{"id":"https://openalex.org/W7213506592","doi":"https://doi.org/10.48550/arxiv.2609.17738","title":"Similarity Pairing with Energy Mover's Distance for Self-Supervised Pre-Training at the LHC","display_name":"Similarity Pairing with Energy Mover's Distance for Self-Supervised Pre-Training at the LHC","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213506592","doi":"https://doi.org/10.48550/arxiv.2609.17738"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.17738","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17738","pdf_url":"https://arxiv.org/pdf/2609.17738","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.17738","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018957120","display_name":"Ho Fung Tsoi","orcid":"https://orcid.org/0000-0002-2550-2184","observed_orcids":["https://orcid.org/0000-0002-2550-2184"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsoi, Ho Fung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000142430","display_name":"Dylan Sheldon Rankin","orcid":"https://orcid.org/0000-0001-8411-9620","observed_orcids":["https://orcid.org/0000-0001-8411-9620","https://orcid.org/0000-0001-9234-4465","https://orcid.org/0000-0003-3119-9924"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rankin, Dylan","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":true,"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/T10048","display_name":"Particle physics theoretical and experimental studies","score":0.7529000043869019,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10048","display_name":"Particle physics theoretical and experimental studies","score":0.7529000043869019,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.05649999901652336,"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/T11044","display_name":"Particle Detector Development and Performance","score":0.032099999487400055,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.8360000252723694},{"id":"https://openalex.org/keywords/self-distillation","display_name":"self-distillation","score":0.7889999747276306},{"id":"https://openalex.org/keywords/qcd-jets","display_name":"QCD jets","score":0.9309999942779541},{"id":"https://openalex.org/keywords/large-hadron-collider","display_name":"Large Hadron Collider","score":0.8209999799728394},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.527999997138977}],"concepts":[{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.7486000061035156},{"id":"https://openalex.org/C87668248","wikidata":"https://www.wikidata.org/wiki/Q40605","display_name":"Large Hadron Collider","level":2,"score":0.734499990940094},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6830999851226807},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.559499979019165},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.54830002784729},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5285000205039978},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.4885999858379364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4805999994277954},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C119947313","wikidata":"https://www.wikidata.org/wiki/Q5596635","display_name":"Jet (fluid)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.428600013256073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4025000035762787},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C152290109","wikidata":"https://www.wikidata.org/wiki/Q2033879","display_name":"Collider","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C117137515","wikidata":"https://www.wikidata.org/wiki/Q238170","display_name":"Quantum chromodynamics","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2779081240","wikidata":"https://www.wikidata.org/wiki/Q9178706","display_name":"Missing energy","level":4,"score":0.29670000076293945},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C19694890","wikidata":"https://www.wikidata.org/wiki/Q101667","display_name":"Hadron","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.17738","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17738","pdf_url":"https://arxiv.org/pdf/2609.17738","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.2609.17738","doi":"https://doi.org/10.48550/arxiv.2609.17738","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.17738","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:2609.17738","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17738","pdf_url":"https://arxiv.org/pdf/2609.17738","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":[{"id":"https://openalex.org/G1624822810","display_name":"CI-New: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI)","funder_award_id":"1730158","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1891638606","display_name":"SEARCHING