{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WSX4CFVMSLSCHJG3QHV4VOEFHM","short_pith_number":"pith:WSX4CFVM","canonical_record":{"source":{"id":"2109.07306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-15T14:04:16Z","cross_cats_sorted":[],"title_canon_sha256":"68a9164d3f1876aa676d04ae122d48ee4c416ffb63b3d9a280bd15035dceaa51","abstract_canon_sha256":"3d52d1894d2f0b3c47fcb157d8875165ebefec2dc370b66acce3abb60e484cf0"},"schema_version":"1.0"},"canonical_sha256":"b4afc116ac92e423a4db81ebcab8853b1360f10f85966db7a15c3344562e5eea","source":{"kind":"arxiv","id":"2109.07306","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07306","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07306v1","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07306","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"WSX4CFVMSLSC","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"WSX4CFVMSLSCHJG3","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"WSX4CFVM","created_at":"2026-07-05T03:14:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WSX4CFVMSLSCHJG3QHV4VOEFHM","target":"record","payload":{"canonical_record":{"source":{"id":"2109.07306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-15T14:04:16Z","cross_cats_sorted":[],"title_canon_sha256":"68a9164d3f1876aa676d04ae122d48ee4c416ffb63b3d9a280bd15035dceaa51","abstract_canon_sha256":"3d52d1894d2f0b3c47fcb157d8875165ebefec2dc370b66acce3abb60e484cf0"},"schema_version":"1.0"},"canonical_sha256":"b4afc116ac92e423a4db81ebcab8853b1360f10f85966db7a15c3344562e5eea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:47.506910Z","signature_b64":"tGR+HfGfSxjOyJb9DXL7NuB4mvu6ERihrixvp4sJxUa6Gp9l+nUsJGSEtm6vT2sXTm24sHFrGMiXHgVk+YKMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4afc116ac92e423a4db81ebcab8853b1360f10f85966db7a15c3344562e5eea","last_reissued_at":"2026-07-05T03:14:47.506462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:47.506462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.07306","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":"2026-07-05T03:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hjxo5vEcJhPFqZ4yTJDxrb4k5P99aeL+fK9GxDPZY/3MTkSnGs/AGHWHpP2ZKsWMjpjHLv4T6Dg3M/zboXHbDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:41:12.192859Z"},"content_sha256":"297375fad5c043b2a8fc6fc12c73ee0f89e02460fc953c022675cf863787f505","schema_version":"1.0","event_id":"sha256:297375fad5c043b2a8fc6fc12c73ee0f89e02460fc953c022675cf863787f505"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WSX4CFVMSLSCHJG3QHV4VOEFHM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Furu Wei, Li Dong, Saksham Singhal, Shaohan Huang, Ting Liu, Wanxiang Che, Xia Song","submitted_at":"2021-09-15T14:04:16Z","abstract_excerpt":"Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity. To this end, we propose an algorithm VoCap to determine the desired vocabulary capacity of each language. However, increasing the vocabulary size significantly slows down the pre-training speed. In order to address the issues, we propose k-NN-based target sampling to accelerate the expensive softmax. Our experiments show that the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07306","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.07306/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":"2026-07-05T03:14:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lngU9jVtuEQWoJSyyD/R5w7qUaF0se4t1e6dWWx7QFpElyCGYuSfLz3WaMRL1Q5lNQVBdIlmxYruX3dlS6q5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:41:12.193713Z"},"content_sha256":"4a1d9658994dfd143bc18f7a4758b0bcac96e3308ba7b44ddc5ab0710f342372","schema_version":"1.0","event_id":"sha256:4a1d9658994dfd143bc18f7a4758b0bcac96e3308ba7b44ddc5ab0710f342372"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WSX4CFVMSLSCHJG3QHV4VOEFHM/bundle.json","state_url":"https://pith.science/pith/WSX4CFVMSLSCHJG3QHV4VOEFHM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WSX4CFVMSLSCHJG3QHV4VOEFHM/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":"2026-07-09T05:41:12Z","links