{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UCGEUNUSTV3KZ5MKB2WO27JOQS","short_pith_number":"pith:UCGEUNUS","schema_version":"1.0","canonical_sha256":"a08c4a36929d76acf58a0eaced7d2e848d5225e99695e230b6678f048eed59c7","source":{"kind":"arxiv","id":"2202.04538","version":2},"attestation_state":"computed","paper":{"title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Jiaxin Huang, Yu Meng, Yu Zhang","submitted_at":"2022-02-09T16:02:18Z","abstract_excerpt":"Pretrained language models (PLMs) have demonstrated remarkable performance in various natural language processing tasks: Unidirectional PLMs (e.g., GPT) are well known for their superior text generation capabilities; bidirectional PLMs (e.g., BERT) have been the prominent choice for natural language understanding (NLU) tasks. While both types of models have achieved promising few-shot learning performance, their potential for zero-shot learning has been underexplored. In this paper, we present a simple approach that uses both types of PLMs for fully zero-shot learning of NLU tasks without requ"},"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":"2202.04538","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-02-09T16:02:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df458f41de2d17572edcdca61e4c40f8b86fd75f81a41267ce53b8c45d6571db","abstract_canon_sha256":"a2448f18dfe38b9b8709b72269248c95afe08ddf3bbafac67a49d1a19e42f0c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:45.443794Z","signature_b64":"ClHlm5x6AJHTpLrxwewS1jUvxUWIA71294eGrc6CzypwPpGsi+sDXfHexVR5OI2aMf/jitgH+IPJOYiCVOVaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a08c4a36929d76acf58a0eaced7d2e848d5225e99695e230b6678f048eed59c7","last_reissued_at":"2026-07-05T05:05:45.443260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:45.443260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Jiaxin Huang, Yu Meng, Yu Zhang","submitted_at":"2022-02-09T16:02:18Z","abstract_excerpt":"Pretrained language models (PLMs) have demonstrated remarkable performance in various natural language processing tasks: Unidirectional PLMs (e.g., GPT) are well known for their superior text generation capabilities; bidirectional PLMs (e.g., BERT) have been the prominent choice for natural language understanding (NLU) tasks. While both types of models have achieved promising few-shot learning performance, their potential for zero-shot learning has been underexplored. In this paper, we present a simple approach that uses both types of PLMs for fully zero-shot learning of NLU tasks without requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04538","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/2202.04538/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":"2202.04538","created_at":"2026-07-05T05:05:45.443325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.04538v2","created_at":"2026-07-05T05:05:45.443325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04538","created_at":"2026-07-05T05:05:45.443325+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCGEUNUSTV3K","created_at":"2026-07-05T05:05:45.443325+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCGEUNUSTV3KZ5MK","created_at":"2026-07-05T05:05:45.443325+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCGEUNUS","created_at":"2026-07-05T05:05:45.443325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30775","citing_title":"A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization","ref_index":78,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS","json":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS.json","graph_json":"https://pith.science/api/pith-number/UCGEUNUSTV3KZ5MKB2WO27JOQS/graph.json","events_json":"https://pith.science/api/pith-number/UCGEUNUSTV3KZ5MKB2WO27JOQS/events.json","paper":"https://pith.science/paper/UCGEUNUS"},"agent_actions":{"view_html":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS","download_json":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS.json","view_paper":"https://pith.science/paper/UCGEUNUS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.04538&json=true","fetch_graph":"https://pith.science/api/pith-number/UCGEUNUSTV3KZ5MKB2WO27JOQS/graph.json","fetch_events":"https://pith.science/api/pith-number/UCGEUNUSTV3KZ5MKB2WO27JOQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS/action/storage_attestation","attest_author":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS/action/author_attestation","sign_citation":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS/action/citation_signature","submit_replication":"https://pith.science/pith/UCGEUNUSTV3KZ5MKB2WO27JOQS/action/replication_record"}},"created_at":"2026-07-05T05:05:45.443325+00:00","updated_at":"2026-07-05T05:05:45.443325+00:00"}