{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HMXFZHIIW6YN75WYFJSECE3JO4","short_pith_number":"pith:HMXFZHII","canonical_record":{"source":{"id":"1901.11504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-31T18:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"f7f03101d77075e3c232a14f053d0ff50872cf58ce2fac6c76dce64f9848e512","abstract_canon_sha256":"63025ca624c5ac5bc37ea5414af23b3e3d29b90654e850eace380e97076d0d3b"},"schema_version":"1.0"},"canonical_sha256":"3b2e5c9d08b7b0dff6d82a64411369771f5a6c19f5fc40bfe5604547ddb9d28d","source":{"kind":"arxiv","id":"1901.11504","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11504","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11504v2","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11504","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"HMXFZHIIW6YN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HMXFZHIIW6YN75WY","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HMXFZHII","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HMXFZHIIW6YN75WYFJSECE3JO4","target":"record","payload":{"canonical_record":{"source":{"id":"1901.11504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-31T18:07:25Z","cross_cats_sorted":[],"title_canon_sha256":"f7f03101d77075e3c232a14f053d0ff50872cf58ce2fac6c76dce64f9848e512","abstract_canon_sha256":"63025ca624c5ac5bc37ea5414af23b3e3d29b90654e850eace380e97076d0d3b"},"schema_version":"1.0"},"canonical_sha256":"3b2e5c9d08b7b0dff6d82a64411369771f5a6c19f5fc40bfe5604547ddb9d28d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:42.532202Z","signature_b64":"93LsFEpgkxxodJay15axX9DkJ80qV5V2Ue5RCHscgWyWGPpk4m8pU7SisbN6nIE/lJq2dAQ5BL6fVaHs5t98Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b2e5c9d08b7b0dff6d82a64411369771f5a6c19f5fc40bfe5604547ddb9d28d","last_reissued_at":"2026-05-17T23:44:42.531685Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:42.531685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.11504","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"85fK6NCLuGRCU7hjxHWiI7qgfNcHPR1/g7fh4D8bERn9r4wLJlVCxr8iYz+aHT/4u6PkT7D+yUEvX+VGUJg9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T11:18:18.975277Z"},"content_sha256":"8488270675ef49ce20ff3f65c66bb22ff4cd3cdfa0072b6bcd8f7e48bdb2efd5","schema_version":"1.0","event_id":"sha256:8488270675ef49ce20ff3f65c66bb22ff4cd3cdfa0072b6bcd8f7e48bdb2efd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HMXFZHIIW6YN75WYFJSECE3JO4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Deep Neural Networks for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Pengcheng He, Weizhu Chen, XiaoDong Liu","submitted_at":"2019-01-31T18:07:25Z","abstract_excerpt":"In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11504","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":""},"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":"2026-05-17T23:44:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JeD+Yz+y582QGb6aGUWpC+uIuQ2kVs6JAU/cKA2OsYKSYH8jTPDUuArDMOcRNtzlXWS9HgF1XtzTAjbQVR3JAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T11:18:18.975646Z"},"content_sha256":"19e77c2e9149484da0d07221d222387208c0b422dc9ae000ba185a0d5dd67ec9","schema_version":"1.0","event_id":"sha256:19e77c2e9149484da0d07221d222387208c0b422dc9ae000ba185a0d5dd67ec9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/bundle.json","state_url":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMXFZHIIW6YN75WYFJSECE3JO4/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":"2026-07-11T11:18:18Z","links":{"resolver":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4","bundle":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/bundle.json","state":"https://pith.science/pith/HMXFZHIIW6YN75WYFJSECE3JO4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMXFZHIIW6YN75WYFJSECE3JO4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HMXFZHIIW6YN75WYFJSECE3JO4","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":"63025ca624c5ac5bc37ea5414af23b3e3d29b90654e850eace380e97076d0d3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-31T18:07:25Z","title_canon_sha256":"f7f03101d77075e3c232a14f053d0ff50872cf58ce2fac6c76dce64f9848e512"},"schema_version":"1.0","source":{"id":"1901.11504","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11504","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11504v2","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11504","created_at":"2026-05-17T23:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"HMXFZHIIW6YN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HMXFZHIIW6YN75WY","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HMXFZHII","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:19e77c2e9149484da0d07221d222387208c0b422dc9ae000ba185a0d5dd67ec9","target":"graph","created_at":"2026-05-17T23:44:42Z","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"},"paper":{"abstract_excerpt":"In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTai","authors_text":"Jianfeng Gao, Pengcheng He, Weizhu Chen, XiaoDong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-31T18:07:25Z","title":"Multi-Task Deep Neural Networks for Natural Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11504","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":"sha256:8488270675ef49ce20ff3f65c66bb22ff4cd3cdfa0072b6bcd8f7e48bdb2efd5","target":"record","created_at":"2026-05-17T23:44:42Z","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":"63025ca624c5ac5bc37ea5414af23b3e3d29b90654e850eace380e97076d0d3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-31T18:07:25Z","title_canon_sha256":"f7f03101d77075e3c232a14f053d0ff50872cf58ce2fac6c76dce64f9848e512"},"schema_version":"1.0","source":{"id":"1901.11504","kind":"arxiv","version":2}},"canonical_sha256":"3b2e5c9d08b7b0dff6d82a64411369771f5a6c19f5fc40bfe5604547ddb9d28d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b2e5c9d08b7b0dff6d82a64411369771f5a6c19f5fc40bfe5604547ddb9d28d","first_computed_at":"2026-05-17T23:44:42.531685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:42.531685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"93LsFEpgkxxodJay15axX9DkJ80qV5V2Ue5RCHscgWyWGPpk4m8pU7SisbN6nIE/lJq2dAQ5BL6fVaHs5t98Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:42.532202Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.11504","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8488270675ef49ce20ff3f65c66bb22ff4cd3cdfa0072b6bcd8f7e48bdb2efd5","sha256:19e77c2e9149484da0d07221d222387208c0b422dc9ae000ba185a0d5dd67ec9"],"state_sha256":"013ff830b1f3b01b284397e12a369bef28446dbb9d8e65392e73e6fd2ba90db5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+8fUKaogdnApt7zfM041wJXOJI9VNZhn8RSfRmDG3MZFgRwmLMydNeA4UxRVrvi5Ch2ubSKcyMKH4iiJb2kDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T11:18:18.977732Z","bundle_sha256":"8686fae17c7ebc6c2dd30955c8ffe024e73423bc64b155889fed22180ccbf49f"}}