{"id":"https://openalex.org/W7163990229","doi":"https://doi.org/10.48550/arxiv.2606.08935","title":"PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection","display_name":"PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7163990229","doi":"https://doi.org/10.48550/arxiv.2606.08935"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08935","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.2606.08935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138225086","display_name":"Kang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016712110","display_name":"Wei Jian Lau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lau, Wei Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103055019","display_name":"Shoushou Ren","orcid":"https://orcid.org/0009-0003-8530-5259"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Shoushou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702468","display_name":"Dong Lin","orcid":"https://orcid.org/0000-0003-3736-8768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138283902","display_name":"Joon Son Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung, Joon Son","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054171919","display_name":"Chuanhao Sun","orcid":"https://orcid.org/0000-0003-4889-2055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Chuanhao","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9761000275611877,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9761000275611877,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.008999999612569809,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/amplitude","display_name":"Amplitude","score":0.644599974155426},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6431000232696533},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.6075000166893005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5351999998092651},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5198000073432922},{"id":"https://openalex.org/keywords/notice","display_name":"Notice","score":0.41819998621940613},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.4041000008583069}],"concepts":[{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.644599974155426},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6431000232696533},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5198000073432922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44029998779296875},{"id":"https://openalex.org/C2779913896","wikidata":"https://www.wikidata.org/wiki/Q7063001","display_name":"Notice","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4043999910354614},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.3310000002384186},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08935","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.2606.08935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08935","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Representation-based":[0],"time-series":[1,213],"anomaly":[2,11,62,137,214],"detection":[3,12],"algorithms":[4],"significantly":[5],"outperform":[6],"other":[7],"methods":[8,152],"on":[9,40,90,185],"diverse":[10],"tasks.":[13],"However,":[14],"we":[15,58],"notice":[16],"that":[17,204],"they":[18],"suffer":[19],"from":[20],"a":[21,60,73,77,115,123,192],"major":[22],"limitation":[23],"in":[24,103,108,220],"our":[25],"evaluation":[26,184],"-":[27],"their":[28],"learned":[29,105],"embeddings":[30],"are":[31,127],"often":[32],"amplitude-agnostic.":[33],"Losing":[34],"amplitude":[35,41,98,207],"information":[36,99,208],"can":[37],"degrade":[38],"performance":[39],"related":[42],"anomalies,":[43],"and":[44,76,87,118,122,142,163,191],"this":[45],"failure":[46],"is":[47,100,209,225],"prevalent":[48],"across":[49,153],"all":[50,148,167],"existing":[51,221],"representation-based":[52,151,212],"methods.":[53],"To":[54],"address":[55],"aforementioned":[56],"issues,":[57],"propose":[59],"new":[61],"scoring":[63,89,222],"scheme":[64],"named":[65],"PAI.":[66],"PAI":[67,113,146,172],"consists":[68],"of":[69,161],"two":[70],"complementary":[71],"modules,":[72],"diagnostic":[74,83],"module":[75,84],"final":[78,109,136],"score":[79,110,121,132],"augmentation":[80,111],"function.":[81],"The":[82],"compares":[85],"cosine":[86],"Euclidean":[88],"the":[91,104,130,135,140,174,178,198],"same":[92],"representation":[93,131],"bank":[94],"to":[95,133],"test":[96],"whether":[97],"already":[101],"captured":[102],"representation.":[106],"Then":[107],"function,":[112],"computes":[114],"point-wise":[116],"median":[117],"MAD":[119],"deviation":[120],"local":[124],"mean-shift":[125],"score-which":[126],"fused":[128],"with":[129],"produce":[134],"score.":[138],"On":[139],"TSB-AD-U-Eva":[141],"TAB":[143],"UV":[144],"datasets,":[145],"improves":[147],"four":[149],"evaluated":[150,168],"every":[154],"reported":[155],"metric,":[156],"achieving":[157],"average":[158],"VUS-PR":[159],"gains":[160],"98.4%":[162],"36.8%,":[164],"respectively.":[165],"Among":[166],"combinations,":[169],"PaAno":[170],"+":[171],"achieves":[173],"best":[175],"performance,":[176],"outperforming":[177],"state-of-the-art":[179],"method":[180],"by":[181],"15%.":[182],"Further":[183],"bootstrap":[186],"confidence":[187],"intervals,":[188],"anomaly-type":[189],"breakdowns,":[190],"TS2Vec":[193],"input-normalization":[194],"ablation":[195],"further":[196],"support":[197],"proposed":[199],"scheme.":[200],"These":[201],"results":[202],"suggest":[203],"explicitly":[205],"retaining":[206],"important":[210],"for":[211],"detection,":[215],"which":[216],"has":[217],"been":[218],"underemphasized":[219],"schemes.":[223],"Code":[224],"available":[226],"at:":[227],"https://github.com/pantheon5100/PAI":[228]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-10T00:00:00"}