{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VMJDU7QNMMBBL53GCXHFVE5LOB","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":"83217d9e21c7fb0eef21d63e53b72352c01bb076ed57778c684af9c5f795dd87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T03:05:28Z","title_canon_sha256":"00cd05dfe976ff4b55dc5b6077eb5ef75d75e02032355bdfc88a715f0d1b2945"},"schema_version":"1.0","source":{"id":"2002.07972","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.07972","created_at":"2026-07-05T01:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2002.07972v2","created_at":"2026-07-05T01:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07972","created_at":"2026-07-05T01:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"VMJDU7QNMMBB","created_at":"2026-07-05T01:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"VMJDU7QNMMBBL53G","created_at":"2026-07-05T01:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"VMJDU7QN","created_at":"2026-07-05T01:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:649c14744fe8361386d85d261aa52ef713cb4524c42d7545e1c33662a94f503d","target":"graph","created_at":"2026-07-05T01:03:08Z","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/2002.07972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models. Built upon PyTorch and Transformers, MT-DNN is designed to facilitate rapid customization for a broad spectrum of NLU tasks, using a variety of objectives (classification, regression, structured prediction) and text encoders (e.g., RNNs, BERT, RoBERTa, UniLM). A unique feature of MT-DNN is its built-in support for robust and transferable learning using the adversarial multi-task learning paradigm. To enable efficient producti","authors_text":"Emmanuel Awa, Guihong Cao, Hao Cheng, Hoifung Poon, Jianfeng Gao, Jianshu Ji, Pengcheng He, Weizhu Chen, XiaoDong Liu, Xueyun Zhu, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T03:05:28Z","title":"The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07972","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":"sha256:0cef65c24783f43c2f0a90a916941f5e2aa535383fe6decbe925f1aa3f8c108b","target":"record","created_at":"2026-07-05T01:03:08Z","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":"83217d9e21c7fb0eef21d63e53b72352c01bb076ed57778c684af9c5f795dd87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-19T03:05:28Z","title_canon_sha256":"00cd05dfe976ff4b55dc5b6077eb5ef75d75e02032355bdfc88a715f0d1b2945"},"schema_version":"1.0","source":{"id":"2002.07972","kind":"arxiv","version":2}},"canonical_sha256":"ab123a7e0d630215f76615ce5a93ab705840d9155426fb0e51fb79a859ea8e8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab123a7e0d630215f76615ce5a93ab705840d9155426fb0e51fb79a859ea8e8a","first_computed_at":"2026-07-05T01:03:08.029718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:08.029718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qk8ZQrukFyV/1UuWySC4vT+Mi7F7FvB+mgahKt4dngs+2x+fOn5HFIprObGEmLjKYoZHyDnn/YayVjZ0Qh/bAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:08.030198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.07972","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cef65c24783f43c2f0a90a916941f5e2aa535383fe6decbe925f1aa3f8c108b","sha256:649c14744fe8361386d85d261aa52ef713cb4524c42d7545e1c33662a94f503d"],"state_sha256":"1dae647ec523147f1eae81581d27a27993c75a71757ad47fe1ace428b8486b3d"}