{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:I2432NZGDQ64IUVEVBDEKIFJKG","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":"b69039803ced6479eab9427ad2f4d357e5c00fc4f6bf8172b84d7f7656daac9a","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T17:55:51Z","title_canon_sha256":"2a20383752954009624d58367352df331e62f890827c466bb908849651ebaede"},"schema_version":"1.0","source":{"id":"2105.11447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11447","created_at":"2026-07-05T02:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11447v1","created_at":"2026-07-05T02:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11447","created_at":"2026-07-05T02:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"I2432NZGDQ64","created_at":"2026-07-05T02:42:38Z"},{"alias_kind":"pith_short_16","alias_value":"I2432NZGDQ64IUVE","created_at":"2026-07-05T02:42:38Z"},{"alias_kind":"pith_short_8","alias_value":"I2432NZG","created_at":"2026-07-05T02:42:38Z"}],"graph_snapshots":[{"event_id":"sha256:1cb324d8830ae47e8926cffa14def174ea010a275c40ebc41181ae9a1b5d7adf","target":"graph","created_at":"2026-07-05T02:42:38Z","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/2105.11447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models (LMs) perform well on many tasks even when learning from a few examples, but prior work uses many held-out examples to tune various aspects of learning, such as hyperparameters, training objectives, and natural language templates (\"prompts\"). Here, we evaluate the few-shot ability of LMs when such held-out examples are unavailable, a setting we call true few-shot learning. We test two model selection criteria, cross-validation and minimum description length, for choosing LM prompts and hyperparameters in the true few-shot setting. On average, both marginally outperfo","authors_text":"Douwe Kiela, Ethan Perez, Kyunghyun Cho","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T17:55:51Z","title":"True Few-Shot Learning with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11447","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:ade6cfd84fdae6b93b1f582b2103c7437e281c72611253f219c65cd20a3fe854","target":"record","created_at":"2026-07-05T02:42:38Z","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":"b69039803ced6479eab9427ad2f4d357e5c00fc4f6bf8172b84d7f7656daac9a","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T17:55:51Z","title_canon_sha256":"2a20383752954009624d58367352df331e62f890827c466bb908849651ebaede"},"schema_version":"1.0","source":{"id":"2105.11447","kind":"arxiv","version":1}},"canonical_sha256":"46b9bd37261c3dc452a4a8464520a951a2c38869bc496956f3981f672e562e95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46b9bd37261c3dc452a4a8464520a951a2c38869bc496956f3981f672e562e95","first_computed_at":"2026-07-05T02:42:38.503393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:38.503393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U9VyVb3TAQULojLkwL3Ct24Z+JLnhaDlvuqJqA+gAZGuVwietR9Mp9TKUq9kx0nNW+AH0+9MsEm1PF5knQskBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:38.504064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ade6cfd84fdae6b93b1f582b2103c7437e281c72611253f219c65cd20a3fe854","sha256:1cb324d8830ae47e8926cffa14def174ea010a275c40ebc41181ae9a1b5d7adf"],"state_sha256":"c43c0df018923aa9ff24534b7f8a083e94d9dfcf7c63d14c445d5d3e84dac5dd"}