{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DCJABTA4CPAQRGE5DYLKMIITUS","short_pith_number":"pith:DCJABTA4","schema_version":"1.0","canonical_sha256":"189200cc1c13c108989d1e16a62113a481235e497c965213a549616d7093e9a6","source":{"kind":"arxiv","id":"2411.11081","version":2},"attestation_state":"computed","paper":{"title":"The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Andre Greiner-Petter, Bela Gipp, Christoph Mandl, Terry Ruas, Timo Spinde, Tomas Horych","submitted_at":"2024-11-17T14:14:36Z","abstract_excerpt":"High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation process, reducing these costs while maintaining data quality. LLMs have shown promising results in annotating downstream tasks like hate speech detection and political framing. Building on the success in these areas, this study investigates whether LLMs are viable for annotating the complex task of media bias detection and whether a downstream media bias cl"},"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":"2411.11081","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-17T14:14:36Z","cross_cats_sorted":[],"title_canon_sha256":"3180d99c2242ab5393262be14d8ee47dd2da6ceb9dfe0498447e07c7d188ae0c","abstract_canon_sha256":"bbe97f9f69bdba43a72c242f33ebaa75a76dff77e6041ff2bf018a41a4aee15c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:40.976627Z","signature_b64":"UC+zwQlmtAbcQ0RpHGGGT1faOhDgK714HJXg8FTCnm2nP4WDV7SCZ055df0D5u3Ps/930HhvFLEztP1bBAhPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"189200cc1c13c108989d1e16a62113a481235e497c965213a549616d7093e9a6","last_reissued_at":"2026-07-05T10:04:40.976160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:40.976160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Promises and Pitfalls of LLM Annotations in Dataset Labeling: a Case Study on Media Bias Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Andre Greiner-Petter, Bela Gipp, Christoph Mandl, Terry Ruas, Timo Spinde, Tomas Horych","submitted_at":"2024-11-17T14:14:36Z","abstract_excerpt":"High annotation costs from hiring or crowdsourcing complicate the creation of large, high-quality datasets needed for training reliable text classifiers. Recent research suggests using Large Language Models (LLMs) to automate the annotation process, reducing these costs while maintaining data quality. LLMs have shown promising results in annotating downstream tasks like hate speech detection and political framing. Building on the success in these areas, this study investigates whether LLMs are viable for annotating the complex task of media bias detection and whether a downstream media bias cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11081","kind":"arxiv","version":2},"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/2411.11081/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":"2411.11081","created_at":"2026-07-05T10:04:40.976214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11081v2","created_at":"2026-07-05T10:04:40.976214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11081","created_at":"2026-07-05T10:04:40.976214+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCJABTA4CPAQ","created_at":"2026-07-05T10:04:40.976214+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCJABTA4CPAQRGE5","created_at":"2026-07-05T10:04:40.976214+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCJABTA4","created_at":"2026-07-05T10:04:40.976214+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/DCJABTA4CPAQRGE5DYLKMIITUS","json":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS.json","graph_json":"https://pith.science/api/pith-number/DCJABTA4CPAQRGE5DYLKMIITUS/graph.json","events_json":"https://pith.science/api/pith-number/DCJABTA4CPAQRGE5DYLKMIITUS/events.json","paper":"https://pith.science/paper/DCJABTA4"},"agent_actions":{"view_html":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS","download_json":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS.json","view_paper":"https://pith.science/paper/DCJABTA4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11081&json=true","fetch_graph":"https://pith.science/api/pith-number/DCJABTA4CPAQRGE5DYLKMIITUS/graph.json","fetch_events":"https://pith.science/api/pith-number/DCJABTA4CPAQRGE5DYLKMIITUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS/action/storage_attestation","attest_author":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS/action/author_attestation","sign_citation":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS/action/citation_signature","submit_replication":"https://pith.science/pith/DCJABTA4CPAQRGE5DYLKMIITUS/action/replication_record"}},"created_at":"2026-07-05T10:04:40.976214+00:00","updated_at":"2026-07-05T10:04:40.976214+00:00"}