":{"resolver":"https://pith.science/pith/WSX4CFVMSLSCHJG3QHV4VOEFHM","bundle":"https://pith.science/pith/WSX4CFVMSLSCHJG3QHV4VOEFHM/bundle.json","state":"https://pith.science/pith/WSX4CFVMSLSCHJG3QHV4VOEFHM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WSX4CFVMSLSCHJG3QHV4VOEFHM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WSX4CFVMSLSCHJG3QHV4VOEFHM","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":"3d52d1894d2f0b3c47fcb157d8875165ebefec2dc370b66acce3abb60e484cf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-15T14:04:16Z","title_canon_sha256":"68a9164d3f1876aa676d04ae122d48ee4c416ffb63b3d9a280bd15035dceaa51"},"schema_version":"1.0","source":{"id":"2109.07306","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.07306","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"arxiv_version","alias_value":"2109.07306v1","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07306","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"pith_short_12","alias_value":"WSX4CFVMSLSC","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"pith_short_16","alias_value":"WSX4CFVMSLSCHJG3","created_at":"2026-07-05T03:14:47Z"},{"alias_kind":"pith_short_8","alias_value":"WSX4CFVM","created_at":"2026-07-05T03:14:47Z"}],"graph_snapshots":[{"event_id":"sha256:4a1d9658994dfd143bc18f7a4758b0bcac96e3308ba7b44ddc5ab0710f342372","target":"graph","created_at":"2026-07-05T03:14:47Z","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/2109.07306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compared to monolingual models, cross-lingual models usually require a more expressive vocabulary to represent all languages adequately. We find that many languages are under-represented in recent cross-lingual language models due to the limited vocabulary capacity. To this end, we propose an algorithm VoCap to determine the desired vocabulary capacity of each language. However, increasing the vocabulary size significantly slows down the pre-training speed. In order to address the issues, we propose k-NN-based target sampling to accelerate the expensive softmax. Our experiments show that the m","authors_text":"Bo Zheng, Furu Wei, Li Dong, Saksham Singhal, Shaohan Huang, Ting Liu, Wanxiang Che, Xia Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-15T14:04:16Z","title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07306","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":"sha256:297375fad5c043b2a8fc6fc12c73ee0f89e02460fc953c022675cf863787f505","target":"record","created_at":"2026-07-05T03:14:47Z","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":"3d52d1894d2f0b3c47fcb157d8875165ebefec2dc370b66acce3abb60e484cf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-15T14:04:16Z","title_canon_sha256":"68a9164d3f1876aa676d04ae122d48ee4c416ffb63b3d9a280bd15035dceaa51"},"schema_version":"1.0","source":{"id":"2109.07306","kind":"arxiv","version":1}},"canonical_sha256":"b4afc116ac92e423a4db81ebcab8853b1360f10f85966db7a15c3344562e5eea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4afc116ac92e423a4db81ebcab8853b1360f10f85966db7a15c3344562e5eea","first_computed_at":"2026-07-05T03:14:47.506462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:47.506462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tGR+HfGfSxjOyJb9DXL7NuB4mvu6ERihrixvp4sJxUa6Gp9l+nUsJGSEtm6vT2sXTm24sHFrGMiXHgVk+YKMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:47.506910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.07306","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:297375fad5c043b2a8fc6fc12c73ee0f89e02460fc953c022675cf863787f505","sha256:4a1d9658994dfd143bc18f7a4758b0bcac96e3308ba7b44ddc5ab0710f342372"],"state_sha256":"7b24fbecc9781a0fb739b38f4a6d608d74a25a5fe53c5d3b9caca5c0f73e7181"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MyeQpPgWk7HNJKVVrjfwehjeMiEoxavFSvBfZKes/uJ9j6eFHONFaDIwKLx/3tRm6piKuqEldLCH/XxbWXUkDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:41:12.197876Z","bundle_sha256":"15fc40e486a16f9ebdecc8a3917e9c0609a8dac9c2a6d362df85afe673c57b7b"}}