{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6XBLTDCH77HVIH2NDPG3UJQNT2","short_pith_number":"pith:6XBLTDCH","canonical_record":{"source":{"id":"2010.11934","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T17:58:14Z","cross_cats_sorted":[],"title_canon_sha256":"0543b28134c097d7464d5bca55551922817efb8417c6b766938362bd725cfdf7","abstract_canon_sha256":"3294fe684013b82b5768b76e246048fca843970c418abc521f549e0e92a44c6d"},"schema_version":"1.0"},"canonical_sha256":"f5c2b98c47ffcf541f4d1bcdba260d9ea34295767ae3af1465612e95e8e70cb8","source":{"kind":"arxiv","id":"2010.11934","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11934","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11934v3","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11934","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"6XBLTDCH77HV","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"6XBLTDCH77HVIH2N","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"6XBLTDCH","created_at":"2026-07-05T02:22:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6XBLTDCH77HVIH2NDPG3UJQNT2","target":"record","payload":{"canonical_record":{"source":{"id":"2010.11934","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T17:58:14Z","cross_cats_sorted":[],"title_canon_sha256":"0543b28134c097d7464d5bca55551922817efb8417c6b766938362bd725cfdf7","abstract_canon_sha256":"3294fe684013b82b5768b76e246048fca843970c418abc521f549e0e92a44c6d"},"schema_version":"1.0"},"canonical_sha256":"f5c2b98c47ffcf541f4d1bcdba260d9ea34295767ae3af1465612e95e8e70cb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:16.956683Z","signature_b64":"KmgUfIn7fkSpfjiuO2n00MU6XwaNSooswVgVxAqHJRK9Njejj9JgXPJmJJ9pXOju9uquVyaCD0zHX6qwRKHMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5c2b98c47ffcf541f4d1bcdba260d9ea34295767ae3af1465612e95e8e70cb8","last_reissued_at":"2026-07-05T02:22:16.956205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:16.956205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.11934","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iIV/VYnURCCfV4WeQ7RhRQtZ0durvzgHQqRYQGRPtJNXoWPkenxCezVLpLQLn0YsT1dSQkBSFfVOw7EfLSb+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:39:17.019782Z"},"content_sha256":"8f4215fc85ffe4e58d46ee92b35ac48917c5417b5ee9eabe1df7a16220d717fc","schema_version":"1.0","event_id":"sha256:8f4215fc85ffe4e58d46ee92b35ac48917c5417b5ee9eabe1df7a16220d717fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6XBLTDCH77HVIH2NDPG3UJQNT2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"mT5: A massively multilingual pre-trained text-to-text transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Roberts, Aditya Barua, Aditya Siddhant, Colin Raffel, Linting Xue, Mihir Kale, Noah Constant, Rami Al-Rfou","submitted_at":"2020-10-22T17:58:14Z","abstract_excerpt":"The recent \"Text-to-Text Transfer Transformer\" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent \"accidental translation\" in the zero-shot setting, where a generative model chooses to (part"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11934","kind":"arxiv","version":3},"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/2010.11934/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":"2026-07-05T02:22:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QweVdPYcCAiiRroTLOnHuOaBfXFdvfKdT1pwz7fyvYaNYwcx+mWBzKs4stNgTzJh8UDidRUTGTrOvb9jNeDCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:39:17.020274Z"},"content_sha256":"19011ad83284e55da78aa51eede1bf4f1c061f219a3685fb065200ffa080cdd9","schema_version":"1.0","event_id":"sha256:19011ad83284e55da78aa51eede1bf4f1c061f219a3685fb065200ffa080cdd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XBLTDCH77HVIH2NDPG3UJQNT2/bundle.json","state_url":"https://pith.science/pith/6XBLTDCH77HVIH2NDPG3UJQNT2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XBLTDCH77HVIH2NDPG3UJQNT2/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":"2026-08-04T09:39:17Z","links":{"resolver":"https://pith.science/pith/6XBLTDCH77HVIH2NDPG3UJQNT2","bundle":"https://pith.science/pith/6XBLTDCH77HVIH2NDPG3UJQNT2/bundle.json","state":"https://pith.science/pith/6XBLTDCH77HVIH2NDPG3UJQNT2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XBLTDCH77HVIH2NDPG3UJQNT2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6XBLTDCH77HVIH2NDPG3UJQNT2","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":"3294fe684013b82b5768b76e246048fca843970c418abc521f549e0e92a44c6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T17:58:14Z","title_canon_sha256":"0543b28134c097d7464d5bca55551922817efb8417c6b766938362bd725cfdf7"},"schema_version":"1.0","source":{"id":"2010.11934","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11934","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11934v3","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11934","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_12","alias_value":"6XBLTDCH77HV","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_16","alias_value":"6XBLTDCH77HVIH2N","created_at":"2026-07-05T02:22:16Z"},{"alias_kind":"pith_short_8","alias_value":"6XBLTDCH","created_at":"2026-07-05T02:22:16Z"}],"graph_snapshots":[{"event_id":"sha256:19011ad83284e55da78aa51eede1bf4f1c061f219a3685fb065200ffa080cdd9","target":"graph","created_at":"2026-07-05T02:22:16Z","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/2010.11934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent \"Text-to-Text Transfer Transformer\" (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent \"accidental translation\" in the zero-shot setting, where a generative model chooses to (part","authors_text":"Adam Roberts, Aditya Barua, Aditya Siddhant, Colin Raffel, Linting Xue, Mihir Kale, Noah Constant, Rami Al-Rfou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T17:58:14Z","title":"mT5: A massively multilingual pre-trained text-to-text transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11934","kind":"arxiv","version":3},"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":"sha256:8f4215fc85ffe4e58d46ee92b35ac48917c5417b5ee9eabe1df7a16220d717fc","target":"record","created_at":"2026-07-05T02:22:16Z","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":"3294fe684013b82b5768b76e246048fca843970c418abc521f549e0e92a44c6d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-22T17:58:14Z","title_canon_sha256":"0543b28134c097d7464d5bca55551922817efb8417c6b766938362bd725cfdf7"},"schema_version":"1.0","source":{"id":"2010.11934","kind":"arxiv","version":3}},"canonical_sha256":"f5c2b98c47ffcf541f4d1bcdba260d9ea34295767ae3af1465612e95e8e70cb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5c2b98c47ffcf541f4d1bcdba260d9ea34295767ae3af1465612e95e8e70cb8","first_computed_at":"2026-07-05T02:22:16.956205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:16.956205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KmgUfIn7fkSpfjiuO2n00MU6XwaNSooswVgVxAqHJRK9Njejj9JgXPJmJJ9pXOju9uquVyaCD0zHX6qwRKHMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:16.956683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11934","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f4215fc85ffe4e58d46ee92b35ac48917c5417b5ee9eabe1df7a16220d717fc","sha256:19011ad83284e55da78aa51eede1bf4f1c061f219a3685fb065200ffa080cdd9"],"state_sha256":"f0fc39b88b089445cd1b5fd76abf8ee901ed94d8e40562ecfb9101891bbae90a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQN7uT34FhqpYvg8sdkf8BRBXk6+HohY46Fs8sbaFEHQZUnxmnjGGI50oBig/DYp1xzoOcr+8VmmEYuOgU+KDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:39:17.025399Z","bundle_sha256":"34cae49c990aba9b36ea8176b9a09d67c04db0ff276bb243119ccbba3a6f2f01"}}