{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KTXSZIWRFJMVEQ735L4QJUJG6L","short_pith_number":"pith:KTXSZIWR","schema_version":"1.0","canonical_sha256":"54ef2ca2d12a595243fbeaf904d126f2d6706f113b2bd47563934d56b785b83e","source":{"kind":"arxiv","id":"2109.13532","version":3},"attestation_state":"computed","paper":{"title":"Template-free Prompt Tuning for Few-shot NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Linyang Li, Qi Zhang, Ruotian Ma, Tao Gui, Xin Zhou, Xuanjing Huang, Yiding Tan","submitted_at":"2021-09-28T07:19:24Z","abstract_excerpt":"Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would be time-consuming to enumerate the template queries over all potential entity spans. In this work, we propose a more elegant method to reformulate NER tasks as LM problems without any templates. Specifically, we discard the template construction process while maintaining the word prediction paradigm of pre-training models to predict a class-related pivot wor"},"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":"2109.13532","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-28T07:19:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"62204100b26b2ad653865aed0b455fba3737db7aaed5d62172eacc4944f7e097","abstract_canon_sha256":"aa0bdccc9101a9425194fdd96a5baba4ba161d2a2f4e04e8572af6cb2818555b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:43.923965Z","signature_b64":"beaWZ3dB4OXhCgVO7KzDMSdMrXs/aSU0Q8LLIWio5d6ti1RIG/By3L9YyqYbQUNer/29mR+deWvSgFQ+yNsJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54ef2ca2d12a595243fbeaf904d126f2d6706f113b2bd47563934d56b785b83e","last_reissued_at":"2026-07-05T05:18:43.923556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:43.923556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Template-free Prompt Tuning for Few-shot NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Linyang Li, Qi Zhang, Ruotian Ma, Tao Gui, Xin Zhou, Xuanjing Huang, Yiding Tan","submitted_at":"2021-09-28T07:19:24Z","abstract_excerpt":"Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would be time-consuming to enumerate the template queries over all potential entity spans. In this work, we propose a more elegant method to reformulate NER tasks as LM problems without any templates. Specifically, we discard the template construction process while maintaining the word prediction paradigm of pre-training models to predict a class-related pivot wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13532","kind":"arxiv","version":3},"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/2109.13532/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":"2109.13532","created_at":"2026-07-05T05:18:43.923614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.13532v3","created_at":"2026-07-05T05:18:43.923614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13532","created_at":"2026-07-05T05:18:43.923614+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTXSZIWRFJMV","created_at":"2026-07-05T05:18:43.923614+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTXSZIWRFJMVEQ73","created_at":"2026-07-05T05:18:43.923614+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTXSZIWR","created_at":"2026-07-05T05:18:43.923614+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/KTXSZIWRFJMVEQ735L4QJUJG6L","json":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L.json","graph_json":"https://pith.science/api/pith-number/KTXSZIWRFJMVEQ735L4QJUJG6L/graph.json","events_json":"https://pith.science/api/pith-number/KTXSZIWRFJMVEQ735L4QJUJG6L/events.json","paper":"https://pith.science/paper/KTXSZIWR"},"agent_actions":{"view_html":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L","download_json":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L.json","view_paper":"https://pith.science/paper/KTXSZIWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.13532&json=true","fetch_graph":"https://pith.science/api/pith-number/KTXSZIWRFJMVEQ735L4QJUJG6L/graph.json","fetch_events":"https://pith.science/api/pith-number/KTXSZIWRFJMVEQ735L4QJUJG6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L/action/storage_attestation","attest_author":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L/action/author_attestation","sign_citation":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L/action/citation_signature","submit_replication":"https://pith.science/pith/KTXSZIWRFJMVEQ735L4QJUJG6L/action/replication_record"}},"created_at":"2026-07-05T05:18:43.923614+00:00","updated_at":"2026-07-05T05:18:43.923614+00:00"}