{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2FARITXWSPIRXGLMTTS4TRVXCF","short_pith_number":"pith:2FARITXW","canonical_record":{"source":{"id":"2012.05958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T20:29:34Z","cross_cats_sorted":[],"title_canon_sha256":"ca5f59eff708bc26c23b77ea0c635b2c9c6ebb333d01235f3263cd603c097076","abstract_canon_sha256":"01e73e0588849bff05e102c9a89d30cf9c8227cd4fed5a438d853f60b28d8261"},"schema_version":"1.0"},"canonical_sha256":"d141144ef693d11b996c9ce5c9c6b71140f367db218d055c725836ea35cb3b4f","source":{"kind":"arxiv","id":"2012.05958","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05958","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05958v1","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05958","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"2FARITXWSPIR","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"2FARITXWSPIRXGLM","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"2FARITXW","created_at":"2026-07-05T01:58:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2FARITXWSPIRXGLMTTS4TRVXCF","target":"record","payload":{"canonical_record":{"source":{"id":"2012.05958","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T20:29:34Z","cross_cats_sorted":[],"title_canon_sha256":"ca5f59eff708bc26c23b77ea0c635b2c9c6ebb333d01235f3263cd603c097076","abstract_canon_sha256":"01e73e0588849bff05e102c9a89d30cf9c8227cd4fed5a438d853f60b28d8261"},"schema_version":"1.0"},"canonical_sha256":"d141144ef693d11b996c9ce5c9c6b71140f367db218d055c725836ea35cb3b4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:45.363331Z","signature_b64":"7hmAwjOZgt6UVzPa4uzDXTHjVRoWIBQsn2V7HvzTz18G1hbYJIOWnhO+Svux15SRgg5gp+p4NCCjDix2dZbyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d141144ef693d11b996c9ce5c9c6b71140f367db218d055c725836ea35cb3b4f","last_reissued_at":"2026-07-05T01:58:45.361853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:45.361853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.05958","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":"2026-07-05T01:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jYhmj9vxZCeElJMh5KZJfimKB3z/UHyegyc5K+J4a8EIn+pKlDS5mbriA6JgH6Sn4CMawmvRBwEbIlaUktFlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:44:23.442575Z"},"content_sha256":"d0050796b31c386ee0190d439f8b9a2a200d50cae4c181b1ebfefac36768a7bb","schema_version":"1.0","event_id":"sha256:d0050796b31c386ee0190d439f8b9a2a200d50cae4c181b1ebfefac36768a7bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2FARITXWSPIRXGLMTTS4TRVXCF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Transfer Learning for QA Using Translation as Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avirup Sil, Lin Pan, Mihaela Bornea, Radu Florian, Sara Rosenthal","submitted_at":"2020-12-10T20:29:34Z","abstract_excerpt":"Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages. In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. Our first strategy augments the original English training data with machine translation-generated data. This results in a corpus of multilingual silver-labeled QA pairs that is 14 times larger than the original training set. In ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05958","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/2012.05958/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":"2026-07-05T01:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v98tWIIHA5flLw7QHQkwLZ0zE5tZLPpe0Kv8Y3wv+SgqxKtsg4RnIuDLEoe3K2Ag7bF7gifgu420sLyx4z6gAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:44:23.442946Z"},"content_sha256":"26f79167315433c04fe791e6eae9af504967757790924166a46ddb740f986f4e","schema_version":"1.0","event_id":"sha256:26f79167315433c04fe791e6eae9af504967757790924166a46ddb740f986f4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2FARITXWSPIRXGLMTTS4TRVXCF/bundle.json","state_url":"https://pith.science/pith/2FARITXWSPIRXGLMTTS4TRVXCF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2FARITXWSPIRXGLMTTS4TRVXCF/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":"2026-07-07T03:44:23Z","links":{"resolver":"https://pith.science/pith/2FARITXWSPIRXGLMTTS4TRVXCF","bundle":"https://pith.science/pith/2FARITXWSPIRXGLMTTS4TRVXCF/bundle.json","state":"https://pith.science/pith/2FARITXWSPIRXGLMTTS4TRVXCF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2FARITXWSPIRXGLMTTS4TRVXCF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2FARITXWSPIRXGLMTTS4TRVXCF","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":"01e73e0588849bff05e102c9a89d30cf9c8227cd4fed5a438d853f60b28d8261","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T20:29:34Z","title_canon_sha256":"ca5f59eff708bc26c23b77ea0c635b2c9c6ebb333d01235f3263cd603c097076"},"schema_version":"1.0","source":{"id":"2012.05958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05958","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05958v1","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05958","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"2FARITXWSPIR","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"2FARITXWSPIRXGLM","created_at":"2026-07-05T01:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"2FARITXW","created_at":"2026-07-05T01:58:45Z"}],"graph_snapshots":[{"event_id":"sha256:26f79167315433c04fe791e6eae9af504967757790924166a46ddb740f986f4e","target":"graph","created_at":"2026-07-05T01:58:45Z","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/2012.05958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a QA model on English and test on other languages. In this work, we explore strategies that improve cross-lingual transfer by bringing the multilingual embeddings closer in the semantic space. Our first strategy augments the original English training data with machine translation-generated data. This results in a corpus of multilingual silver-labeled QA pairs that is 14 times larger than the original training set. In ad","authors_text":"Avirup Sil, Lin Pan, Mihaela Bornea, Radu Florian, Sara Rosenthal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T20:29:34Z","title":"Multilingual Transfer Learning for QA Using Translation as Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05958","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:d0050796b31c386ee0190d439f8b9a2a200d50cae4c181b1ebfefac36768a7bb","target":"record","created_at":"2026-07-05T01:58:45Z","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":"01e73e0588849bff05e102c9a89d30cf9c8227cd4fed5a438d853f60b28d8261","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-10T20:29:34Z","title_canon_sha256":"ca5f59eff708bc26c23b77ea0c635b2c9c6ebb333d01235f3263cd603c097076"},"schema_version":"1.0","source":{"id":"2012.05958","kind":"arxiv","version":1}},"canonical_sha256":"d141144ef693d11b996c9ce5c9c6b71140f367db218d055c725836ea35cb3b4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d141144ef693d11b996c9ce5c9c6b71140f367db218d055c725836ea35cb3b4f","first_computed_at":"2026-07-05T01:58:45.361853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:45.361853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7hmAwjOZgt6UVzPa4uzDXTHjVRoWIBQsn2V7HvzTz18G1hbYJIOWnhO+Svux15SRgg5gp+p4NCCjDix2dZbyBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:45.363331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0050796b31c386ee0190d439f8b9a2a200d50cae4c181b1ebfefac36768a7bb","sha256:26f79167315433c04fe791e6eae9af504967757790924166a46ddb740f986f4e"],"state_sha256":"615e31bb464c21f296620ce693cb726e1d17f9bebba3c279df83d008250ab398"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fPOZVMGamqQrNKe/BBDi1n2zcEDSoSDFGRkTiyAZAwMJyx7d0bH4Ca46p2+ytXFHD3OajUTenGIAFdYRvnPUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:44:23.444953Z","bundle_sha256":"fa4ca440201f2e9d2bd57c7beb37afaeab168eca018f8080e57d2f6e074eb01b"}}