{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:F7IRPZ7TM24ENHAT2YOEGOPOYW","short_pith_number":"pith:F7IRPZ7T","schema_version":"1.0","canonical_sha256":"2fd117e7f366b8469c13d61c4339eec580d6ec7fb2e4e9ef7b6c17a3ee5fcd30","source":{"kind":"arxiv","id":"2112.08709","version":2},"attestation_state":"computed","paper":{"title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Chia-Hsuan Lee, Melvin Johnson, Viresh Ratnakar","submitted_at":"2021-12-16T08:58:52Z","abstract_excerpt":"In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pretrained model that can understand and generate long documents. We propose a simple and effective pretraining objective - Document reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated. DrMT brings consistent improvements over strong baselines on a variety of document-level genera"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2112.08709","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T08:58:52Z","cross_cats_sorted":[],"title_canon_sha256":"801109510d974df825f7e3b42a5c7ad8dceb0c5c0df2da9ea4d550388b1c75c7","abstract_canon_sha256":"46d62f261f742e999bf260f352a12018bf197a73c11b3d51a5b3506e180400d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:31.887099Z","signature_b64":"Y2tWF3mZerzSuuUrbcpdWljZPNiconULjJEFTv0lGFEizhrHi3Aj/Y3qW8FSjqVrUWLngD9mmevr1B4nlj3yDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fd117e7f366b8469c13d61c4339eec580d6ec7fb2e4e9ef7b6c17a3ee5fcd30","last_reissued_at":"2026-07-05T04:20:31.886627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:31.886627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Chia-Hsuan Lee, Melvin Johnson, Viresh Ratnakar","submitted_at":"2021-12-16T08:58:52Z","abstract_excerpt":"In this paper, we introduce DOCmT5, a multilingual sequence-to-sequence language model pretrained with large scale parallel documents. While previous approaches have focused on leveraging sentence-level parallel data, we try to build a general-purpose pretrained model that can understand and generate long documents. We propose a simple and effective pretraining objective - Document reordering Machine Translation (DrMT), in which the input documents that are shuffled and masked need to be translated. DrMT brings consistent improvements over strong baselines on a variety of document-level genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08709","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/2112.08709/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2112.08709","created_at":"2026-07-05T04:20:31.886687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08709v2","created_at":"2026-07-05T04:20:31.886687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08709","created_at":"2026-07-05T04:20:31.886687+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7IRPZ7TM24E","created_at":"2026-07-05T04:20:31.886687+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7IRPZ7TM24ENHAT","created_at":"2026-07-05T04:20:31.886687+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7IRPZ7T","created_at":"2026-07-05T04:20:31.886687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW","json":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW.json","graph_json":"https://pith.science/api/pith-number/F7IRPZ7TM24ENHAT2YOEGOPOYW/graph.json","events_json":"https://pith.science/api/pith-number/F7IRPZ7TM24ENHAT2YOEGOPOYW/events.json","paper":"https://pith.science/paper/F7IRPZ7T"},"agent_actions":{"view_html":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW","download_json":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW.json","view_paper":"https://pith.science/paper/F7IRPZ7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08709&json=true","fetch_graph":"https://pith.science/api/pith-number/F7IRPZ7TM24ENHAT2YOEGOPOYW/graph.json","fetch_events":"https://pith.science/api/pith-number/F7IRPZ7TM24ENHAT2YOEGOPOYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW/action/storage_attestation","attest_author":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW/action/author_attestation","sign_citation":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW/action/citation_signature","submit_replication":"https://pith.science/pith/F7IRPZ7TM24ENHAT2YOEGOPOYW/action/replication_record"}},"created_at":"2026-07-05T04:20:31.886687+00:00","updated_at":"2026-07-05T04:20:31.886687+00:00"}