{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YDXBVYRPUXHD34GL7OPA46MEYW","short_pith_number":"pith:YDXBVYRP","schema_version":"1.0","canonical_sha256":"c0ee1ae22fa5ce3df0cbfb9e0e7984c58063cf64b24281ae1d1752af3f316d3a","source":{"kind":"arxiv","id":"2012.11926","version":2},"attestation_state":"computed","paper":{"title":"Few-Shot Text Generation with Pattern-Exploiting Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Timo Schick","submitted_at":"2020-12-22T10:53:07Z","abstract_excerpt":"Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields impressive few-shot results for a wide range of text classification tasks. It is also a promising direction to improve data efficiency in generative settings, but there are several challenges to using a combination of task descriptions and example-based learning for text generation. In particular, it is crucial to find task descriptions that are easy to understand fo"},"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":"2012.11926","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-22T10:53:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"055d4be35df3cdafdce180c3c4ecaaa47c75e7973dd1f9e0244ac4c26b2be608","abstract_canon_sha256":"039b734c7fce31e5f4b47afb74da3a21c30b32afc57c6a5d6e5a9f5dd255a994"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:41.394266Z","signature_b64":"FIxkQKnm4EoGoqWQgszLXuTxeQtfQkJKj2JXrwPegRlXOsKoaIV4De/9MpMdQNkOx5VetHo3Q/8LmjBOyoB7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0ee1ae22fa5ce3df0cbfb9e0e7984c58063cf64b24281ae1d1752af3f316d3a","last_reissued_at":"2026-07-05T03:19:41.393769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:41.393769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Text Generation with Pattern-Exploiting Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Timo Schick","submitted_at":"2020-12-22T10:53:07Z","abstract_excerpt":"Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields impressive few-shot results for a wide range of text classification tasks. It is also a promising direction to improve data efficiency in generative settings, but there are several challenges to using a combination of task descriptions and example-based learning for text generation. In particular, it is crucial to find task descriptions that are easy to understand fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11926","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/2012.11926/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":"2012.11926","created_at":"2026-07-05T03:19:41.393831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11926v2","created_at":"2026-07-05T03:19:41.393831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11926","created_at":"2026-07-05T03:19:41.393831+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDXBVYRPUXHD","created_at":"2026-07-05T03:19:41.393831+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDXBVYRPUXHD34GL","created_at":"2026-07-05T03:19:41.393831+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDXBVYRP","created_at":"2026-07-05T03:19:41.393831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16196","citing_title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW","json":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW.json","graph_json":"https://pith.science/api/pith-number/YDXBVYRPUXHD34GL7OPA46MEYW/graph.json","events_json":"https://pith.science/api/pith-number/YDXBVYRPUXHD34GL7OPA46MEYW/events.json","paper":"https://pith.science/paper/YDXBVYRP"},"agent_actions":{"view_html":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW","download_json":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW.json","view_paper":"https://pith.science/paper/YDXBVYRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11926&json=true","fetch_graph":"https://pith.science/api/pith-number/YDXBVYRPUXHD34GL7OPA46MEYW/graph.json","fetch_events":"https://pith.science/api/pith-number/YDXBVYRPUXHD34GL7OPA46MEYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW/action/storage_attestation","attest_author":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW/action/author_attestation","sign_citation":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW/action/citation_signature","submit_replication":"https://pith.science/pith/YDXBVYRPUXHD34GL7OPA46MEYW/action/replication_record"}},"created_at":"2026-07-05T03:19:41.393831+00:00","updated_at":"2026-07-05T03:19:41.393831+00:00"}