{"id":"https://openalex.org/W7160888283","doi":"https://doi.org/10.48550/arxiv.2605.08590","title":"Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations","display_name":"Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations","publication_year":2026,"publication_date":"2026-05-09","ids":{"openalex":"https://openalex.org/W7160888283","doi":"https://doi.org/10.48550/arxiv.2605.08590"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.08590","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083742240","display_name":"Shanshan Zhu","orcid":"https://orcid.org/0000-0001-9265-8595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Shanshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135957487","display_name":"Han Zhang","orcid":"https://orcid.org/0009-0001-2612-9166"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133419574","display_name":"J. Doris Chi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, J. Doris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135992724","display_name":"Subigya Nepal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nepal, Subigya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135968268","display_name":"Koustuv Saha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saha, Koustuv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.17080000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.17080000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.06539999693632126,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.05820000171661377,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6883999705314636},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6241000294685364},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.4406999945640564},{"id":"https://openalex.org/keywords/mood","display_name":"Mood","score":0.4325999915599823},{"id":"https://openalex.org/keywords/motivated-reasoning","display_name":"Motivated reasoning","score":0.41269999742507935},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3935000002384186},{"id":"https://openalex.org/keywords/overconfidence-effect","display_name":"Overconfidence effect","score":0.3718000054359436}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6883999705314636},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6241000294685364},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5763000249862671},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.46869999170303345},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C2780733359","wikidata":"https://www.wikidata.org/wiki/Q331769","display_name":"Mood","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.41269999742507935},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3734000027179718},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C2781426361","wikidata":"https://www.wikidata.org/wiki/Q5326940","display_name":"Earnings","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C80114427","wikidata":"https://www.wikidata.org/wiki/Q634260","display_name":"Circumstantial evidence","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.26910001039505005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.08590","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08590","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.7965103387832642,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"LLMs":[0,184],"are":[1],"increasingly":[2],"used":[3],"to":[4,127,130,144,147,189],"explain":[5],"personal":[6,240,250],"sensing":[7,63,84,241,251],"data,":[8,196],"translating":[9],"traces":[10],"of":[11,18,86,140,167],"activity":[12],"and":[13,32,71,91,96,110,121,178,197,206,245,265],"mood":[14],"into":[15,164],"natural-language":[16],"accounts":[17],"why":[19],"an":[20],"anomalous":[21,187],"day":[22],"may":[23],"have":[24],"occurred.":[25],"However,":[26],"such":[27],"explanations":[28,102,252],"can":[29,65],"sound":[30],"coherent":[31],"personally":[33],"meaningful":[34],"even":[35],"when":[36],"the":[37,61,131,138,145,165,195],"underlying":[38],"evidence":[39,64,142,151],"is":[40,260,263],"sparse":[41],"or":[42],"missing.":[43],"We":[44,154,181,247],"introduce":[45],"epistemic":[46],"overreach":[47],"(EO)":[48],"as":[49],"a":[50,55,159,234],"measure":[51],"for":[52,238],"cases":[53],"where":[54],"generated":[56,100],"explanation":[57,157],"implies":[58],"more":[59,150],"than":[60],"available":[62,143],"justify.":[66],"To":[67],"audit":[68],"how":[69],"often":[70],"in":[72],"what":[73,259,262,266],"forms":[74],"EO":[75,163],"occurs,":[76],"we":[77,99,136],"obtained":[78],"anomalous-day":[79],"scenarios":[80],"from":[81,194],"three":[82,104],"longitudinal":[83],"datasets":[85],"college":[87],"students:":[88],"StudentLife,":[89],"GLOBEM,":[90],"CollegeExperience.":[92],"Across":[93],"activity,":[94],"sleep,":[95],"affect":[97],"anomalies,":[98],"14,922":[101],"using":[103,158],"LLM":[105],"families":[106],"--":[107,112],"Llama,":[108],"Qwen,":[109],"GPT":[111],"under":[113],"two":[114],"prompting":[115,219],"conditions:":[116],"one":[117],"minimally":[118],"constrained":[119],"prompt":[120,123],"another":[122],"explicitly":[124],"instructing":[125],"models":[126],"bound":[128],"claims":[129],"data.":[132],"For":[133],"each":[134,156],"scenario,":[135],"varied":[137],"amount":[139],"behavioral":[141],"model":[146,207],"examine":[148],"whether":[149],"reduces":[152],"EO.":[153],"evaluated":[155],"structured":[160],"rubric,":[161],"decomposing":[162],"dimensions":[166],"unsupported":[168],"causal":[169],"attribution,":[170],"unacknowledged":[171],"data":[172],"gaps,":[173],"overconfident":[174],"language,":[175],"temporal":[176],"inconsistency,":[177],"diagnostic":[179],"inference.":[180],"find":[182],"that":[183,198,229,249],"routinely":[185],"attribute":[186],"days":[188],"causes":[190],"without":[191],"sufficient":[192],"support":[193],"this":[199],"pattern":[200],"replicates":[201],"across":[202],"datasets,":[203],"anomaly":[204],"types,":[205],"families.":[208],"Further,":[209],"providing":[210],"richer":[211],"context":[212],"does":[213,222],"not":[214,223],"reliably":[215],"reduce":[216],"EO;":[217],"bounded":[218],"helps":[220],"but":[221],"eliminate":[224],"it.":[225],"These":[226],"findings":[227],"suggest":[228],"evidential":[230,254],"grounding":[231],"should":[232],"be":[233],"first-order":[235],"evaluation":[236],"criterion":[237],"LLM-generated":[239],"explanations,":[242],"alongside":[243],"fluency":[244],"plausibility.":[246],"argue":[248],"require":[253],"discipline:":[255],"systems":[256],"must":[257],"distinguish":[258],"observed,":[261],"inferred,":[264],"remains":[267],"unknown.":[268]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}