{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VZKEU67W7JB7FGHB5F44S5DL4B","short_pith_number":"pith:VZKEU67W","schema_version":"1.0","canonical_sha256":"ae544a7bf6fa43f298e1e979c9746be06f92abd941993487c5ee24ae8898a738","source":{"kind":"arxiv","id":"2509.07512","version":1},"attestation_state":"computed","paper":{"title":"ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Lei Shi, Qiji Zhou, Weize Wu, Yue Zhang, Zihan Chen","submitted_at":"2025-09-09T08:47:13Z","abstract_excerpt":"Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a best performance-cost trade-off, we propose ALLabel, a three-stage framework designed to select the mo"},"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":"2509.07512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-09T08:47:13Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"e785d2400f593a3b0ffa1c39947a7f9e7dea6bd17e236d109721862fce9935d1","abstract_canon_sha256":"ef774d567a29b06f436d9fd2680e017334585af5aa594080d81c4192d11c37da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:22.899594Z","signature_b64":"3P89EwliA8K3cHpD5PW9ko63mTKaFSfyGLrrBYQEiIleeQaXP9kzNomRqRub1ScLjdBpKbw1Zp+cZn+RpPXhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae544a7bf6fa43f298e1e979c9746be06f92abd941993487c5ee24ae8898a738","last_reissued_at":"2026-07-05T12:07:22.899009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:22.899009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALLabel: Three-stage Active Learning for LLM-based Entity Recognition using Demonstration Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Lei Shi, Qiji Zhou, Weize Wu, Yue Zhang, Zihan Chen","submitted_at":"2025-09-09T08:47:13Z","abstract_excerpt":"Many contemporary data-driven research efforts in the natural sciences, such as chemistry and materials science, require large-scale, high-performance entity recognition from scientific datasets. Large language models (LLMs) have increasingly been adopted to solve the entity recognition task, with the same trend being observed on all-spectrum NLP tasks. The prevailing entity recognition LLMs rely on fine-tuned technology, yet the fine-tuning process often incurs significant cost. To achieve a best performance-cost trade-off, we propose ALLabel, a three-stage framework designed to select the mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.07512","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/2509.07512/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":"2509.07512","created_at":"2026-07-05T12:07:22.899098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.07512v1","created_at":"2026-07-05T12:07:22.899098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.07512","created_at":"2026-07-05T12:07:22.899098+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZKEU67W7JB7","created_at":"2026-07-05T12:07:22.899098+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZKEU67W7JB7FGHB","created_at":"2026-07-05T12:07:22.899098+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZKEU67W","created_at":"2026-07-05T12:07:22.899098+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/VZKEU67W7JB7FGHB5F44S5DL4B","json":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B.json","graph_json":"https://pith.science/api/pith-number/VZKEU67W7JB7FGHB5F44S5DL4B/graph.json","events_json":"https://pith.science/api/pith-number/VZKEU67W7JB7FGHB5F44S5DL4B/events.json","paper":"https://pith.science/paper/VZKEU67W"},"agent_actions":{"view_html":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B","download_json":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B.json","view_paper":"https://pith.science/paper/VZKEU67W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.07512&json=true","fetch_graph":"https://pith.science/api/pith-number/VZKEU67W7JB7FGHB5F44S5DL4B/graph.json","fetch_events":"https://pith.science/api/pith-number/VZKEU67W7JB7FGHB5F44S5DL4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/action/storage_attestation","attest_author":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/action/author_attestation","sign_citation":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/action/citation_signature","submit_replication":"https://pith.science/pith/VZKEU67W7JB7FGHB5F44S5DL4B/action/replication_record"}},"created_at":"2026-07-05T12:07:22.899098+00:00","updated_at":"2026-07-05T12:07:22.899098+00:00"}