{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PLOB6HOKO4D56Z3OWHOMC2HJ4T","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":"83c6d87e5cc5243fdeabd70e0439beca78dc92c27de777a834f64a16afc64def","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T17:52:25Z","title_canon_sha256":"6f1d992b577dd360aab67d9920075026b94ec66ea84a3614f27451cf9f8e7ed6"},"schema_version":"1.0","source":{"id":"2010.02194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02194","created_at":"2026-07-05T01:40:18Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02194v1","created_at":"2026-07-05T01:40:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02194","created_at":"2026-07-05T01:40:18Z"},{"alias_kind":"pith_short_12","alias_value":"PLOB6HOKO4D5","created_at":"2026-07-05T01:40:18Z"},{"alias_kind":"pith_short_16","alias_value":"PLOB6HOKO4D56Z3O","created_at":"2026-07-05T01:40:18Z"},{"alias_kind":"pith_short_8","alias_value":"PLOB6HOK","created_at":"2026-07-05T01:40:18Z"}],"graph_snapshots":[{"event_id":"sha256:cc99e24bbcee78b30768e39658c18559621d5c7a1aef41137b2c6ee38f368560","target":"graph","created_at":"2026-07-05T01:40:18Z","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/2010.02194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a specific task, we introduce SentAugment, a data augmentation method which computes task-specific query embeddings from labeled data to retrieve sentences from a bank of billions of unlabeled sentences crawled from the web. Unlike previous semi-supervised methods, our approach does not require in-domain unlabeled data and is therefore more generally applicable","authors_text":"Alexis Conneau, Beliz Gunel, Edouard Grave, Jingfei Du, Michael Auli, Onur Celebi, Ves Stoyanov, Vishrav Chaudhary","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T17:52:25Z","title":"Self-training Improves Pre-training for Natural Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02194","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:b3d45807a10276cc54de4c180cce7dec2f4bd556b415f0adc8c6bc98b8076a97","target":"record","created_at":"2026-07-05T01:40:18Z","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":"83c6d87e5cc5243fdeabd70e0439beca78dc92c27de777a834f64a16afc64def","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T17:52:25Z","title_canon_sha256":"6f1d992b577dd360aab67d9920075026b94ec66ea84a3614f27451cf9f8e7ed6"},"schema_version":"1.0","source":{"id":"2010.02194","kind":"arxiv","version":1}},"canonical_sha256":"7adc1f1dca7707df676eb1dcc168e9e4f7b14a0913d59666b99a719587dc3f48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7adc1f1dca7707df676eb1dcc168e9e4f7b14a0913d59666b99a719587dc3f48","first_computed_at":"2026-07-05T01:40:18.371795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:40:18.371795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3cO1RXd6gZUjTRF8AgJbHsJBFM1DWlqfr+heggiaH/7mGkvoVN6ovqqwpVLg4xeu2YIq86dipMml5PfRgLACBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:40:18.372233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3d45807a10276cc54de4c180cce7dec2f4bd556b415f0adc8c6bc98b8076a97","sha256:cc99e24bbcee78b30768e39658c18559621d5c7a1aef41137b2c6ee38f368560"],"state_sha256":"9727a5eb0a79b258e44d80b4dd0fa934d39e1a3dfde2505614fcd6d394143a02"}