{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:F7IRPZ7TM24ENHAT2YOEGOPOYW","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":"46d62f261f742e999bf260f352a12018bf197a73c11b3d51a5b3506e180400d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T08:58:52Z","title_canon_sha256":"801109510d974df825f7e3b42a5c7ad8dceb0c5c0df2da9ea4d550388b1c75c7"},"schema_version":"1.0","source":{"id":"2112.08709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08709","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08709v2","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08709","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_12","alias_value":"F7IRPZ7TM24E","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_16","alias_value":"F7IRPZ7TM24ENHAT","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_8","alias_value":"F7IRPZ7T","created_at":"2026-07-05T04:20:31Z"}],"graph_snapshots":[{"event_id":"sha256:079ac98ba6d63be4f66af7b1fe5e898959b856a43ff1fb00e3218cacd1e9ab64","target":"graph","created_at":"2026-07-05T04:20:31Z","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/2112.08709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Siddhant, Chia-Hsuan Lee, Melvin Johnson, Viresh Ratnakar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T08:58:52Z","title":"DOCmT5: Document-Level Pretraining of Multilingual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08709","kind":"arxiv","version":2},"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:f254f01137e75a0c389b0cbeb9215e3e58796ba4ad39d54e0c657c533e6f5b6f","target":"record","created_at":"2026-07-05T04:20:31Z","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":"46d62f261f742e999bf260f352a12018bf197a73c11b3d51a5b3506e180400d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T08:58:52Z","title_canon_sha256":"801109510d974df825f7e3b42a5c7ad8dceb0c5c0df2da9ea4d550388b1c75c7"},"schema_version":"1.0","source":{"id":"2112.08709","kind":"arxiv","version":2}},"canonical_sha256":"2fd117e7f366b8469c13d61c4339eec580d6ec7fb2e4e9ef7b6c17a3ee5fcd30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fd117e7f366b8469c13d61c4339eec580d6ec7fb2e4e9ef7b6c17a3ee5fcd30","first_computed_at":"2026-07-05T04:20:31.886627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:31.886627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y2tWF3mZerzSuuUrbcpdWljZPNiconULjJEFTv0lGFEizhrHi3Aj/Y3qW8FSjqVrUWLngD9mmevr1B4nlj3yDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:31.887099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f254f01137e75a0c389b0cbeb9215e3e58796ba4ad39d54e0c657c533e6f5b6f","sha256:079ac98ba6d63be4f66af7b1fe5e898959b856a43ff1fb00e3218cacd1e9ab64"],"state_sha256":"82312d5de4e47a1dc269002892f025c1733d02114e264bda435fe310083d3b0b"}