state":"computed","paper":{"title":"Compression of Neural Machine Translation Models via Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"cs.AI","authors_text":"Abigail See, Christopher D. Manning, Minh-Thang Luong","submitted_at":"2016-06-29T20:36:23Z","abstract_excerpt":"Neural Machine Translation (NMT), like many other deep learning domains, typically suffers from over-parameterization, resulting in large storage sizes. This paper examines three simple magnitude-based pruning schemes to compress NMT models, namely class-blind, class-uniform, and class-distribution, which differ in terms of how pruning thresholds are computed for the different classes of weights in the NMT architecture. We demonstrate the efficacy of weight pruning as a compression technique for a state-of-the-art NMT system. We show that an NMT model with over 200 million parameters can be pr"},"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":"1606.09274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-29T20:36:23Z","cross_cats_sorted":["cs.CL","cs.NE"],"title_canon_sha256":"01fd06e947233c768656d3b0671bdead931598377d0f2e331091a8253564bd60","abstract_canon_sha256":"5f49dbed8b36fcd53b6d39c3e86f6afc9b1172f90544fbe218a1172bebea5505"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:40.714098Z","signature_b64":"PeCR2suhnghUx8gZYcgboE3qOYi3k6QAPHVpTco0MsL2mOc9EwBjNWjHHEAlPCXm2uqrFPkqRLExPXXjkajvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9522d3386c2b6587c0a98bb8e0d0898d24e9fd400742d2e3dc231df6b74d2c3c","last_reissued_at":"2026-05-18T01:11:40.713732Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:40.713732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compression of Neural Machine Translation Models via Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.NE"],"primary_cat":"cs.AI","authors_text":"Abigail See, Christopher D. Manning, Minh-Thang Luong","submitted_at":"2016-06-29T20:36:23Z","abstract_excerpt":"Neural Machine Translation (NMT), like many other deep learning domains, typically suffers from over-parameterization, resulting in large storage sizes. This paper examines three simple magnitude-based pruning schemes to compress NMT models, namely class-blind, class-uniform, and class-distribution, which differ in terms of how pruning thresholds are computed for the different classes of weights in the NMT architecture. We demonstrate the efficacy of weight pruning as a compression technique for a state-of-the-art NMT system. We show that an NMT model with over 200 million parameters can be pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.09274","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":"1606.09274","created_at":"2026-05-18T01:11:40.713795+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.09274v1","created_at":"2026-05-18T01:11:40.713795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.09274","created_at":"2026-05-18T01:11:40.713795+00:00"},{"alias_kind":"pith_short_12","alias_value":"SURNGODMFNSY","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"SURNGODMFNSYPQFJ","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"SURNGODM","created_at":"2026-05-18T12:30:44.179134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.22767","citing_title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU","json":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU.json","graph_json":"https://pith.science/api/pith-number/SURNGODMFNSYPQFJRO4OBUEJRU/graph.json","events_json":"https://pith.science/api/pith-number/SURNGODMFNSYPQFJRO4OBUEJRU/events.json","paper":"https://pith.science/paper/SURNGODM"},"agent_actions":{"view_html":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU","download_json":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU.json","view_paper":"https://pith.science/paper/SURNGODM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.09274&json=true","fetch_graph":"https://pith.science/api/pith-number/SURNGODMFNSYPQFJRO4OBUEJRU/graph.json","fetch_events":"https://pith.science/api/pith-number/SURNGODMFNSYPQFJRO4OBUEJRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/action/storage_attestation","attest_author":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/action/author_attestation","sign_citation":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/action/citation_signature","submit_replication":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/action/replication_record"}},"created_at":"2026-05-18T01:11:40.713795+00:00","updated_at":"2026-05-18T01:11:40.713795+00:00"}