{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QRZ2A24VMJ4LEW63JH2WAQMZRZ","short_pith_number":"pith:QRZ2A24V","schema_version":"1.0","canonical_sha256":"8473a06b956278b25bdb49f56041998e7bac353ad2ac13bea2c1c66b299cdfd6","source":{"kind":"arxiv","id":"2508.06484","version":1},"attestation_state":"computed","paper":{"title":"Non-programmers Assessing AI-Generated Code: A Case Study of Business Users Analyzing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Dongyu Liu, Yuvraj Virk","submitted_at":"2025-08-08T17:49:22Z","abstract_excerpt":"Non-technical end-users increasingly rely on AI code generation to perform technical tasks like data analysis. However, large language models (LLMs) remain unreliable, and it is unclear whether end-users can effectively identify model errors $\\unicode{x2014}$ especially in realistic and domain-specific scenarios. We surveyed marketing and sales professionals to assess their ability to critically evaluate LLM-generated analyses of marketing data. Participants were shown natural language explanations of the AI's code, repeatedly informed the AI often makes mistakes, and explicitly prompted to id"},"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":"2508.06484","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-08-08T17:49:22Z","cross_cats_sorted":[],"title_canon_sha256":"c71b7a3ea879d349f841c6ccb031729acb890d7d0b7e07f72ef5d223c9db75e2","abstract_canon_sha256":"8ec1c769566cf1e274808f3cbdc3b858cd821eeb5834553ae88e019eab208055"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:57.166727Z","signature_b64":"8PSE36nZPihQyOPOPV5Pgsyg6xBYVn+Dfzs14PJv1co6q3jHL1prHujFYI9U4fVggkYcFdifOFIeEv1b/VefDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8473a06b956278b25bdb49f56041998e7bac353ad2ac13bea2c1c66b299cdfd6","last_reissued_at":"2026-07-05T11:50:57.166110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:57.166110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-programmers Assessing AI-Generated Code: A Case Study of Business Users Analyzing Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Dongyu Liu, Yuvraj Virk","submitted_at":"2025-08-08T17:49:22Z","abstract_excerpt":"Non-technical end-users increasingly rely on AI code generation to perform technical tasks like data analysis. However, large language models (LLMs) remain unreliable, and it is unclear whether end-users can effectively identify model errors $\\unicode{x2014}$ especially in realistic and domain-specific scenarios. We surveyed marketing and sales professionals to assess their ability to critically evaluate LLM-generated analyses of marketing data. Participants were shown natural language explanations of the AI's code, repeatedly informed the AI often makes mistakes, and explicitly prompted to id"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06484","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/2508.06484/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":"2508.06484","created_at":"2026-07-05T11:50:57.166180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06484v1","created_at":"2026-07-05T11:50:57.166180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06484","created_at":"2026-07-05T11:50:57.166180+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRZ2A24VMJ4L","created_at":"2026-07-05T11:50:57.166180+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRZ2A24VMJ4LEW63","created_at":"2026-07-05T11:50:57.166180+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRZ2A24V","created_at":"2026-07-05T11:50:57.166180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24521","citing_title":"From Prompting to Verification: How Experience Shapes Vibe Coding Practices","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ","json":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ.json","graph_json":"https://pith.science/api/pith-number/QRZ2A24VMJ4LEW63JH2WAQMZRZ/graph.json","events_json":"https://pith.science/api/pith-number/QRZ2A24VMJ4LEW63JH2WAQMZRZ/events.json","paper":"https://pith.science/paper/QRZ2A24V"},"agent_actions":{"view_html":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ","download_json":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ.json","view_paper":"https://pith.science/paper/QRZ2A24V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06484&json=true","fetch_graph":"https://pith.science/api/pith-number/QRZ2A24VMJ4LEW63JH2WAQMZRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QRZ2A24VMJ4LEW63JH2WAQMZRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ/action/storage_attestation","attest_author":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ/action/author_attestation","sign_citation":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ/action/citation_signature","submit_replication":"https://pith.science/pith/QRZ2A24VMJ4LEW63JH2WAQMZRZ/action/replication_record"}},"created_at":"2026-07-05T11:50:57.166180+00:00","updated_at":"2026-07-05T11:50:57.166180+00:00"}