{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DEYOY5QXAATKTCNMJMZBE2C2XY","short_pith_number":"pith:DEYOY5QX","schema_version":"1.0","canonical_sha256":"1930ec76170026a989ac4b3212685abe3d3d21f6cf9b13cd4c2a991754c0ca62","source":{"kind":"arxiv","id":"2506.03857","version":1},"attestation_state":"computed","paper":{"title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haobo Wang, Jindong Wang, Junbo Zhao, Mingxuan Xia, Runze Wu, Yixuan Li, Zewei Yu","submitted_at":"2025-06-04T11:42:37Z","abstract_excerpt":"Recently, Large Language Models (LLMs) have demonstrated significant potential for data annotation, markedly reducing the labor costs associated with downstream applications. However, existing methods mostly adopt an aggressive strategy by prompting LLM to determine a single gold label for each unlabeled sample. Due to the inherent uncertainty within LLMs, they often produce incorrect labels for difficult samples, severely compromising the data quality for downstream applications. Motivated by ambiguity aversion in human behaviors, we propose a novel candidate annotation paradigm wherein large"},"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":"2506.03857","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T11:42:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2c6c9ba911867b9ae85ecb2c887b6297a26927a65bbcc1e29fa012473d82e439","abstract_canon_sha256":"b928956159525673bb8c88700c4319f719bc7005d464451f53ee22363e61e0b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:52.927929Z","signature_b64":"wwJIvE5DperT5Gb0e5EH6as6/QvBXK9qHhraAM5arVhmhefnD3pK+/VD4VeaV8xbmpnmVpxsR2/8kG2THgiPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1930ec76170026a989ac4b3212685abe3d3d21f6cf9b13cd4c2a991754c0ca62","last_reissued_at":"2026-07-05T11:15:52.927384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:52.927384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haobo Wang, Jindong Wang, Junbo Zhao, Mingxuan Xia, Runze Wu, Yixuan Li, Zewei Yu","submitted_at":"2025-06-04T11:42:37Z","abstract_excerpt":"Recently, Large Language Models (LLMs) have demonstrated significant potential for data annotation, markedly reducing the labor costs associated with downstream applications. However, existing methods mostly adopt an aggressive strategy by prompting LLM to determine a single gold label for each unlabeled sample. Due to the inherent uncertainty within LLMs, they often produce incorrect labels for difficult samples, severely compromising the data quality for downstream applications. Motivated by ambiguity aversion in human behaviors, we propose a novel candidate annotation paradigm wherein large"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03857","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/2506.03857/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":"2506.03857","created_at":"2026-07-05T11:15:52.927449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03857v1","created_at":"2026-07-05T11:15:52.927449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03857","created_at":"2026-07-05T11:15:52.927449+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEYOY5QXAATK","created_at":"2026-07-05T11:15:52.927449+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEYOY5QXAATKTCNM","created_at":"2026-07-05T11:15:52.927449+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEYOY5QX","created_at":"2026-07-05T11:15:52.927449+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/DEYOY5QXAATKTCNMJMZBE2C2XY","json":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY.json","graph_json":"https://pith.science/api/pith-number/DEYOY5QXAATKTCNMJMZBE2C2XY/graph.json","events_json":"https://pith.science/api/pith-number/DEYOY5QXAATKTCNMJMZBE2C2XY/events.json","paper":"https://pith.science/paper/DEYOY5QX"},"agent_actions":{"view_html":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY","download_json":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY.json","view_paper":"https://pith.science/paper/DEYOY5QX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03857&json=true","fetch_graph":"https://pith.science/api/pith-number/DEYOY5QXAATKTCNMJMZBE2C2XY/graph.json","fetch_events":"https://pith.science/api/pith-number/DEYOY5QXAATKTCNMJMZBE2C2XY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY/action/storage_attestation","attest_author":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY/action/author_attestation","sign_citation":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY/action/citation_signature","submit_replication":"https://pith.science/pith/DEYOY5QXAATKTCNMJMZBE2C2XY/action/replication_record"}},"created_at":"2026-07-05T11:15:52.927449+00:00","updated_at":"2026-07-05T11:15:52.927449+00:00"}