{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NMP6NLPJBTGBS5ZJ4B3NLY6MDU","short_pith_number":"pith:NMP6NLPJ","schema_version":"1.0","canonical_sha256":"6b1fe6ade90ccc197729e076d5e3cc1d25cfeaf87081a61b0660f63232f0f317","source":{"kind":"arxiv","id":"2311.09825","version":1},"attestation_state":"computed","paper":{"title":"Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingsheng Yao, Dakuo Wang, Peng Zhang, Shao Zhang, Toby Jia-Jun Li, Tun Lu, Yun Wang, Yuxuan Lu","submitted_at":"2023-11-16T11:51:13Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance. However, in real-world tasks, domain knowledge is often required. Low-resource learning methods like Active Learning (AL) have been proposed to tackle the cost of domain expert annotation, raising this question: Can LLMs surpass compact models trained with expert annotations in domain-specific tasks? In this work, we conduct an empirical experiment on four datasets from three different domains comparing SOTA LLMs with small models trained on expert an"},"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":"2311.09825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:51:13Z","cross_cats_sorted":[],"title_canon_sha256":"5906017ab53f52dee97ebf07376c0f5742e035971a4a3ffb7c9021137df70ce1","abstract_canon_sha256":"f0ff2f09185329efbe708261f2b56549892ac636335023f34ebe0b0c8d01259d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:33.370586Z","signature_b64":"74ecOgrU7LBQX5lZ74l3OKmj/DFvJXO3KwhvanYtrczL8pQbSmY1jtoTTy12sWFTjEXxSth0ZiE/QJ8BB5tEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b1fe6ade90ccc197729e076d5e3cc1d25cfeaf87081a61b0660f63232f0f317","last_reissued_at":"2026-07-05T07:13:33.369648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:33.369648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human Still Wins over LLM: An Empirical Study of Active Learning on Domain-Specific Annotation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingsheng Yao, Dakuo Wang, Peng Zhang, Shao Zhang, Toby Jia-Jun Li, Tun Lu, Yun Wang, Yuxuan Lu","submitted_at":"2023-11-16T11:51:13Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated considerable advances, and several claims have been made about their exceeding human performance. However, in real-world tasks, domain knowledge is often required. Low-resource learning methods like Active Learning (AL) have been proposed to tackle the cost of domain expert annotation, raising this question: Can LLMs surpass compact models trained with expert annotations in domain-specific tasks? In this work, we conduct an empirical experiment on four datasets from three different domains comparing SOTA LLMs with small models trained on expert an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09825","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/2311.09825/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":"2311.09825","created_at":"2026-07-05T07:13:33.369698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09825v1","created_at":"2026-07-05T07:13:33.369698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09825","created_at":"2026-07-05T07:13:33.369698+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMP6NLPJBTGB","created_at":"2026-07-05T07:13:33.369698+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMP6NLPJBTGBS5ZJ","created_at":"2026-07-05T07:13:33.369698+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMP6NLPJ","created_at":"2026-07-05T07:13:33.369698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05003","citing_title":"A Multi-Stage Large Language Model Framework for Extracting Suicide-Related Social Determinants of Health","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU","json":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU.json","graph_json":"https://pith.science/api/pith-number/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/graph.json","events_json":"https://pith.science/api/pith-number/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/events.json","paper":"https://pith.science/paper/NMP6NLPJ"},"agent_actions":{"view_html":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU","download_json":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU.json","view_paper":"https://pith.science/paper/NMP6NLPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09825&json=true","fetch_graph":"https://pith.science/api/pith-number/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/graph.json","fetch_events":"https://pith.science/api/pith-number/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/action/storage_attestation","attest_author":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/action/author_attestation","sign_citation":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/action/citation_signature","submit_replication":"https://pith.science/pith/NMP6NLPJBTGBS5ZJ4B3NLY6MDU/action/replication_record"}},"created_at":"2026-07-05T07:13:33.369698+00:00","updated_at":"2026-07-05T07:13:33.369698+00:00"}