{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GIH5FWROI4PFMBP4EWNKUNUFAT","short_pith_number":"pith:GIH5FWRO","schema_version":"1.0","canonical_sha256":"320fd2da2e471e5605fc259aaa368504c604fd7fb238633713e57295e6aaf203","source":{"kind":"arxiv","id":"1908.10423","version":1},"attestation_state":"computed","paper":{"title":"Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Keyi Yu, Zi-Yi Dou","submitted_at":"2019-08-27T19:26:31Z","abstract_excerpt":"Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust representations. However, these methods can achieve sub-optimal performance in low-resource scenarios. Inspired by the recent success of optimization-based meta-learning algorithms, in this paper, we explore the model-agnostic meta-learning algorithm (MAML) and its variants for low-resource NLU tasks. We validate our methods on the GLUE benchmark and show that our p"},"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":"1908.10423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T19:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"4301e1a32efd5c1c611b62176f9c2c200cd0097053e2abd852e401c6fc98338a","abstract_canon_sha256":"0606e1168f898845ec076cff7c935602fd3e0d39a36a40d0456675841f9cf9b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:17.144356Z","signature_b64":"t6m2Hxub4NO8hwCfqUmZhmMFS6cz/g+PvrdFuo92h1Wg4J1M+fA/ncRoqWSGF5bi//jqUXBYES/ZF3q1tKHBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"320fd2da2e471e5605fc259aaa368504c604fd7fb238633713e57295e6aaf203","last_reissued_at":"2026-07-05T00:00:17.143932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:17.143932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Keyi Yu, Zi-Yi Dou","submitted_at":"2019-08-27T19:26:31Z","abstract_excerpt":"Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust representations. However, these methods can achieve sub-optimal performance in low-resource scenarios. Inspired by the recent success of optimization-based meta-learning algorithms, in this paper, we explore the model-agnostic meta-learning algorithm (MAML) and its variants for low-resource NLU tasks. We validate our methods on the GLUE benchmark and show that our p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10423","kind":"arxiv","version":1},"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/1908.10423/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":"1908.10423","created_at":"2026-07-05T00:00:17.143990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10423v1","created_at":"2026-07-05T00:00:17.143990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10423","created_at":"2026-07-05T00:00:17.143990+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIH5FWROI4PF","created_at":"2026-07-05T00:00:17.143990+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIH5FWROI4PFMBP4","created_at":"2026-07-05T00:00:17.143990+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIH5FWRO","created_at":"2026-07-05T00:00:17.143990+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/GIH5FWROI4PFMBP4EWNKUNUFAT","json":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT.json","graph_json":"https://pith.science/api/pith-number/GIH5FWROI4PFMBP4EWNKUNUFAT/graph.json","events_json":"https://pith.science/api/pith-number/GIH5FWROI4PFMBP4EWNKUNUFAT/events.json","paper":"https://pith.science/paper/GIH5FWRO"},"agent_actions":{"view_html":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT","download_json":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT.json","view_paper":"https://pith.science/paper/GIH5FWRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10423&json=true","fetch_graph":"https://pith.science/api/pith-number/GIH5FWROI4PFMBP4EWNKUNUFAT/graph.json","fetch_events":"https://pith.science/api/pith-number/GIH5FWROI4PFMBP4EWNKUNUFAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT/action/storage_attestation","attest_author":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT/action/author_attestation","sign_citation":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT/action/citation_signature","submit_replication":"https://pith.science/pith/GIH5FWROI4PFMBP4EWNKUNUFAT/action/replication_record"}},"created_at":"2026-07-05T00:00:17.143990+00:00","updated_at":"2026-07-05T00:00:17.143990+00:00"}