{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:A6DNMNYP6HN7UTCTTNDU7BOJOT","short_pith_number":"pith:A6DNMNYP","canonical_record":{"source":{"id":"2004.02334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T22:17:34Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"97af1be4425066ff0eda94da8ef83bc227d707b6d8a81d913ab8dbf49e67fde3","abstract_canon_sha256":"7d7fcaf24e8ab13fc9421f2a8afbf1947261f36f30a7ca0c23076dd25b47c080"},"schema_version":"1.0"},"canonical_sha256":"0786d6370ff1dbfa4c539b474f85c974ce94333e9ca27981b34f1992209149b9","source":{"kind":"arxiv","id":"2004.02334","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02334","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02334v2","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02334","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"A6DNMNYP6HN7","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"A6DNMNYP6HN7UTCT","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"A6DNMNYP","created_at":"2026-07-05T02:28:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:A6DNMNYP6HN7UTCTTNDU7BOJOT","target":"record","payload":{"canonical_record":{"source":{"id":"2004.02334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T22:17:34Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"97af1be4425066ff0eda94da8ef83bc227d707b6d8a81d913ab8dbf49e67fde3","abstract_canon_sha256":"7d7fcaf24e8ab13fc9421f2a8afbf1947261f36f30a7ca0c23076dd25b47c080"},"schema_version":"1.0"},"canonical_sha256":"0786d6370ff1dbfa4c539b474f85c974ce94333e9ca27981b34f1992209149b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:48.937481Z","signature_b64":"tKm69xRRUepIp/zICaKutpiOPULdcfPYjH/0BY/2xHYaiR5SjY90cFMKoBfJvs2wgK/XsEz9cfVPWH4di+nzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0786d6370ff1dbfa4c539b474f85c974ce94333e9ca27981b34f1992209149b9","last_reissued_at":"2026-07-05T02:28:48.937068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:48.937068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.02334","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":"2026-07-05T02:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l/KekVe2GYGsiaqMbasy05IaLzeqoVuS2cnEW6V/WROpJe0M1f8JFuJ4mAew6HAZGbFvxlw3i8ZYLaRde57tDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:40:14.548902Z"},"content_sha256":"3297a25b840b1e0f0feb5d7a5cae044ea5c255d28c13977374a1f90f3826be45","schema_version":"1.0","event_id":"sha256:3297a25b840b1e0f0feb5d7a5cae044ea5c255d28c13977374a1f90f3826be45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:A6DNMNYP6HN7UTCTTNDU7BOJOT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finding the Optimal Vocabulary Size for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jonathan May, Thamme Gowda","submitted_at":"2020-04-05T22:17:34Z","abstract_excerpt":"We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class distributions during training. Since the Zipfian nature of languages causes imbalanced classes, we explore its effect on NMT. We analyze the effect of various vocabulary sizes on NMT performance on multiple languages with many data sizes, and reveal an explanation for why certain vocabulary sizes are better than others."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02334","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.02334/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xRDIfR7isy+q36ueD9T1+FnLU7ces5oziCywT0HnPD02svMAPs/A2R3VHPD/kQ5dBes7AON33mzglq8+6yGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:40:14.549918Z"},"content_sha256":"f50af7ef7b256d02166bba815c34da6901f3942f83d80a0f0398332773edeb60","schema_version":"1.0","event_id":"sha256:f50af7ef7b256d02166bba815c34da6901f3942f83d80a0f0398332773edeb60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6DNMNYP6HN7UTCTTNDU7BOJOT/bundle.json","state_url":"https://pith.science/pith/A6DNMNYP6HN7UTCTTNDU7BOJOT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6DNMNYP6HN7UTCTTNDU7BOJOT/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":"2026-08-12T06:40:14Z","links":{"resolver":"https://pith.science/pith/A6DNMNYP6HN7UTCTTNDU7BOJOT","bundle":"https://pith.science/pith/A6DNMNYP6HN7UTCTTNDU7BOJOT/bundle.json","state":"https://pith.science/pith/A6DNMNYP6HN7UTCTTNDU7BOJOT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6DNMNYP6HN7UTCTTNDU7BOJOT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:A6DNMNYP6HN7UTCTTNDU7BOJOT","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":"7d7fcaf24e8ab13fc9421f2a8afbf1947261f36f30a7ca0c23076dd25b47c080","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T22:17:34Z","title_canon_sha256":"97af1be4425066ff0eda94da8ef83bc227d707b6d8a81d913ab8dbf49e67fde3"},"schema_version":"1.0","source":{"id":"2004.02334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02334","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02334v2","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02334","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"A6DNMNYP6HN7","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"A6DNMNYP6HN7UTCT","created_at":"2026-07-05T02:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"A6DNMNYP","created_at":"2026-07-05T02:28:48Z"}],"graph_snapshots":[{"event_id":"sha256:f50af7ef7b256d02166bba815c34da6901f3942f83d80a0f0398332773edeb60","target":"graph","created_at":"2026-07-05T02:28:48Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.02334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We cast neural machine translation (NMT) as a classification task in an autoregressive setting and analyze the limitations of both classification and autoregression components. Classifiers are known to perform better with balanced class distributions during training. Since the Zipfian nature of languages causes imbalanced classes, we explore its effect on NMT. We analyze the effect of various vocabulary sizes on NMT performance on multiple languages with many data sizes, and reveal an explanation for why certain vocabulary sizes are better than others.","authors_text":"Jonathan May, Thamme Gowda","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T22:17:34Z","title":"Finding the Optimal Vocabulary Size for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02334","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":"sha256:3297a25b840b1e0f0feb5d7a5cae044ea5c255d28c13977374a1f90f3826be45","target":"record","created_at":"2026-07-05T02:28:48Z","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":"7d7fcaf24e8ab13fc9421f2a8afbf1947261f36f30a7ca0c23076dd25b47c080","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-04-05T22:17:34Z","title_canon_sha256":"97af1be4425066ff0eda94da8ef83bc227d707b6d8a81d913ab8dbf49e67fde3"},"schema_version":"1.0","source":{"id":"2004.02334","kind":"arxiv","version":2}},"canonical_sha256":"0786d6370ff1dbfa4c539b474f85c974ce94333e9ca27981b34f1992209149b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0786d6370ff1dbfa4c539b474f85c974ce94333e9ca27981b34f1992209149b9","first_computed_at":"2026-07-05T02:28:48.937068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:48.937068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tKm69xRRUepIp/zICaKutpiOPULdcfPYjH/0BY/2xHYaiR5SjY90cFMKoBfJvs2wgK/XsEz9cfVPWH4di+nzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:48.937481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3297a25b840b1e0f0feb5d7a5cae044ea5c255d28c13977374a1f90f3826be45","sha256:f50af7ef7b256d02166bba815c34da6901f3942f83d80a0f0398332773edeb60"],"state_sha256":"e649b72bdbfb3c65df8850afccc81326b30398b2f451d1c22be06a48b768a12a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IjH9G2pI8vGg/qqYGAOmt/1wa7aCrSnBMdEOoZ170TLTtgYX9TrjRjXTrCN74vvxn55ulFvHHZIQiPU1PbhIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:40:14.557310Z","bundle_sha256":"39ebbdca9c6b77973c9fc4d11175f68aa8071c561a0c41cd8d438c24425b426e"}}