{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZYG6Y7YYM7QJEAR6QZMV7SCGRJ","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":"c602efd4f09fea42790229cad8c43d4f49c0be8962bcfccc8dc2ab371a239966","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T02:18:29Z","title_canon_sha256":"c87b153627d40e089905100a50a66037a695ea59feaf779c90fad4bafe5661b0"},"schema_version":"1.0","source":{"id":"2310.13022","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13022","created_at":"2026-07-05T07:02:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13022v1","created_at":"2026-07-05T07:02:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13022","created_at":"2026-07-05T07:02:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZYG6Y7YYM7QJ","created_at":"2026-07-05T07:02:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZYG6Y7YYM7QJEAR6","created_at":"2026-07-05T07:02:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZYG6Y7YY","created_at":"2026-07-05T07:02:55Z"}],"graph_snapshots":[{"event_id":"sha256:a278028ef8bb1533b4e6dd4b4076373b175738473a0cb599c3471e5da68a5f28","target":"graph","created_at":"2026-07-05T07:02:55Z","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/2310.13022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the predominant semi-supervised learning (SSL) approaches, which utilizes large-scale unlabeled data to generate synthetic examples. However, too many noisy labels will hurt the model performance, and the self-training procedure requires multiple training iterations making it more expensive if all the model parameters of the PLM are updated. This paper presents UPE","authors_text":"Chengyu Wang, Jianing Wang, Jun Huang, Ming Gao, Nuo Chen, Qiushi Sun, Xiang Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T02:18:29Z","title":"Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13022","kind":"arxiv","version":1},"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":"sha256:2a460f67e6e5af2c8b9bbbfd668844465254569e5d956d740e1575458b28825c","target":"record","created_at":"2026-07-05T07:02:55Z","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":"c602efd4f09fea42790229cad8c43d4f49c0be8962bcfccc8dc2ab371a239966","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T02:18:29Z","title_canon_sha256":"c87b153627d40e089905100a50a66037a695ea59feaf779c90fad4bafe5661b0"},"schema_version":"1.0","source":{"id":"2310.13022","kind":"arxiv","version":1}},"canonical_sha256":"ce0dec7f1867e092023e86595fc8468a4a868c82ca61107b321b5539f41e3e72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce0dec7f1867e092023e86595fc8468a4a868c82ca61107b321b5539f41e3e72","first_computed_at":"2026-07-05T07:02:55.924386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:02:55.924386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eq0X0UQrQnbwU8AUR9M0re9c8ut5w/kOzK0SVfGnBnZevTn4C+AoyH28CZ3anie9wmDSaceuCZCRg64zgE+nBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:02:55.924906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13022","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a460f67e6e5af2c8b9bbbfd668844465254569e5d956d740e1575458b28825c","sha256:a278028ef8bb1533b4e6dd4b4076373b175738473a0cb599c3471e5da68a5f28"],"state_sha256":"3755c890e825d43afa8f9db931843fe555feff44a5986e184343375298a9a7b0"}