{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GSLQ5M67GJFIL3DMIWA7UKXD7H","short_pith_number":"pith:GSLQ5M67","canonical_record":{"source":{"id":"2109.09138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-19T14:51:51Z","cross_cats_sorted":[],"title_canon_sha256":"ced16af797672de95f39ac068e314779af34294585b625151914fd403173c5fd","abstract_canon_sha256":"681f8a1fc1e7832a3fb4c6ad6a126f3964ba2b10c18a82b1b1e31799ffe214c7"},"schema_version":"1.0"},"canonical_sha256":"34970eb3df324a85ec6c4581fa2ae3f9f0a5261412e8c6e1451070861965fbc8","source":{"kind":"arxiv","id":"2109.09138","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09138","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09138v2","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09138","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"GSLQ5M67GJFI","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"GSLQ5M67GJFIL3DM","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"GSLQ5M67","created_at":"2026-07-05T08:12:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GSLQ5M67GJFIL3DMIWA7UKXD7H","target":"record","payload":{"canonical_record":{"source":{"id":"2109.09138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-19T14:51:51Z","cross_cats_sorted":[],"title_canon_sha256":"ced16af797672de95f39ac068e314779af34294585b625151914fd403173c5fd","abstract_canon_sha256":"681f8a1fc1e7832a3fb4c6ad6a126f3964ba2b10c18a82b1b1e31799ffe214c7"},"schema_version":"1.0"},"canonical_sha256":"34970eb3df324a85ec6c4581fa2ae3f9f0a5261412e8c6e1451070861965fbc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:41.083876Z","signature_b64":"lo0LeSnSir3wifkMgJRbEbuTVIEffL7YycWMqJ76kbynbzK6v9IPCbhuJQeM8emUBqrkdx/urKG38XmzpdEqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34970eb3df324a85ec6c4581fa2ae3f9f0a5261412e8c6e1451070861965fbc8","last_reissued_at":"2026-07-05T08:12:41.083511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:41.083511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.09138","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":"2026-07-05T08:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J7O7ep8mju1VBpnpYtHdWUsCiAh9d/jpG9BFXdSaykKxSIF0v0TSLqCFAHINlf3qGKOuXl/ADL9627VG60ijCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:32:28.040076Z"},"content_sha256":"263de05352f3acf201e9c1e12d87e4ff95c9e0d9d7c1ba83379f0ee50747b119","schema_version":"1.0","event_id":"sha256:263de05352f3acf201e9c1e12d87e4ff95c9e0d9d7c1ba83379f0ee50747b119"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GSLQ5M67GJFIL3DMIWA7UKXD7H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Learning in Natural Language Processing: An Overview","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Qiang Yang, Shijie Chen, Yu Zhang","submitted_at":"2021-09-19T14:51:51Z","abstract_excerpt":"Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, directly training deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks. In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on these tasks, has been used to handle these problems. In this paper, we give an overview of the use of MTL in NLP tasks. We first review MTL architectures used in NLP tasks and categorize them into four classes,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09138","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/2109.09138/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":"2026-07-05T08:12:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqB2wIcZaCcs7QJeOA25Lb8xyCtXtsxcD+RWseAQFcdYZBjqE5p/7TTSI6b32pHI0+HFV9fWD5gfDpGJKXQlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:32:28.040653Z"},"content_sha256":"ec14be517660b68e54b7fc66d64f9312b86a0a412e5d8c59fac01d353e8a938f","schema_version":"1.0","event_id":"sha256:ec14be517660b68e54b7fc66d64f9312b86a0a412e5d8c59fac01d353e8a938f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSLQ5M67GJFIL3DMIWA7UKXD7H/bundle.json","state_url":"https://pith.science/pith/GSLQ5M67GJFIL3DMIWA7UKXD7H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSLQ5M67GJFIL3DMIWA7UKXD7H/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":"2026-08-09T06:32:28Z","links":{"resolver":"https://pith.science/pith/GSLQ5M67GJFIL3DMIWA7UKXD7H","bundle":"https://pith.science/pith/GSLQ5M67GJFIL3DMIWA7UKXD7H/bundle.json","state":"https://pith.science/pith/GSLQ5M67GJFIL3DMIWA7UKXD7H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSLQ5M67GJFIL3DMIWA7UKXD7H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GSLQ5M67GJFIL3DMIWA7UKXD7H","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":"681f8a1fc1e7832a3fb4c6ad6a126f3964ba2b10c18a82b1b1e31799ffe214c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-19T14:51:51Z","title_canon_sha256":"ced16af797672de95f39ac068e314779af34294585b625151914fd403173c5fd"},"schema_version":"1.0","source":{"id":"2109.09138","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09138","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09138v2","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09138","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"pith_short_12","alias_value":"GSLQ5M67GJFI","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"pith_short_16","alias_value":"GSLQ5M67GJFIL3DM","created_at":"2026-07-05T08:12:41Z"},{"alias_kind":"pith_short_8","alias_value":"GSLQ5M67","created_at":"2026-07-05T08:12:41Z"}],"graph_snapshots":[{"event_id":"sha256:ec14be517660b68e54b7fc66d64f9312b86a0a412e5d8c59fac01d353e8a938f","target":"graph","created_at":"2026-07-05T08:12:41Z","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/2109.09138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning approaches have achieved great success in the field of Natural Language Processing (NLP). However, directly training deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks. In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on these tasks, has been used to handle these problems. In this paper, we give an overview of the use of MTL in NLP tasks. We first review MTL architectures used in NLP tasks and categorize them into four classes,","authors_text":"Qiang Yang, Shijie Chen, Yu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-19T14:51:51Z","title":"Multi-Task Learning in Natural Language Processing: An Overview"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09138","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":"sha256:263de05352f3acf201e9c1e12d87e4ff95c9e0d9d7c1ba83379f0ee50747b119","target":"record","created_at":"2026-07-05T08:12:41Z","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":"681f8a1fc1e7832a3fb4c6ad6a126f3964ba2b10c18a82b1b1e31799ffe214c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-19T14:51:51Z","title_canon_sha256":"ced16af797672de95f39ac068e314779af34294585b625151914fd403173c5fd"},"schema_version":"1.0","source":{"id":"2109.09138","kind":"arxiv","version":2}},"canonical_sha256":"34970eb3df324a85ec6c4581fa2ae3f9f0a5261412e8c6e1451070861965fbc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34970eb3df324a85ec6c4581fa2ae3f9f0a5261412e8c6e1451070861965fbc8","first_computed_at":"2026-07-05T08:12:41.083511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:41.083511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lo0LeSnSir3wifkMgJRbEbuTVIEffL7YycWMqJ76kbynbzK6v9IPCbhuJQeM8emUBqrkdx/urKG38XmzpdEqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:41.083876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09138","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:263de05352f3acf201e9c1e12d87e4ff95c9e0d9d7c1ba83379f0ee50747b119","sha256:ec14be517660b68e54b7fc66d64f9312b86a0a412e5d8c59fac01d353e8a938f"],"state_sha256":"5df951baa9c788a1cb3ac932a47fc5e91f760250b0496f919b988a30e4998b60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHZ5A7jO+0e88vuwpZkNg+jHkNVmAghKqipYnVvdPyXq9iDZyqVA3UJl2NaqwkhhechDPrzdVTVAS/xvg8PBDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:32:28.045528Z","bundle_sha256":"2a6fa2555315950bb7e1ac69aa76a605ed1c569f98e7dc1462368338789ef29d"}}