{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:SURNGODMFNSYPQFJRO4OBUEJRU","short_pith_number":"pith:SURNGODM","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"},"canonical_sha256":"9522d3386c2b6587c0a98bb8e0d0898d24e9fd400742d2e3dc231df6b74d2c3c","source":{"kind":"arxiv","id":"1606.09274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.09274","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1606.09274v1","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.09274","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"SURNGODMFNSY","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SURNGODMFNSYPQFJ","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SURNGODM","created_at":"2026-05-18T12:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:SURNGODMFNSYPQFJRO4OBUEJRU","target":"record","payload":{"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"},"canonical_sha256":"9522d3386c2b6587c0a98bb8e0d0898d24e9fd400742d2e3dc231df6b74d2c3c","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"},"source_kind":"arxiv","source_id":"1606.09274","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x12t4cuKOE8Mtj0H73Mst26bwDN1nr8Md4UelEb9b0DDsqyTcREWOd8fbVxFQuAP62xV4EJVAAgH9Ao9KWhwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:32:28.260395Z"},"content_sha256":"011b9a9e748353ebe02296f32b85229f4b0582093ec83860a6db9af907a24aa7","schema_version":"1.0","event_id":"sha256:011b9a9e748353ebe02296f32b85229f4b0582093ec83860a6db9af907a24aa7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:SURNGODMFNSYPQFJRO4OBUEJRU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2HIqTaJqtEZlzXPW3+RES/XVHPy/3V8opCQSYJjebH/4+R8oRKZTQ8bR8m+lPhY8z0tCjaR/x9vmw/APdk1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T11:32:28.261092Z"},"content_sha256":"a8846709e3faa02f3d69e55cc1a5da378dfb7d3af93221ab2adab72a9ef52e30","schema_version":"1.0","event_id":"sha256:a8846709e3faa02f3d69e55cc1a5da378dfb7d3af93221ab2adab72a9ef52e30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/bundle.json","state_url":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SURNGODMFNSYPQFJRO4OBUEJRU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T11:32:28Z","links":{"resolver":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU","bundle":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/bundle.json","state":"https://pith.science/pith/SURNGODMFNSYPQFJRO4OBUEJRU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SURNGODMFNSYPQFJRO4OBUEJRU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:SURNGODMFNSYPQFJRO4OBUEJRU","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":"5f49dbed8b36fcd53b6d39c3e86f6afc9b1172f90544fbe218a1172bebea5505","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-29T20:36:23Z","title_canon_sha256":"01fd06e947233c768656d3b0671bdead931598377d0f2e331091a8253564bd60"},"schema_version":"1.0","source":{"id":"1606.09274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.09274","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"1606.09274v1","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.09274","created_at":"2026-05-18T01:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"SURNGODMFNSY","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"SURNGODMFNSYPQFJ","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"SURNGODM","created_at":"2026-05-18T12:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:a8846709e3faa02f3d69e55cc1a5da378dfb7d3af93221ab2adab72a9ef52e30","target":"graph","created_at":"2026-05-18T01:11:40Z","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 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","authors_text":"Abigail See, Christopher D. Manning, Minh-Thang Luong","cross_cats":["cs.CL","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-29T20:36:23Z","title":"Compression of Neural Machine Translation Models via Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.09274","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":"sha256:011b9a9e748353ebe02296f32b85229f4b0582093ec83860a6db9af907a24aa7","target":"record","created_at":"2026-05-18T01:11:40Z","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":"5f49dbed8b36fcd53b6d39c3e86f6afc9b1172f90544fbe218a1172bebea5505","cross_cats_sorted":["cs.CL","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-29T20:36:23Z","title_canon_sha256":"01fd06e947233c768656d3b0671bdead931598377d0f2e331091a8253564bd60"},"schema_version":"1.0","source":{"id":"1606.09274","kind":"arxiv","version":1}},"canonical_sha256":"9522d3386c2b6587c0a98bb8e0d0898d24e9fd400742d2e3dc231df6b74d2c3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9522d3386c2b6587c0a98bb8e0d0898d24e9fd400742d2e3dc231df6b74d2c3c","first_computed_at":"2026-05-18T01:11:40.713732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:40.713732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PeCR2suhnghUx8gZYcgboE3qOYi3k6QAPHVpTco0MsL2mOc9EwBjNWjHHEAlPCXm2uqrFPkqRLExPXXjkajvDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:40.714098Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.09274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:011b9a9e748353ebe02296f32b85229f4b0582093ec83860a6db9af907a24aa7","sha256:a8846709e3faa02f3d69e55cc1a5da378dfb7d3af93221ab2adab72a9ef52e30"],"state_sha256":"cb07c34189ad7bc369e774374e721d499b4ead8aa54b0f1fa01290b02e368a35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uhCc5olPnu25tGmNtVgE6PgoFuPXh2POFDt0oYVvougMrTGArLgFN0iAoT9VTle7WECQ1H1ikzcM9i4Yw7GCBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T11:32:28.264901Z","bundle_sha256":"a28c704f9523318271df3499970c731a292b554b3e1df1f8b9ed6f9e896a70f0"}}