{"paper":{"title":"\"If I Had to Buy Just ONE: Galaxy S26 Ultra\": Auditing AI-Generated Product Recommendations","arxiv_id":"2609.18729","primary_cat":"cs.CY","submitted_at":"2026-09-16T14:29:22+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Consumers increasingly use AI chatbots for advice on what to buy.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.04,"main_claim_p":0.01,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.96,"id":"s1","own":false,"role":"background","text":"With companies like OpenAI and Google monetising their AI through advertising, this raises difficult questions about the bias and impartiality of such advice.","hedge":{"p":0.76,"label":"asserted"},"own_p":0.04,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.04,"method":0.0,"result":0.0,"background":0.96,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.95,"id":"s2","own":true,"role":"contribution","text":"In response, we conduct an AI audit of popular chatbots using real commercial-advice queries.","hedge":{"p":0.9,"label":"asserted"},"own_p":0.93,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.95,"interpretation":0.0}},{"i":3,"p":0.99,"id":"s3","own":true,"role":"method","text":"First, we curate a dataset of 2,528 real commercial-advice queries (ConsumerQ).","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.02,"quantitative":true,"quantitative_p":0.98,"role_probabilities":{"gap":0.0,"method":0.99,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.0}},{"i":4,"p":0.98,"id":"s4","own":true,"role":"method","text":"Then, we evaluate 1,536 responses to product queries from popular AI chatbots: ChatGPT (chatbot and API), Google Gemini (chatbot and API), and Google Search (AI Overviews).","hedge":{"p":0.95,"label":"asserted"},"own_p":0.93,"main_claim_p":0.02,"quantitative":true,"quantitative_p":0.96,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":5,"p":1.0,"id":"s5","own":true,"role":"result","text":"We find that ChatGPT expresses a first-person product preference in 79% of product-recommending responses, compared with 7% for Gemini and 2% for AI Overviews, while the products recommended often change across repeated requests.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.97,"main_claim_p":0.14,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":6,"p":1.0,"id":"s6","own":true,"role":"result","text":"Displayed sources vary strongly: for the same query, the ChatGPT and Gemini interfaces share only 5.4% of domains on average, with no domain in common in 76.7% of comparisons.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":7,"p":1.0,"id":"s7","own":true,"role":"result","text":"APIs provide a different view from their corresponding interfaces, with mean domain overlaps of 12.0% for ChatGPT and 14.8% for Gemini, and also differ in the types and layers of source information they expose.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.05,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":8,"p":0.95,"id":"s8","own":true,"role":"interpretation","text":"Our findings show that neither isolated responses nor API observations can be assumed to represent the commercial advice consumers encounter.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.84,"main_claim_p":0.63,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.05,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.95}},{"i":9,"p":0.79,"id":"s9","own":false,"role":"future_work","text":"Independent audits of AI-mediated commercial advice should therefore account for repeated responses, consumer-facing conditions, and the source layer being observed.","hedge":{"p":0.87,"label":"asserted"},"own_p":0.25,"main_claim_p":0.77,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.79,"contribution":0.0,"interpretation":0.21}}]},"compiled":{"main_claim":{"p":0.89,"text":"Our findings show that neither isolated responses nor API observations can be assumed to represent the commercial advice consumers encounter.","location":"abstract s8","hedge_strength":{"p":0.99,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7645,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.07,"states_limitation":0.68,"human_participants":0.15,"controlled_comparison":0.17,"randomized_assignment":0.02,"states_quantitative_result":0.99,"compares_with_prior_results":0.58,"mentions_code_or_data_availability":0.04},"evidential_basis":{"p":0.98,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.02,"observation_or_experiment":0.98,"simulation_or_computation":0.0}},"contribution_type":{"p":1.0,"value":"empirical study","probabilities":{"review":0.0,"method_or_tool":0.0,"empirical_study":1.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.95,"text":"In response, we conduct an AI audit of popular chatbots using real commercial-advice queries.","location":"abstract s2"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448}}