{"id":"https://openalex.org/W7167055683","doi":"https://doi.org/10.48550/arxiv.2607.00958","title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","display_name":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7167055683","doi":"https://doi.org/10.48550/arxiv.2607.00958"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.00958","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00958","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":"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.2607.00958","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139923870","display_name":"Alexander Chemeris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chemeris, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139934906","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":"last","author":{"id":"https://openalex.org/A5139944734","display_name":"Randall Balestriero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balestriero, Randall","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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.43689998984336853,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.43689998984336853,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.3422999978065491,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.03400000184774399,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recipe","display_name":"Recipe","score":0.6599000096321106},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6134999990463257},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4869000017642975},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.414000004529953},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.38830000162124634},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.387800008058548},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.37689998745918274},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.37119999527931213}],"concepts":[{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158000230789185},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6134999990463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5900999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5005999803543091},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.414000004529953},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C186450821","wikidata":"https://www.wikidata.org/wiki/Q17295","display_name":"Euclidean space","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26030001044273376},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.00958","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00958","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":"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.2607.00958","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00958","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":"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/9","score":0.47120293974876404,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Time":[0],"series":[1],"are":[2,139],"central":[3],"to":[4,15],"modern":[5],"data":[6],"mining":[7],"applications,":[8],"from":[9],"industrial":[10],"telemetry":[11],"and":[12,17,27,98,128,232],"server":[13],"metrics":[14],"finance":[16],"physiology,":[18],"yet":[19],"time-series":[20,253],"self-supervised":[21],"learning":[22],"often":[23],"depends":[24],"on":[25,126,142,161,168,176],"view":[26],"augmentation":[28],"choices":[29],"that":[30,108],"encode":[31],"domain-specific":[32],"invariances.":[33],"We":[34,69,113],"study":[35],"how":[36],"an":[37,117],"SSL":[38],"recipe":[39,120,157,250],"behaves":[40],"when":[41,165],"its":[42,190],"method-specific":[43,148],"configuration":[44],"is":[45,109,158],"reused":[46,166],"unchanged":[47,167],"after":[48,194],"the":[49,87,100,154,202,240],"pretraining":[50],"signal":[51],"family":[52],"changes,":[53],"framing":[54],"this":[55,152],"as":[56,246],"a":[57,63,77,82,104,122,130,207,212,223,247],"fixed-recipe":[58],"stress":[59],"test":[60],"rather":[61],"than":[62],"comparison":[64],"against":[65],"optimally":[66],"tuned":[67],"methods.":[68],"introduce":[70],"Latent":[71],"Euclidean":[72],"Next-Embedding":[73],"Prediction":[74],"Architecture":[75],"(LeNEPA),":[76],"no-augmentation":[78,243],"next-latent-token":[79],"objective":[80],"with":[81,94,116,135,198],"causal":[83],"backbone.":[84],"LeNEPA":[85,115,171,186,214],"replaces":[86],"stop-gradient/EMA":[88],"stabilization":[89],"used":[90],"by":[91],"vanilla":[92],"NEPA":[93],"SIGReg-based":[95],"isotropy":[96],"regularization":[97],"computes":[99],"predictive":[101],"loss":[102],"in":[103,222],"lightweight":[105],"projected":[106],"space":[107],"discarded":[110],"for":[111,201,251],"evaluation.":[112],"compare":[114],"ECG-tuned":[118,155],"JEPA":[119,156,204],"under":[121],"fixed-horizon":[123],"frozen-probe":[124,174],"protocol":[125],"PTB-XL":[127,162],"Diag,":[129,169],"synthetic":[131],"diagnostic":[132],"corpus":[133],"generated":[134],"Aionoscope.":[136],"Both":[137],"methods":[138],"retrained":[140],"independently":[141],"each":[143],"dataset":[144],"while":[145],"keeping":[146],"their":[147],"recipes":[149],"unchanged.":[150],"In":[151],"protocol,":[153],"strong":[159],"in-domain":[160],"but":[163],"weaker":[164],"whereas":[170],"preserves":[172],"useful":[173,248],"gains":[175],"both":[177],"datasets.":[178],"Learning":[179],"curves":[180],"suggest":[181],"faster":[182,203],"early":[183],"representation":[184],"acquisition:":[185],"reaches":[187,216],"80%":[188],"of":[189,230,236],"final":[191],"AUROC/AUPRC":[192],"gain":[193],"2--5k":[195],"updates,":[196],"compared":[197],"5--10k":[199],"updates":[200],"readout.":[205],"As":[206],"separate":[208],"external":[209],"frozen-encoder":[210],"check,":[211],"CauKer-pretrained":[213],"variant":[215],"77.65%":[217],"mean":[218],"UCR-128":[219],"Random-Forest":[220],"accuracy":[221],"single-seed,":[224],"best-checkpoint":[225],"run,":[226],"within":[227,233],"1.16":[228],"points":[229,235],"Mantis":[231],"0.24":[234],"MOMENT":[237],"(77.89%).":[238],"Overall,":[239],"results":[241],"support":[242],"latent":[244],"prediction":[245],"candidate":[249],"low-retuning":[252],"SSL.":[254]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-03T00:00:00"}