{"id":"https://openalex.org/W7214975710","doi":"https://doi.org/10.48550/arxiv.2610.14024","title":"Beyond a Better Score: Long-Horizon Agentic ML Development and Evaluation Protocol for Physics Time Series","display_name":"Beyond a Better Score: Long-Horizon Agentic ML Development and Evaluation Protocol for Physics Time Series","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214975710","doi":"https://doi.org/10.48550/arxiv.2610.14024"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.14024","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.14024","pdf_url":"https://arxiv.org/pdf/2610.14024","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/2610.14024","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107929968","display_name":"Yajun Ma","orcid":"https://orcid.org/0000-0002-5227-675X","observed_orcids":["https://orcid.org/0000-0002-5227-675X"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ma, Yue","raw_affiliation_strings":["Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143953067","display_name":"Lucas Venetoulias","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venetoulias, Lucas","raw_affiliation_strings":["Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153658980","display_name":"Akbota Assan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Assan, Akbota","raw_affiliation_strings":["Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016189936","display_name":"A. Li","orcid":"https://orcid.org/0000-0002-4844-9339","observed_orcids":["https://orcid.org/0000-0002-4844-9339"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Aobo","raw_affiliation_strings":["Department of Physics , University of California San Diego La Jolla , CA 92093 , USA","Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics , University of California San Diego La Jolla , CA 92093 , USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Hal\u0131c\u0131oglu Data Science Institute , University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"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/T13904","display_name":"Artificial Intelligence Applications","score":0.4390000104904175,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.4390000104904175,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.21729999780654907,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.06960000097751617,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.9169999957084656},{"id":"https://openalex.org/keywords/mode-collapse","display_name":"mode collapse","score":0.6610000133514404},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"human-in-the-loop","score":0.7639999985694885},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6026999950408936},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5313000082969666},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42980000376701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41659998893737793},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.4041000008583069},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35600000619888306},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3479999899864197},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2610.14024","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.14024","pdf_url":"https://arxiv.org/pdf/2610.14024","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.2610.14024","doi":"https://doi.org/10.48550/arxiv.2610.14024","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.14024","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"},{"id":"doi:10.5281/zenodo.23071120","doi":"https://doi.org/10.5281/zenodo.23071120","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23071120","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23071121","doi":"https://doi.org/10.5281/zenodo.23071121","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23071121","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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:2610.14024","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.14024","pdf_url":"https://arxiv.org/pdf/2610.14024","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214975710.pdf","grobid_xml":"https://content.openalex.org/works/W7214975710.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4385963839","https://openalex.org/W4387432648","https://openalex.org/W4403571374","https://openalex.org/W4416159200","https://openalex.org/W7140287209","https://openalex.org/W7140324928","https://openalex.org/W7196932832"],"related_works":["https://openalex.org/W7167825852","https://openalex.org/W7223242834","https://openalex.org/W4416159200","https://openalex.org/W4414587939","https://openalex.org/W7117242258","https://openalex.org/W7154966767","https://openalex.org/W7222478994","https://openalex.org/W7128395166","https://openalex.org/W7162409218","https://openalex.org/W7118539294"],"abstract_inverted_index":{"Physics":[0],"time-series":[1,181],"data":[2],"are":[3,40,76],"central":[4],"to":[5,21,87],"fundamental":[6],"discoveries":[7],"involving":[8],"dark":[9],"matter,":[10],"neutrinos,":[11],"and":[12,107,123,148,159,186,213],"gravitational":[13],"waves.":[14],"Machine":[15],"learning":[16],"has":[17],"shown":[18],"strong":[19],"potential":[20],"recover":[22],"weak":[23],"scientific":[24,111,129,199],"signals":[25],"buried":[26],"in":[27,197],"complex":[28],"noise.":[29],"Recent":[30],"LLM-agent":[31],"systems":[32],"further":[33,174],"automate":[34],"ML":[35,97,200],"development,":[36],"but":[37,75],"existing":[38],"approaches":[39],"often":[41],"driven":[42],"primarily":[43],"by":[44,208,214],"one":[45],"or":[46,64,120],"a":[47,54,90,109,137,205],"few":[48],"numerical":[49],"scores.":[50],"In":[51,131],"pursuit":[52],"of":[53,146,154],"better":[55,91,206],"score,":[56,207],"agents":[57],"may":[58],"exploit":[59],"shortcuts,":[60],"trigger":[61],"mode":[62],"collapse,":[63],"game":[65],"the":[66,141,149,163,168,216],"evaluation":[67,112],"procedure,":[68],"producing":[69],"models":[70,117,217],"that":[71,114,195],"achieve":[72],"high":[73],"scores":[74],"scientifically":[77,94],"invalid.":[78],"We":[79,173],"introduce":[80],"SIDERIUS,":[81],"an":[82,210],"LLM":[83],"agent":[84,211],"system":[85],"designed":[86],"move":[88],"beyond":[89,204],"score":[92,153],"toward":[93],"valid,":[95],"long-horizon":[96],"development.":[98],"SIDERIUS":[99,135,176],"combines":[100],"contract-defined":[101],"composable":[102],"capabilities":[103],"for":[104,126,162],"flexible":[105],"orchestration":[106],"human-in-the-loop,":[108],"multi-layer":[110],"protocol":[113],"distinguishes":[115],"valid":[116,151],"from":[118],"unhealthy":[119],"gaming":[121],"models,":[122],"resource-aware":[124],"exploration":[125],"computationally":[127],"expensive":[128],"ML.":[130],"our":[132],"TIDMAD":[133],"benchmark,":[134],"with":[136,157],"GPT-based":[138],"orchestrator":[139],"achieves":[140],"highest":[142],"Valid-model":[143],"proposal":[144],"rate":[145],"63.8%":[147],"best":[150],"denoising":[152],"2.744,":[155],"compared":[156],"1.6%":[158],"-0.647,":[160],"respectively,":[161],"same":[164],"GPT":[165],"model":[166],"using":[167],"general-purpose":[169],"Codex":[170],"coding":[171],"agent.":[172],"benchmark":[175],"on":[177],"three":[178],"additional":[179],"physics":[180],"datasets,":[182],"demonstrating":[183],"its":[184],"reuse":[185],"performance":[187],"across":[188],"different":[189],"tasks.":[190],"Together,":[191],"these":[192],"results":[193],"suggest":[194],"progress":[196],"agentic":[198],"should":[201],"be":[202,221],"measured":[203],"how":[209],"explores":[212],"whether":[215],"it":[218],"produces":[219],"can":[220],"trusted":[222],"as":[223],"science.":[224]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}