{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ID3P4KDKRJZJ5SKIRPYRIC5VQP","short_pith_number":"pith:ID3P4KDK","schema_version":"1.0","canonical_sha256":"40f6fe286a8a729ec9488bf1140bb583fba274ba8a2c04b88f020bd54e2b84aa","source":{"kind":"arxiv","id":"2304.10145","version":2},"attestation_state":"computed","paper":{"title":"Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ehsan-Ul Haq, Gareth Tyson, Pan Hui, Peixian Zhang, Yiming Zhu","submitted_at":"2023-04-20T08:08:12Z","abstract_excerpt":"The release of ChatGPT has uncovered a range of possibilities whereby large language models (LLMs) can substitute human intelligence. In this paper, we seek to understand whether ChatGPT has the potential to reproduce human-generated label annotations in social computing tasks. Such an achievement could significantly reduce the cost and complexity of social computing research. As such, we use ChatGPT to relabel five seminal datasets covering stance detection (2x), sentiment analysis, hate speech, and bot detection. Our results highlight that ChatGPT does have the potential to handle these data"},"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":"2304.10145","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2023-04-20T08:08:12Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"04b035cb7d4f4fc5e857657f3eba1725d534159a765e7ea559880c7b4e642214","abstract_canon_sha256":"e2a6a153ddbe818db77301ce9b98a71ade73523aa1040b4a463d670f0f58beb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:29.042091Z","signature_b64":"g8tTixSmU5xFxi0RTg/2EWpyUPDE4cYwWlX+qjYg49MHqipgJwYwxyKnghbdtzHatwasFzpYgVn4aLAWV3c0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40f6fe286a8a729ec9488bf1140bb583fba274ba8a2c04b88f020bd54e2b84aa","last_reissued_at":"2026-07-05T06:03:29.041698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:29.041698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can ChatGPT Reproduce Human-Generated Labels? A Study of Social Computing Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ehsan-Ul Haq, Gareth Tyson, Pan Hui, Peixian Zhang, Yiming Zhu","submitted_at":"2023-04-20T08:08:12Z","abstract_excerpt":"The release of ChatGPT has uncovered a range of possibilities whereby large language models (LLMs) can substitute human intelligence. In this paper, we seek to understand whether ChatGPT has the potential to reproduce human-generated label annotations in social computing tasks. Such an achievement could significantly reduce the cost and complexity of social computing research. As such, we use ChatGPT to relabel five seminal datasets covering stance detection (2x), sentiment analysis, hate speech, and bot detection. Our results highlight that ChatGPT does have the potential to handle these data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.10145","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/2304.10145/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":"2304.10145","created_at":"2026-07-05T06:03:29.041757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.10145v2","created_at":"2026-07-05T06:03:29.041757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.10145","created_at":"2026-07-05T06:03:29.041757+00:00"},{"alias_kind":"pith_short_12","alias_value":"ID3P4KDKRJZJ","created_at":"2026-07-05T06:03:29.041757+00:00"},{"alias_kind":"pith_short_16","alias_value":"ID3P4KDKRJZJ5SKI","created_at":"2026-07-05T06:03:29.041757+00:00"},{"alias_kind":"pith_short_8","alias_value":"ID3P4KDK","created_at":"2026-07-05T06:03:29.041757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20809","citing_title":"Refining and Reusing Annotation Guidelines for LLM Annotation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":159,"is_internal_anchor":false},{"citing_arxiv_id":"2308.03825","citing_title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09625","citing_title":"Toward Generalized Cross-Lingual Hateful Language Detection with Web-Scale Data and Ensemble LLM Annotations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10339","citing_title":"An Annotation Scheme and Classifier for Personal Facts in Dialogue","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP","json":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP.json","graph_json":"https://pith.science/api/pith-number/ID3P4KDKRJZJ5SKIRPYRIC5VQP/graph.json","events_json":"https://pith.science/api/pith-number/ID3P4KDKRJZJ5SKIRPYRIC5VQP/events.json","paper":"https://pith.science/paper/ID3P4KDK"},"agent_actions":{"view_html":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP","download_json":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP.json","view_paper":"https://pith.science/paper/ID3P4KDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.10145&json=true","fetch_graph":"https://pith.science/api/pith-number/ID3P4KDKRJZJ5SKIRPYRIC5VQP/graph.json","fetch_events":"https://pith.science/api/pith-number/ID3P4KDKRJZJ5SKIRPYRIC5VQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP/action/storage_attestation","attest_author":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP/action/author_attestation","sign_citation":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP/action/citation_signature","submit_replication":"https://pith.science/pith/ID3P4KDKRJZJ5SKIRPYRIC5VQP/action/replication_record"}},"created_at":"2026-07-05T06:03:29.041757+00:00","updated_at":"2026-07-05T06:03:29.041757+00:00"}