{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AMBPOFYWCXCQRTSUB3PQHSZYLH","short_pith_number":"pith:AMBPOFYW","canonical_record":{"source":{"id":"1703.03906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-11T04:17:46Z","cross_cats_sorted":[],"title_canon_sha256":"6aeafdf1915affae4ac741251ec41b0b6a217752bc109c73b9e883f1fda7a164","abstract_canon_sha256":"b2f03fda80d0dc9fc626d33c7c238c45c7e222f33f686d016313768c6bf60434"},"schema_version":"1.0"},"canonical_sha256":"0302f7171615c508ce540edf03cb3859e98a34212d791b68399519a912bc5501","source":{"kind":"arxiv","id":"1703.03906","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03906","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03906v2","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03906","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"AMBPOFYWCXCQ","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AMBPOFYWCXCQRTSU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AMBPOFYW","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AMBPOFYWCXCQRTSUB3PQHSZYLH","target":"record","payload":{"canonical_record":{"source":{"id":"1703.03906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-11T04:17:46Z","cross_cats_sorted":[],"title_canon_sha256":"6aeafdf1915affae4ac741251ec41b0b6a217752bc109c73b9e883f1fda7a164","abstract_canon_sha256":"b2f03fda80d0dc9fc626d33c7c238c45c7e222f33f686d016313768c6bf60434"},"schema_version":"1.0"},"canonical_sha256":"0302f7171615c508ce540edf03cb3859e98a34212d791b68399519a912bc5501","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:09.146082Z","signature_b64":"+JDjfsHYwMD2ucF70OZE1DeRn63MJ6rn95OfRIC61U9RpS+te3i3huBYtSgP4qoeNFgR769Kmsh+dkvZrou7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0302f7171615c508ce540edf03cb3859e98a34212d791b68399519a912bc5501","last_reissued_at":"2026-05-18T00:48:09.145504Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:09.145504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.03906","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cZFSxqrJq+uPumRpYEF8RQqx54NwMIKd04vNDdJ/k7/33VM8oYu2pc+I0GRc51jmIlMlwJw5mKM2vZscOQfHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:19:52.055401Z"},"content_sha256":"2d80b539293130633b54f3b87f1e3f298b7b4b7ea862f9db231e4c47bd486b79","schema_version":"1.0","event_id":"sha256:2d80b539293130633b54f3b87f1e3f298b7b4b7ea862f9db231e4c47bd486b79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AMBPOFYWCXCQRTSUB3PQHSZYLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Massive Exploration of Neural Machine Translation Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Goldie, Denny Britz, Minh-Thang Luong, Quoc Le","submitted_at":"2017-03-11T04:17:46Z","abstract_excerpt":"Neural Machine Translation (NMT) has shown remarkable progress over the past few years with production systems now being deployed to end-users. One major drawback of current architectures is that they are expensive to train, typically requiring days to weeks of GPU time to converge. This makes exhaustive hyperparameter search, as is commonly done with other neural network architectures, prohibitively expensive. In this work, we present the first large-scale analysis of NMT architecture hyperparameters. We report empirical results and variance numbers for several hundred experimental runs, corr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03906","kind":"arxiv","version":2},"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":"2026-05-18T00:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JtMv1gFJJPHIyY/yVkgKVz8Wmb3lRKeaPhLKjXz35lrYOqd/7NrX0O+FrAuFEvzowa9g+f+u1wCdUxlnOUkdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T12:19:52.056191Z"},"content_sha256":"21f46998587ab86cf725025aab1a7c05ab5b17adebb22fa097323eaf2362f0fe","schema_version":"1.0","event_id":"sha256:21f46998587ab86cf725025aab1a7c05ab5b17adebb22fa097323eaf2362f0fe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMBPOFYWCXCQRTSUB3PQHSZYLH/bundle.json","state_url":"https://pith.science/pith/AMBPOFYWCXCQRTSUB3PQHSZYLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMBPOFYWCXCQRTSUB3PQHSZYLH/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":"2026-06-03T12:19:52Z","links":{"resolver":"https://pith.science/pith/AMBPOFYWCXCQRTSUB3PQHSZYLH","bundle":"https://pith.science/pith/AMBPOFYWCXCQRTSUB3PQHSZYLH/bundle.json","state":"https://pith.science/pith/AMBPOFYWCXCQRTSUB3PQHSZYLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMBPOFYWCXCQRTSUB3PQHSZYLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AMBPOFYWCXCQRTSUB3PQHSZYLH","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":"b2f03fda80d0dc9fc626d33c7c238c45c7e222f33f686d016313768c6bf60434","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-11T04:17:46Z","title_canon_sha256":"6aeafdf1915affae4ac741251ec41b0b6a217752bc109c73b9e883f1fda7a164"},"schema_version":"1.0","source":{"id":"1703.03906","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03906","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03906v2","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03906","created_at":"2026-05-18T00:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"AMBPOFYWCXCQ","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AMBPOFYWCXCQRTSU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AMBPOFYW","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:21f46998587ab86cf725025aab1a7c05ab5b17adebb22fa097323eaf2362f0fe","target":"graph","created_at":"2026-05-18T00:48:09Z","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) has shown remarkable progress over the past few years with production systems now being deployed to end-users. One major drawback of current architectures is that they are expensive to train, typically requiring days to weeks of GPU time to converge. This makes exhaustive hyperparameter search, as is commonly done with other neural network architectures, prohibitively expensive. In this work, we present the first large-scale analysis of NMT architecture hyperparameters. We report empirical results and variance numbers for several hundred experimental runs, corr","authors_text":"Anna Goldie, Denny Britz, Minh-Thang Luong, Quoc Le","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-11T04:17:46Z","title":"Massive Exploration of Neural Machine Translation Architectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03906","kind":"arxiv","version":2},"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":"sha256:2d80b539293130633b54f3b87f1e3f298b7b4b7ea862f9db231e4c47bd486b79","target":"record","created_at":"2026-05-18T00:48:09Z","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":"b2f03fda80d0dc9fc626d33c7c238c45c7e222f33f686d016313768c6bf60434","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-11T04:17:46Z","title_canon_sha256":"6aeafdf1915affae4ac741251ec41b0b6a217752bc109c73b9e883f1fda7a164"},"schema_version":"1.0","source":{"id":"1703.03906","kind":"arxiv","version":2}},"canonical_sha256":"0302f7171615c508ce540edf03cb3859e98a34212d791b68399519a912bc5501","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0302f7171615c508ce540edf03cb3859e98a34212d791b68399519a912bc5501","first_computed_at":"2026-05-18T00:48:09.145504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:09.145504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+JDjfsHYwMD2ucF70OZE1DeRn63MJ6rn95OfRIC61U9RpS+te3i3huBYtSgP4qoeNFgR769Kmsh+dkvZrou7BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:09.146082Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.03906","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d80b539293130633b54f3b87f1e3f298b7b4b7ea862f9db231e4c47bd486b79","sha256:21f46998587ab86cf725025aab1a7c05ab5b17adebb22fa097323eaf2362f0fe"],"state_sha256":"c6087f6beb4f8445c3031f623d11ea3540f178f02dc8a3d0de53256d96bd5611"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YwpdhpPFz+S9YMny/ib9/GpEVmXPE15oY7YHyQhcq/L8BUFNWJ7dJrZPg5QzJ0wZnxO0UxYSRDA1WvrXdqAqAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T12:19:52.059509Z","bundle_sha256":"1123632fb709ecdf2e9d172b136f8511a790b9b0ac4d7df24f2701ea8e0d632a"}}