{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7GXQB5NSMTYXQKN2HVWFVXE63W","short_pith_number":"pith:7GXQB5NS","schema_version":"1.0","canonical_sha256":"f9af00f5b264f17829ba3d6c5adc9eddb88669bf2fd94cce76c87cdbc9763970","source":{"kind":"arxiv","id":"2507.00543","version":1},"attestation_state":"computed","paper":{"title":"Reliable Annotations with Less Effort: Evaluating LLM-Human Collaboration in Search Clarifications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.IR","authors_text":"Hamed Zamani, Leila Tavakoli","submitted_at":"2025-07-01T08:04:58Z","abstract_excerpt":"Despite growing interest in using large language models (LLMs) to automate annotation, their effectiveness in complex, nuanced, and multi-dimensional labelling tasks remains relatively underexplored. This study focuses on annotation for the search clarification task, leveraging a high-quality, multi-dimensional dataset that includes five distinct fine-grained annotation subtasks. Although LLMs have shown impressive capabilities in general settings, our study reveals that even state-of-the-art models struggle to replicate human-level performance in subjective or fine-grained evaluation tasks. T"},"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":"2507.00543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-01T08:04:58Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"bd0a5d0b769d66d061409da0bcf854f611c3b234c30ee6abf92d6b2bac9253f2","abstract_canon_sha256":"579898543b11ce1a41b7429dcff38c62c98d01d123664ac2f4977f454290037c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:10.592543Z","signature_b64":"/6gH8fbDZILiXhu5lzqk1gPlQQBWYMgU+5wM+XotUV8P7FmO8htkzOCZaAW5SQhWgsZB2/C2tVoevkMPm9izAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9af00f5b264f17829ba3d6c5adc9eddb88669bf2fd94cce76c87cdbc9763970","last_reissued_at":"2026-07-05T11:30:10.592107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:10.592107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Annotations with Less Effort: Evaluating LLM-Human Collaboration in Search Clarifications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.IR","authors_text":"Hamed Zamani, Leila Tavakoli","submitted_at":"2025-07-01T08:04:58Z","abstract_excerpt":"Despite growing interest in using large language models (LLMs) to automate annotation, their effectiveness in complex, nuanced, and multi-dimensional labelling tasks remains relatively underexplored. This study focuses on annotation for the search clarification task, leveraging a high-quality, multi-dimensional dataset that includes five distinct fine-grained annotation subtasks. Although LLMs have shown impressive capabilities in general settings, our study reveals that even state-of-the-art models struggle to replicate human-level performance in subjective or fine-grained evaluation tasks. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00543","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/2507.00543/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":"2507.00543","created_at":"2026-07-05T11:30:10.592162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00543v1","created_at":"2026-07-05T11:30:10.592162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00543","created_at":"2026-07-05T11:30:10.592162+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GXQB5NSMTYX","created_at":"2026-07-05T11:30:10.592162+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GXQB5NSMTYXQKN2","created_at":"2026-07-05T11:30:10.592162+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GXQB5NS","created_at":"2026-07-05T11:30:10.592162+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/7GXQB5NSMTYXQKN2HVWFVXE63W","json":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W.json","graph_json":"https://pith.science/api/pith-number/7GXQB5NSMTYXQKN2HVWFVXE63W/graph.json","events_json":"https://pith.science/api/pith-number/7GXQB5NSMTYXQKN2HVWFVXE63W/events.json","paper":"https://pith.science/paper/7GXQB5NS"},"agent_actions":{"view_html":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W","download_json":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W.json","view_paper":"https://pith.science/paper/7GXQB5NS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00543&json=true","fetch_graph":"https://pith.science/api/pith-number/7GXQB5NSMTYXQKN2HVWFVXE63W/graph.json","fetch_events":"https://pith.science/api/pith-number/7GXQB5NSMTYXQKN2HVWFVXE63W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W/action/storage_attestation","attest_author":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W/action/author_attestation","sign_citation":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W/action/citation_signature","submit_replication":"https://pith.science/pith/7GXQB5NSMTYXQKN2HVWFVXE63W/action/replication_record"}},"created_at":"2026-07-05T11:30:10.592162+00:00","updated_at":"2026-07-05T11:30:10.592162+00:00"}