{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YZYFU67XONDWJN7U77C7B532EI","short_pith_number":"pith:YZYFU67X","canonical_record":{"source":{"id":"1706.03824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T19:51:00Z","cross_cats_sorted":[],"title_canon_sha256":"0234321307c4a107f0db126863e64798ada46132b6080e6ddfccd83926ec2468","abstract_canon_sha256":"b326046ca632b038a956bde907cd095591ed22ff7c2b0b2958fbbdeb9dec63bd"},"schema_version":"1.0"},"canonical_sha256":"c6705a7bf7734764b7f4ffc5f0f77a221bcb11fbd048dca3d7d289f4ca972631","source":{"kind":"arxiv","id":"1706.03824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03824","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03824v1","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03824","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"YZYFU67XONDW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"YZYFU67XONDWJN7U","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"YZYFU67X","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YZYFU67XONDWJN7U77C7B532EI","target":"record","payload":{"canonical_record":{"source":{"id":"1706.03824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T19:51:00Z","cross_cats_sorted":[],"title_canon_sha256":"0234321307c4a107f0db126863e64798ada46132b6080e6ddfccd83926ec2468","abstract_canon_sha256":"b326046ca632b038a956bde907cd095591ed22ff7c2b0b2958fbbdeb9dec63bd"},"schema_version":"1.0"},"canonical_sha256":"c6705a7bf7734764b7f4ffc5f0f77a221bcb11fbd048dca3d7d289f4ca972631","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:28.293150Z","signature_b64":"ssTsnMPcn7DRIETqV+YX8zLA12SuGHv7V8dI6Xd6b2BzW3R6cMaYguGeGQwYs3v/vBoZa8v2H5AamfIU3FlPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6705a7bf7734764b7f4ffc5f0f77a221bcb11fbd048dca3d7d289f4ca972631","last_reissued_at":"2026-05-18T00:42:28.292632Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:28.292632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.03824","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":"2026-05-18T00:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IICQf/wJ9bOieHCZXvb9PPuMw36dTm063tXlpBrIfWyqpv3AYQ0aGo29QTKMAztoWCV2Myq/juTy2x6RHTsYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:25:49.753433Z"},"content_sha256":"b02567711623157d531c3a2e62d78242322257a88b1108a314039e07923a743e","schema_version":"1.0","event_id":"sha256:b02567711623157d531c3a2e62d78242322257a88b1108a314039e07923a743e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YZYFU67XONDWJN7U77C7B532EI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention-based Vocabulary Selection for NMT Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baskaran Sankaran, Markus Freitag, Yaser Al-Onaizan","submitted_at":"2017-06-12T19:51:00Z","abstract_excerpt":"Neural Machine Translation (NMT) models usually use large target vocabulary sizes to capture most of the words in the target language. The vocabulary size is a big factor when decoding new sentences as the final softmax layer normalizes over all possible target words. To address this problem, it is widely common to restrict the target vocabulary with candidate lists based on the source sentence. Usually, the candidate lists are a combination of external word-to-word aligner, phrase table entries or most frequent words. In this work, we propose a simple and yet novel approach to learn candidate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03824","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":"2026-05-18T00:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0TPnuc7gy5Sy54DgPoAttZcDbGLGAA8EoLjOv6mmOXLwVa5GHJX0Q5AeABIrhLxGDOb/Fz7XuhmBSskfSfYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:25:49.753851Z"},"content_sha256":"5302f9ad4609b5c9d0b5c2fe01e9109396e428a3fe9abf494e5fafd15b9a861e","schema_version":"1.0","event_id":"sha256:5302f9ad4609b5c9d0b5c2fe01e9109396e428a3fe9abf494e5fafd15b9a861e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZYFU67XONDWJN7U77C7B532EI/bundle.json","state_url":"https://pith.science/pith/YZYFU67XONDWJN7U77C7B532EI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZYFU67XONDWJN7U77C7B532EI/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":"2026-05-29T16:25:49Z","links":{"resolver":"https://pith.science/pith/YZYFU67XONDWJN7U77C7B532EI","bundle":"https://pith.science/pith/YZYFU67XONDWJN7U77C7B532EI/bundle.json","state":"https://pith.science/pith/YZYFU67XONDWJN7U77C7B532EI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZYFU67XONDWJN7U77C7B532EI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YZYFU67XONDWJN7U77C7B532EI","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":"b326046ca632b038a956bde907cd095591ed22ff7c2b0b2958fbbdeb9dec63bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T19:51:00Z","title_canon_sha256":"0234321307c4a107f0db126863e64798ada46132b6080e6ddfccd83926ec2468"},"schema_version":"1.0","source":{"id":"1706.03824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.03824","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"1706.03824v1","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03824","created_at":"2026-05-18T00:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"YZYFU67XONDW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"YZYFU67XONDWJN7U","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"YZYFU67X","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:5302f9ad4609b5c9d0b5c2fe01e9109396e428a3fe9abf494e5fafd15b9a861e","target":"graph","created_at":"2026-05-18T00:42:28Z","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) models usually use large target vocabulary sizes to capture most of the words in the target language. The vocabulary size is a big factor when decoding new sentences as the final softmax layer normalizes over all possible target words. To address this problem, it is widely common to restrict the target vocabulary with candidate lists based on the source sentence. Usually, the candidate lists are a combination of external word-to-word aligner, phrase table entries or most frequent words. In this work, we propose a simple and yet novel approach to learn candidate","authors_text":"Baskaran Sankaran, Markus Freitag, Yaser Al-Onaizan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T19:51:00Z","title":"Attention-based Vocabulary Selection for NMT Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03824","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:b02567711623157d531c3a2e62d78242322257a88b1108a314039e07923a743e","target":"record","created_at":"2026-05-18T00:42:28Z","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":"b326046ca632b038a956bde907cd095591ed22ff7c2b0b2958fbbdeb9dec63bd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T19:51:00Z","title_canon_sha256":"0234321307c4a107f0db126863e64798ada46132b6080e6ddfccd83926ec2468"},"schema_version":"1.0","source":{"id":"1706.03824","kind":"arxiv","version":1}},"canonical_sha256":"c6705a7bf7734764b7f4ffc5f0f77a221bcb11fbd048dca3d7d289f4ca972631","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6705a7bf7734764b7f4ffc5f0f77a221bcb11fbd048dca3d7d289f4ca972631","first_computed_at":"2026-05-18T00:42:28.292632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:28.292632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ssTsnMPcn7DRIETqV+YX8zLA12SuGHv7V8dI6Xd6b2BzW3R6cMaYguGeGQwYs3v/vBoZa8v2H5AamfIU3FlPCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:28.293150Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.03824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b02567711623157d531c3a2e62d78242322257a88b1108a314039e07923a743e","sha256:5302f9ad4609b5c9d0b5c2fe01e9109396e428a3fe9abf494e5fafd15b9a861e"],"state_sha256":"1d6e4f5e521fecca13bbd2ea41d6a63181dea57d43631984ca4d6071ece65bc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kKwudEY2b5bMFpU2nCGGA2HLkIto80ek/D38dNXDToUZgs3Gv+5vpi1NjAueHNMoqkftpDaDoxInhnniRGwzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:25:49.756309Z","bundle_sha256":"61f7e2765d15d540f647e357d43828f23e91ba1e54d649b9a93b1d6bf27a8089"}}