{"id":"https://openalex.org/W7161696527","doi":"https://doi.org/10.48550/arxiv.2605.17276","title":"How Do Electrocardiogram Models Scale?","display_name":"How Do Electrocardiogram Models Scale?","publication_year":2026,"publication_date":"2026-05-17","ids":{"openalex":"https://openalex.org/W7161696527","doi":"https://doi.org/10.48550/arxiv.2605.17276"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17276","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136471812","display_name":"Jiawei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071094145","display_name":"Fabio Bonassi","orcid":"https://orcid.org/0000-0002-7270-8185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bonassi, Fabio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136504881","display_name":"Ming Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016001130","display_name":"Stefan Gustafsson","orcid":"https://orcid.org/0000-0001-5894-0351"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gustafsson, Stefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074614812","display_name":"Johan Sundstr\u00f6m","orcid":"https://orcid.org/0000-0003-2247-8454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sundstr\u00f6m, Johan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136464223","display_name":"Thomas B. Sch\u00f6n","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sch\u00f6n, Thomas B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136460601","display_name":"Ant\u00f4nio H. Ribeiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ribeiro, Ant\u00f4nio H.","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/T11021","display_name":"ECG Monitoring and Analysis","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11021","display_name":"ECG Monitoring and Analysis","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10217","display_name":"Cardiac electrophysiology and arrhythmias","score":0.004999999888241291,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.003599999938160181,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5684999823570251},{"id":"https://openalex.org/keywords/overtaking","display_name":"Overtaking","score":0.44600000977516174},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42590001225471497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4056999981403351},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.39489999413490295},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.39250001311302185},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.35339999198913574},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.353300005197525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6435999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5684999823570251},{"id":"https://openalex.org/C2778448659","wikidata":"https://www.wikidata.org/wiki/Q1931051","display_name":"Overtaking","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.353300005197525},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17276","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17276","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7450309991836548}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"scaling":[1,73],"laws":[2,74],"have":[3],"established":[4],"a":[5],"fundamental":[6],"framework":[7],"for":[8,139],"foundation":[9,215],"models":[10,20,83,123,129,183,216],"in":[11,218],"natural":[12],"language":[13],"processing,":[14],"their":[15],"applicability":[16],"to":[17,87,146,157,165,212],"electrocardiogram":[18],"(ECG)":[19],"remains":[21],"poorly":[22],"characterized.":[23],"Indeed,":[24],"recent":[25],"studies":[26],"do":[27],"not":[28],"always":[29],"yield":[30],"consistent":[31],"downstream":[32],"gains":[33],"as":[34],"one":[35],"increases":[36],"the":[37,48,76,91,99,179,186,210,219],"model":[38,102,134,204],"size":[39,43,61],"or":[40],"pre-training":[41,55,80,108],"dataset":[42,94],"of":[44,51,101,222],"ECG":[45,77,214],"models,":[46],"leaving":[47],"exact":[49],"roles":[50],"architectural":[52],"inductive":[53],"biases,":[54],"paradigms,":[56],"and":[57,71,107,135,162,197,224],"expected":[58],"improvements":[59],"with":[60,190],"largely":[62],"unanswered.":[63],"In":[64],"this":[65],"work,":[66],"we":[67,97],"systematically":[68],"investigate":[69],"neural":[70],"loss-to-loss":[72],"within":[75],"domain.":[78],"By":[79],"over":[81],"$120$":[82],"(ranging":[84],"from":[85],"$20$K":[86],"$200$M":[88],"parameters)":[89],"on":[90,173,193],"large-scale":[92],"CODE":[93],"($2.3$M":[95],"records),":[96],"decouple":[98],"effects":[100],"architecture":[103,223],"(ResNet":[104],"vs.":[105],"Transformer)":[106],"paradigm,":[109],"namely":[110],"supervised":[111],"learning":[112,116],"(SL)":[113],"versus":[114],"self-supervised":[115,198],"(SSL).":[117],"We":[118],"found":[119],"that":[120,209],"(i)":[121],"SL":[122,172],"are":[124,144],"data-bottlenecked":[125],"in-distribution,":[126],"whereas":[127],"SSL":[128,154,191],"scale":[130],"robustly":[131],"across":[132,178],"both":[133],"data":[136],"sizes;":[137],"(ii)":[138],"out-of-distribution":[140],"(OOD)":[141],"generalization,":[142],"ResNets":[143],"$1.3$":[145],"$2.5$":[147],"times":[148,159,167],"more":[149,160],"parameter-efficient":[150],"than":[151,171,227],"Transformers,":[152],"while":[153],"is":[155],"up":[156,164],"$16$":[158],"data-efficient":[161],"achieves":[163],"$7.6$":[166],"higher":[168],"transfer":[169],"efficiency":[170],"unseen":[174,194],"clinical":[175,195],"tasks;":[176],"(iii)":[177],"observed":[180],"scales,":[181],"ResNet-based":[182],"generally":[184],"achieve":[185],"lowest":[187],"OOD":[188],"loss,":[189],"dominating":[192],"tasks":[196],"Transformers":[199],"overtaking":[200],"at":[201],"very":[202],"large":[203],"sizes.":[205],"Our":[206],"results":[207],"suggest":[208],"path":[211],"effective":[213],"lies":[217],"strategic":[220],"alignment":[221],"paradigm":[225],"rather":[226],"brute-force":[228],"scaling.":[229]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}