{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CMJVYCAGWOGPD4ZD5PGE7E46G3","short_pith_number":"pith:CMJVYCAG","schema_version":"1.0","canonical_sha256":"13135c0806b38cf1f323ebcc4f939e36c05bdc3bc7c09a166dd8f8872dc2c28e","source":{"kind":"arxiv","id":"2210.12653","version":1},"attestation_state":"computed","paper":{"title":"SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Chen, Soujanya Poria, Wei Han","submitted_at":"2022-10-23T08:19:58Z","abstract_excerpt":"Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a Simple instance-Adaptive self-Training method (SAT) for semi-supervised text classification. SAT first generates two augmented views for each unlabeled data and then trains a meta-learner to automatically identify the relative strength of augmentations based on the similarity between the original view and the augmented views. The weakly-augmented view is fed to the model to produce a pseudo-label and the strongly-augmented view is used to tra"},"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":"2210.12653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-23T08:19:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"777b9570bd6a57b8a6d56799f8910b82929b30f27e29113a4887e9af9ab06189","abstract_canon_sha256":"b1a676ade5735dffd6de921c8004526625004834ff03311af2b98c01f0e1a856"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:31.132866Z","signature_b64":"j9Fj0U4HhkTN4u2pMnPg5wPN7UAAZdAhj4lBq+UJ6wA/NW8phZ0nfPgvE+/2G07tqvrLoPNoGMRqspkL8PawAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13135c0806b38cf1f323ebcc4f939e36c05bdc3bc7c09a166dd8f8872dc2c28e","last_reissued_at":"2026-07-05T05:09:31.132443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:31.132443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Chen, Soujanya Poria, Wei Han","submitted_at":"2022-10-23T08:19:58Z","abstract_excerpt":"Self-training methods have been explored in recent years and have exhibited great performance in improving semi-supervised learning. This work presents a Simple instance-Adaptive self-Training method (SAT) for semi-supervised text classification. SAT first generates two augmented views for each unlabeled data and then trains a meta-learner to automatically identify the relative strength of augmentations based on the similarity between the original view and the augmented views. The weakly-augmented view is fed to the model to produce a pseudo-label and the strongly-augmented view is used to tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12653","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/2210.12653/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":"2210.12653","created_at":"2026-07-05T05:09:31.132504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12653v1","created_at":"2026-07-05T05:09:31.132504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12653","created_at":"2026-07-05T05:09:31.132504+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMJVYCAGWOGP","created_at":"2026-07-05T05:09:31.132504+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMJVYCAGWOGPD4ZD","created_at":"2026-07-05T05:09:31.132504+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMJVYCAG","created_at":"2026-07-05T05:09:31.132504+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/CMJVYCAGWOGPD4ZD5PGE7E46G3","json":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3.json","graph_json":"https://pith.science/api/pith-number/CMJVYCAGWOGPD4ZD5PGE7E46G3/graph.json","events_json":"https://pith.science/api/pith-number/CMJVYCAGWOGPD4ZD5PGE7E46G3/events.json","paper":"https://pith.science/paper/CMJVYCAG"},"agent_actions":{"view_html":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3","download_json":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3.json","view_paper":"https://pith.science/paper/CMJVYCAG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12653&json=true","fetch_graph":"https://pith.science/api/pith-number/CMJVYCAGWOGPD4ZD5PGE7E46G3/graph.json","fetch_events":"https://pith.science/api/pith-number/CMJVYCAGWOGPD4ZD5PGE7E46G3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3/action/storage_attestation","attest_author":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3/action/author_attestation","sign_citation":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3/action/citation_signature","submit_replication":"https://pith.science/pith/CMJVYCAGWOGPD4ZD5PGE7E46G3/action/replication_record"}},"created_at":"2026-07-05T05:09:31.132504+00:00","updated_at":"2026-07-05T05:09:31.132504+00:00"}