{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z4AI7BPFUHCU4OCOJQX3YHDIKO","short_pith_number":"pith:Z4AI7BPF","schema_version":"1.0","canonical_sha256":"cf008f85e5a1c54e384e4c2fbc1c6853a74f3c69fdbec4037e98a58a1a27fdd1","source":{"kind":"arxiv","id":"2109.07589","version":2},"attestation_state":"computed","paper":{"title":"CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arzoo Katiyar, Rebecca J. Passonneau, Rui Zhang, Sarkar Snigdha Sarathi Das","submitted_at":"2021-09-15T21:41:16Z","abstract_excerpt":"Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This affects generalizability to unseen target domains, resulting in suboptimal performances. To this end, we present CONTaiNER, a novel contrastive learning technique that optimizes the inter-token distribution distance for Few-Shot NER. Instead of optimizing class-specific attributes, CONTaiNER optimizes a generalized objective of differentiating between token categori"},"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":"2109.07589","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-15T21:41:16Z","cross_cats_sorted":[],"title_canon_sha256":"a4cc083fbd6bfc427da5971b3c47a276c7ba9e36f2e66af08e67a7160ba66dae","abstract_canon_sha256":"06d6f0239de219f94dd496b57a59b195e143f179692fd7cf5a37c2b5f4d82f3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:58.672249Z","signature_b64":"kD7j6Oa8OYCkCN4eKVGovddyZTvL9lVQ1GvcacsDLOQ6QpzM+S+c09V15aEM4vrajzw0w8BSPF0q0HP28jC4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf008f85e5a1c54e384e4c2fbc1c6853a74f3c69fdbec4037e98a58a1a27fdd1","last_reissued_at":"2026-07-05T04:08:58.671799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:58.671799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arzoo Katiyar, Rebecca J. Passonneau, Rui Zhang, Sarkar Snigdha Sarathi Das","submitted_at":"2021-09-15T21:41:16Z","abstract_excerpt":"Named Entity Recognition (NER) in Few-Shot setting is imperative for entity tagging in low resource domains. Existing approaches only learn class-specific semantic features and intermediate representations from source domains. This affects generalizability to unseen target domains, resulting in suboptimal performances. To this end, we present CONTaiNER, a novel contrastive learning technique that optimizes the inter-token distribution distance for Few-Shot NER. Instead of optimizing class-specific attributes, CONTaiNER optimizes a generalized objective of differentiating between token categori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07589","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/2109.07589/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":"2109.07589","created_at":"2026-07-05T04:08:58.671857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.07589v2","created_at":"2026-07-05T04:08:58.671857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07589","created_at":"2026-07-05T04:08:58.671857+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4AI7BPFUHCU","created_at":"2026-07-05T04:08:58.671857+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4AI7BPFUHCU4OCO","created_at":"2026-07-05T04:08:58.671857+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4AI7BPF","created_at":"2026-07-05T04:08:58.671857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02391","citing_title":"FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO","json":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO.json","graph_json":"https://pith.science/api/pith-number/Z4AI7BPFUHCU4OCOJQX3YHDIKO/graph.json","events_json":"https://pith.science/api/pith-number/Z4AI7BPFUHCU4OCOJQX3YHDIKO/events.json","paper":"https://pith.science/paper/Z4AI7BPF"},"agent_actions":{"view_html":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO","download_json":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO.json","view_paper":"https://pith.science/paper/Z4AI7BPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.07589&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4AI7BPFUHCU4OCOJQX3YHDIKO/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4AI7BPFUHCU4OCOJQX3YHDIKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO/action/storage_attestation","attest_author":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO/action/author_attestation","sign_citation":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO/action/citation_signature","submit_replication":"https://pith.science/pith/Z4AI7BPFUHCU4OCOJQX3YHDIKO/action/replication_record"}},"created_at":"2026-07-05T04:08:58.671857+00:00","updated_at":"2026-07-05T04:08:58.671857+00:00"}