{"id":"https://openalex.org/W7225147456","doi":"https://doi.org/10.48550/arxiv.2611.03420","title":"Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models","display_name":"Temporal Island Sparse Autoencoders for Interpreting Clinical Time-Series Models","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225147456","doi":"https://doi.org/10.48550/arxiv.2611.03420"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03420","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03420","pdf_url":"https://arxiv.org/pdf/2611.03420","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.03420","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027982753","display_name":"Muhan Yeo","orcid":"https://orcid.org/0000-0003-0751-2407","observed_orcids":["https://orcid.org/0000-0003-0751-2407"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeo, Muhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015477574","display_name":"Bong Gyun Kang","orcid":"https://orcid.org/0000-0002-2287-4564","observed_orcids":["https://orcid.org/0000-0002-2287-4564"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Bong Gyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083994142","display_name":"HyunGi Kim","orcid":"https://orcid.org/0009-0005-8854-1446","observed_orcids":["https://orcid.org/0009-0005-8854-1446"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, HyunGi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160522930","display_name":"Sungroh Yoon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoon, Sungroh","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/T13702","display_name":"Machine Learning in Healthcare","score":0.8173999786376953,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.8173999786376953,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.18070000410079956,"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/T10350","display_name":"Electronic Health Records Systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sparse-autoencoders","display_name":"sparse autoencoders","score":0.8450000286102295},{"id":"https://openalex.org/keywords/electronic-health-records","display_name":"electronic health records","score":0.7820000052452087},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6790000200271606},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.5289999842643738},{"id":"https://openalex.org/keywords/faithfulness","display_name":"faithfulness","score":0.4620000123977661},{"id":"https://openalex.org/keywords/mimic-iii","display_name":"MIMIC-III","score":0.8479999899864197},{"id":"https://openalex.org/keywords/mimic-iv","display_name":"MIMIC-IV","score":0.9580000042915344},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7889999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7560999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163000106811523},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5954999923706055},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46950000524520874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C77277458","wikidata":"https://www.wikidata.org/wiki/Q1969246","display_name":"Temporal database","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C2988886741","wikidata":"https://www.wikidata.org/wiki/Q25304494","display_name":"Dictionary learning","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03420","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03420","pdf_url":"https://arxiv.org/pdf/2611.03420","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.03420","doi":"https://doi.org/10.48550/arxiv.2611.03420","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03420","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.03420","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03420","pdf_url":"https://arxiv.org/pdf/2611.03420","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160516884","https://openalex.org/W7112063281","https://openalex.org/W2963532813","https://openalex.org/W7220651987","https://openalex.org/W2809396336","https://openalex.org/W7224097882","https://openalex.org/W2404901863","https://openalex.org/W2923493534","https://openalex.org/W3213237073","https://openalex.org/W7223701893"],"abstract_inverted_index":{"Deep":[0],"learning":[1,102],"models":[2],"for":[3],"electronic":[4],"health":[5],"records":[6],"achieve":[7],"strong":[8,137],"predictive":[9,58],"performance":[10,138],"but":[11],"provide":[12],"little":[13],"insight":[14],"into":[15],"what":[16],"clinical":[17,52,127],"concepts":[18,128],"they":[19],"represent":[20],"internally.":[21],"Post-hoc":[22],"attribution":[23,133],"methods":[24],"produce":[25],"per-cell":[26],"importance":[27],"scores":[28],"that":[29,129],"lack":[30],"temporal":[31,69],"coherence,":[32],"cross-variable":[33],"structure,":[34],"and":[35,78,118],"reusability":[36],"across":[37,108],"patients.":[38],"We":[39,105],"introduce":[40],"the":[41,74],"Temporal":[42],"Island":[43],"Sparse":[44],"Autoencoder":[45],"(TI-SAE),":[46],"which":[47,84,93],"learns":[48],"a":[49,56,79],"backbone-specific,":[50],"patient-shared":[51],"concept":[53,75],"dictionary":[54,62,94],"from":[55,103],"frozen":[57],"model's":[59],"representations.":[60],"Each":[61],"entry":[63],"(latent)":[64],"is":[65,76],"defined":[66],"by":[67],"learned":[68],"Gaussian":[70],"islands":[71],"(specifying":[72,83],"when":[73],"active)":[77],"sparse":[80],"variable-composition":[81],"vector":[82],"variables":[85],"are":[86],"involved).":[87],"A":[88],"decoupled":[89],"selector":[90],"then":[91],"identifies":[92],"entries":[95],"drive":[96],"each":[97],"patient's":[98],"prediction,":[99],"separating":[100],"representation":[101,114],"attribution.":[104],"evaluate":[106],"TI-SAE":[107,124],"five":[109],"backbone":[110],"architectures":[111],"spanning":[112],"different":[113],"strategies":[115],"on":[116,139],"MIMIC-III":[117],"MIMIC-IV":[119],"(three":[120],"prediction":[121],"tasks":[122],"each).":[123],"produces":[125],"structured":[126],"go":[130],"beyond":[131],"transient":[132],"heatmaps":[134],"while":[135],"achieving":[136],"standard":[140],"faithfulness":[141],"benchmarks.":[142]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}