{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BC4TNUWI4WTSDNF5CQBFIG2P54","short_pith_number":"pith:BC4TNUWI","schema_version":"1.0","canonical_sha256":"08b936d2c8e5a721b4bd1402541b4fef1187617853b9302cdc0bc1100aacfaf2","source":{"kind":"arxiv","id":"2107.03176","version":1},"attestation_state":"computed","paper":{"title":"On Training Instance Selection for Few-Shot Neural Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Hui-Syuan Yeh, Vera Demberg, Xiaoyu Shen","submitted_at":"2021-07-07T12:16:16Z","abstract_excerpt":"Large-scale pretrained language models have led to dramatic improvements in text generation. Impressive performance can be achieved by finetuning only on a small number of instances (few-shot setting). Nonetheless, almost all previous work simply applies random sampling to select the few-shot training instances. Little to no attention has been paid to the selection strategies and how they would affect model performance. In this work, we present a study on training instance selection in few-shot neural text generation. The selection decision is made based only on the unlabeled data so as to ide"},"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":"2107.03176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-07T12:16:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bab3068b4f788dc3731b0ffe4f22aaaeafe4501c7ea946d8d8677a45d71d912c","abstract_canon_sha256":"23267c52bbf9d6a90f50af222559a1409c0d13ae4ea5de4bf4b2e9a80c2a5bb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:01.208593Z","signature_b64":"Aq82WUwL2j9ro7EplxKcrwjG7oD5sV7lTD8AcnSoZpktkb6H3izAKINrXNeugUQb1pVtbXsMZe7l45TLLTLECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b936d2c8e5a721b4bd1402541b4fef1187617853b9302cdc0bc1100aacfaf2","last_reissued_at":"2026-07-05T02:56:01.208221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:01.208221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Training Instance Selection for Few-Shot Neural Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ernie Chang, Hui-Syuan Yeh, Vera Demberg, Xiaoyu Shen","submitted_at":"2021-07-07T12:16:16Z","abstract_excerpt":"Large-scale pretrained language models have led to dramatic improvements in text generation. Impressive performance can be achieved by finetuning only on a small number of instances (few-shot setting). Nonetheless, almost all previous work simply applies random sampling to select the few-shot training instances. Little to no attention has been paid to the selection strategies and how they would affect model performance. In this work, we present a study on training instance selection in few-shot neural text generation. The selection decision is made based only on the unlabeled data so as to ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03176","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/2107.03176/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":"2107.03176","created_at":"2026-07-05T02:56:01.208270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03176v1","created_at":"2026-07-05T02:56:01.208270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03176","created_at":"2026-07-05T02:56:01.208270+00:00"},{"alias_kind":"pith_short_12","alias_value":"BC4TNUWI4WTS","created_at":"2026-07-05T02:56:01.208270+00:00"},{"alias_kind":"pith_short_16","alias_value":"BC4TNUWI4WTSDNF5","created_at":"2026-07-05T02:56:01.208270+00:00"},{"alias_kind":"pith_short_8","alias_value":"BC4TNUWI","created_at":"2026-07-05T02:56:01.208270+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/BC4TNUWI4WTSDNF5CQBFIG2P54","json":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54.json","graph_json":"https://pith.science/api/pith-number/BC4TNUWI4WTSDNF5CQBFIG2P54/graph.json","events_json":"https://pith.science/api/pith-number/BC4TNUWI4WTSDNF5CQBFIG2P54/events.json","paper":"https://pith.science/paper/BC4TNUWI"},"agent_actions":{"view_html":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54","download_json":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54.json","view_paper":"https://pith.science/paper/BC4TNUWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03176&json=true","fetch_graph":"https://pith.science/api/pith-number/BC4TNUWI4WTSDNF5CQBFIG2P54/graph.json","fetch_events":"https://pith.science/api/pith-number/BC4TNUWI4WTSDNF5CQBFIG2P54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54/action/storage_attestation","attest_author":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54/action/author_attestation","sign_citation":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54/action/citation_signature","submit_replication":"https://pith.science/pith/BC4TNUWI4WTSDNF5CQBFIG2P54/action/replication_record"}},"created_at":"2026-07-05T02:56:01.208270+00:00","updated_at":"2026-07-05T02:56:01.208270+00:00"}