{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GSIVB7ZT2Z7QCDP5BVMVOLBVIN","short_pith_number":"pith:GSIVB7ZT","canonical_record":{"source":{"id":"2010.12566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:53:11Z","cross_cats_sorted":[],"title_canon_sha256":"736c86f69fa3b355c839405ac3a78122bdfc4342755eef777b471b5633adebd3","abstract_canon_sha256":"13409b3bb806be71604c3207e3a02a4d52eefc9ffa3a247f3050cd97da7c1e6a"},"schema_version":"1.0"},"canonical_sha256":"349150ff33d67f010dfd0d59572c35434356e037cc8f98fd2183d1e78fbcf679","source":{"kind":"arxiv","id":"2010.12566","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12566","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12566v1","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12566","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"GSIVB7ZT2Z7Q","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"GSIVB7ZT2Z7QCDP5","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"GSIVB7ZT","created_at":"2026-07-05T01:45:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GSIVB7ZT2Z7QCDP5BVMVOLBVIN","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:53:11Z","cross_cats_sorted":[],"title_canon_sha256":"736c86f69fa3b355c839405ac3a78122bdfc4342755eef777b471b5633adebd3","abstract_canon_sha256":"13409b3bb806be71604c3207e3a02a4d52eefc9ffa3a247f3050cd97da7c1e6a"},"schema_version":"1.0"},"canonical_sha256":"349150ff33d67f010dfd0d59572c35434356e037cc8f98fd2183d1e78fbcf679","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:38.715612Z","signature_b64":"Kmdpq40jTu7T+aIN0GjZNaNmMjR4HXEQHh1sE0XGKKYoD1QzTCqlYDdaqjId0dpbr+Tf7u/bVtjKAVfIjgrcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"349150ff33d67f010dfd0d59572c35434356e037cc8f98fd2183d1e78fbcf679","last_reissued_at":"2026-07-05T01:45:38.715163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:38.715163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12566","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":"2026-07-05T01:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eZPxS9j504PbrtOg4/SF/s69rTaqOditTAs8F7LUI536THHEJ7I/3XxC4FHfexhhlYF5DqKI+337ceUREGeJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:01:41.493080Z"},"content_sha256":"34963b2ad4ce574e6deef131fb44612829b976f68f39b358087796c3768077f3","schema_version":"1.0","event_id":"sha256:34963b2ad4ce574e6deef131fb44612829b976f68f39b358087796c3768077f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GSIVB7ZT2Z7QCDP5BVMVOLBVIN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Chaudhary, Jiecao Chen, Karthik Raman, Krishna Srinivasan","submitted_at":"2020-10-23T17:53:11Z","abstract_excerpt":"Pre-trained multilingual language models such as mBERT have shown immense gains for several natural language processing (NLP) tasks, especially in the zero-shot cross-lingual setting. Most, if not all, of these pre-trained models rely on the masked-language modeling (MLM) objective as the key language learning objective. The principle behind these approaches is that predicting the masked words with the help of the surrounding text helps learn potent contextualized representations. Despite the strong representation learning capability enabled by MLM, we demonstrate an inherent limitation of MLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12566","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/2010.12566/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":"2026-07-05T01:45:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J62Ag965KcNIWnAgSXhT7S26oGwI646Op0wpc2+142JF2XGpNY5bJd6OVnMfKpNah3Y/2LtiuRb/MmybW9zDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:01:41.493576Z"},"content_sha256":"0f201be1b0ce0573ec64501ae29c63aab98029c9c18b9af7ed396322e8fcc696","schema_version":"1.0","event_id":"sha256:0f201be1b0ce0573ec64501ae29c63aab98029c9c18b9af7ed396322e8fcc696"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSIVB7ZT2Z7QCDP5BVMVOLBVIN/bundle.json","state_url":"https://pith.science/pith/GSIVB7ZT2Z7QCDP5BVMVOLBVIN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSIVB7ZT2Z7QCDP5BVMVOLBVIN/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":"2026-08-04T12:01:41Z","links":{"resolver":"https://pith.science/pith/GSIVB7ZT2Z7QCDP5BVMVOLBVIN","bundle":"https://pith.science/pith/GSIVB7ZT2Z7QCDP5BVMVOLBVIN/bundle.json","state":"https://pith.science/pith/GSIVB7ZT2Z7QCDP5BVMVOLBVIN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSIVB7ZT2Z7QCDP5BVMVOLBVIN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GSIVB7ZT2Z7QCDP5BVMVOLBVIN","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":"13409b3bb806be71604c3207e3a02a4d52eefc9ffa3a247f3050cd97da7c1e6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:53:11Z","title_canon_sha256":"736c86f69fa3b355c839405ac3a78122bdfc4342755eef777b471b5633adebd3"},"schema_version":"1.0","source":{"id":"2010.12566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12566","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12566v1","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12566","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"GSIVB7ZT2Z7Q","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"GSIVB7ZT2Z7QCDP5","created_at":"2026-07-05T01:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"GSIVB7ZT","created_at":"2026-07-05T01:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:0f201be1b0ce0573ec64501ae29c63aab98029c9c18b9af7ed396322e8fcc696","target":"graph","created_at":"2026-07-05T01:45:38Z","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/2010.12566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained multilingual language models such as mBERT have shown immense gains for several natural language processing (NLP) tasks, especially in the zero-shot cross-lingual setting. Most, if not all, of these pre-trained models rely on the masked-language modeling (MLM) objective as the key language learning objective. The principle behind these approaches is that predicting the masked words with the help of the surrounding text helps learn potent contextualized representations. Despite the strong representation learning capability enabled by MLM, we demonstrate an inherent limitation of MLM","authors_text":"Aditi Chaudhary, Jiecao Chen, Karthik Raman, Krishna Srinivasan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:53:11Z","title":"DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12566","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":"sha256:34963b2ad4ce574e6deef131fb44612829b976f68f39b358087796c3768077f3","target":"record","created_at":"2026-07-05T01:45:38Z","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":"13409b3bb806be71604c3207e3a02a4d52eefc9ffa3a247f3050cd97da7c1e6a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:53:11Z","title_canon_sha256":"736c86f69fa3b355c839405ac3a78122bdfc4342755eef777b471b5633adebd3"},"schema_version":"1.0","source":{"id":"2010.12566","kind":"arxiv","version":1}},"canonical_sha256":"349150ff33d67f010dfd0d59572c35434356e037cc8f98fd2183d1e78fbcf679","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"349150ff33d67f010dfd0d59572c35434356e037cc8f98fd2183d1e78fbcf679","first_computed_at":"2026-07-05T01:45:38.715163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:38.715163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kmdpq40jTu7T+aIN0GjZNaNmMjR4HXEQHh1sE0XGKKYoD1QzTCqlYDdaqjId0dpbr+Tf7u/bVtjKAVfIjgrcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:38.715612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34963b2ad4ce574e6deef131fb44612829b976f68f39b358087796c3768077f3","sha256:0f201be1b0ce0573ec64501ae29c63aab98029c9c18b9af7ed396322e8fcc696"],"state_sha256":"23ea15c532aac90e8170da564830f61582ee09fc8462d64c081dd8c15fb9f116"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ke7kS7gB/SCjDrE5DWnsdVjyvi2EbCrqbDclyGCHrXNACFEg5uuZ5uFdLR5RyHYMcRWXjRWQVQPHc/XHUMxSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:01:41.498163Z","bundle_sha256":"b3edb19a23fafe402c936662490a20f1a96436bcbb428a78aa588b2c0c867a44"}}