FOR NEW PHYSICS WITH REAL-TIME ANOMALY DETECTION","funder_award_id":"DESC0025324","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G3725287634","display_name":"Towards Deploying a Science-Driven Regional Interoperable Science DMZ","funder_award_id":"1540112","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G502606643","display_name":"CC* NPEO: Toward the National Research Platform","funder_award_id":"1826967","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5665456810","display_name":"CCRI: ABR: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI)","funder_award_id":"2100237","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6003409357","display_name":"Category II: A Prototype National Research Platform","funder_award_id":"2112167","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7278722489","display_name":"CC*DNI DIBBs: The Pacific Research Platform","funder_award_id":"1541349","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G898084569","display_name":"CCRI: ENS: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI)","funder_award_id":"2120019","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332603","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48"},{"id":"https://openalex.org/F4320337511","display_name":"High Energy Physics","ror":"https://ror.org/035m6g344"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213506592.pdf","grobid_xml":"https://content.openalex.org/works/W7213506592.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2100507804","https://openalex.org/W2899663614","https://openalex.org/W2911264653","https://openalex.org/W3015829700","https://openalex.org/W3035524453","https://openalex.org/W3189302471","https://openalex.org/W4230927393","https://openalex.org/W4393684434","https://openalex.org/W4400720716","https://openalex.org/W4407803509","https://openalex.org/W4410106196","https://openalex.org/W4413059258","https://openalex.org/W4417063412","https://openalex.org/W7083696831","https://openalex.org/W7125187787"],"related_works":["https://openalex.org/W4414945936","https://openalex.org/W4407245117","https://openalex.org/W7125187787","https://openalex.org/W4407803509","https://openalex.org/W7115930375","https://openalex.org/W3217036328","https://openalex.org/W4400720716","https://openalex.org/W7222994374","https://openalex.org/W7164911744","https://openalex.org/W4308162087"],"abstract_inverted_index":{"Many":[0],"self-supervised":[1],"methods":[2],"for":[3,133],"training":[4],"foundation":[5],"models":[6],"at":[7],"the":[8,19,40,66,93,108,115,137],"Large":[9],"Hadron":[10],"Collider":[11],"(LHC)":[12],"rely":[13],"on":[14,50,155],"data":[15],"augmentations":[16,49,58],"to":[17,21,29,111,129,174],"encourage":[18],"model":[20],"embed":[22],"events":[23,88,103,121],"into":[24,114],"a":[25,45,83],"representation":[26],"space":[27],"invariant":[28],"certain":[30],"physical":[31],"or":[32,69,175],"detector":[33],"symmetries.":[34],"A":[35],"common":[36],"challenge":[37],"arises":[38],"from":[39],"large":[41],"freedom":[42],"in":[43,105],"choosing":[44],"proper":[46],"set":[47],"of":[48,57,86,107,140],"which":[51,74,98],"downstream":[52,170],"performance":[53],"depends.":[54],"The":[55],"implementation":[56],"involves":[59],"either":[60],"modifying":[61],"existing":[62],"events,":[63],"potentially":[64],"breaking":[65],"event":[67,72,142],"fidelity,":[68],"simulating":[70],"more":[71],"variants,":[73],"is":[75],"computationally":[76],"intensive.":[77],"In":[78],"this":[79,118,149],"work,":[80],"we":[81],"present":[82],"data-driven":[84],"method":[85,152],"pairing":[87,151],"by":[89,126,153],"their":[90,127],"similarity":[91,128],"via":[92,158],"energy":[94],"mover's":[95],"distance":[96],"(EMD),":[97],"measures":[99],"how":[100],"similar":[101],"two":[102],"are":[104,122],"terms":[106],"work":[109],"required":[110],"transform":[112],"one":[113],"other.":[116],"With":[117],"approach,":[119],"distinct":[120],"sampled":[123],"and":[124,160],"matched":[125],"serve":[130],"as":[131],"views":[132],"learning":[134],"invariance,":[135],"keeping":[136],"physics":[138],"content":[139],"each":[141],"intact":[143],"without":[144],"handcrafted":[145],"distortions.":[146],"We":[147],"demonstrate":[148],"augmentation-free":[150],"pre-training":[154],"QCD":[156],"jets":[157],"self-distillation":[159],"show":[161],"that":[162],"it":[163],"can":[164],"yield":[165],"semantic":[166],"jet":[167],"embeddings":[168],"with":[169],"discrimination":[171],"power":[172],"comparable":[173],"better":[176],"than":[177],"an":[178],"augmentation-based":[179],"baseline.":[180]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-18T00:00:00"}