{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RO3B2FYS4NHBLQXCPP66XAEO4E","short_pith_number":"pith:RO3B2FYS","schema_version":"1.0","canonical_sha256":"8bb61d1712e34e15c2e27bfdeb808ee1010e1cfcf7d5881c6d5ab7fd0029273f","source":{"kind":"arxiv","id":"2311.00408","version":1},"attestation_state":"computed","paper":{"title":"AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Goran Glava\\v{s}, Iryna Gurevych, Kexin Wang, Raj Nath Patel, Sourav Dutta, Yongxin Huang","submitted_at":"2023-11-01T10:00:15Z","abstract_excerpt":"Recent work has found that few-shot sentence classification based on pre-trained Sentence Encoders (SEs) is efficient, robust, and effective. In this work, we investigate strategies for domain-specialization in the context of few-shot sentence classification with SEs. We first establish that unsupervised Domain-Adaptive Pre-Training (DAPT) of a base Pre-trained Language Model (PLM) (i.e., not an SE) substantially improves the accuracy of few-shot sentence classification by up to 8.4 points. However, applying DAPT on SEs, on the one hand, disrupts the effects of their (general-domain) Sentence "},"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":"2311.00408","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T10:00:15Z","cross_cats_sorted":[],"title_canon_sha256":"285a14dd364d7de743f888fd3f12bebe3a0fea8f7bc0d7edaed32fc044a0cf82","abstract_canon_sha256":"d5846e165721aea3b441606e6966136ab871117b57b31bf32b625b3fdea8afd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:57.194556Z","signature_b64":"2vRA+ipYmwpMWzXrhESBLQvOWfH0wa5Uu+IvImmP5iZU+XwkzugE68MjLgWWK+r80NaROL7J2Ws7AMYa3Vc4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bb61d1712e34e15c2e27bfdeb808ee1010e1cfcf7d5881c6d5ab7fd0029273f","last_reissued_at":"2026-07-05T07:07:57.194114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:57.194114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Goran Glava\\v{s}, Iryna Gurevych, Kexin Wang, Raj Nath Patel, Sourav Dutta, Yongxin Huang","submitted_at":"2023-11-01T10:00:15Z","abstract_excerpt":"Recent work has found that few-shot sentence classification based on pre-trained Sentence Encoders (SEs) is efficient, robust, and effective. In this work, we investigate strategies for domain-specialization in the context of few-shot sentence classification with SEs. We first establish that unsupervised Domain-Adaptive Pre-Training (DAPT) of a base Pre-trained Language Model (PLM) (i.e., not an SE) substantially improves the accuracy of few-shot sentence classification by up to 8.4 points. However, applying DAPT on SEs, on the one hand, disrupts the effects of their (general-domain) Sentence "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00408","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/2311.00408/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":"2311.00408","created_at":"2026-07-05T07:07:57.194168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00408v1","created_at":"2026-07-05T07:07:57.194168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00408","created_at":"2026-07-05T07:07:57.194168+00:00"},{"alias_kind":"pith_short_12","alias_value":"RO3B2FYS4NHB","created_at":"2026-07-05T07:07:57.194168+00:00"},{"alias_kind":"pith_short_16","alias_value":"RO3B2FYS4NHBLQXC","created_at":"2026-07-05T07:07:57.194168+00:00"},{"alias_kind":"pith_short_8","alias_value":"RO3B2FYS","created_at":"2026-07-05T07:07:57.194168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09259","citing_title":"Self-Anchored Attention Model for Sample-Efficient Classification of Prosocial Text Chat","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E","json":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E.json","graph_json":"https://pith.science/api/pith-number/RO3B2FYS4NHBLQXCPP66XAEO4E/graph.json","events_json":"https://pith.science/api/pith-number/RO3B2FYS4NHBLQXCPP66XAEO4E/events.json","paper":"https://pith.science/paper/RO3B2FYS"},"agent_actions":{"view_html":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E","download_json":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E.json","view_paper":"https://pith.science/paper/RO3B2FYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00408&json=true","fetch_graph":"https://pith.science/api/pith-number/RO3B2FYS4NHBLQXCPP66XAEO4E/graph.json","fetch_events":"https://pith.science/api/pith-number/RO3B2FYS4NHBLQXCPP66XAEO4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E/action/storage_attestation","attest_author":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E/action/author_attestation","sign_citation":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E/action/citation_signature","submit_replication":"https://pith.science/pith/RO3B2FYS4NHBLQXCPP66XAEO4E/action/replication_record"}},"created_at":"2026-07-05T07:07:57.194168+00:00","updated_at":"2026-07-05T07:07:57.194168+00:00"}