{"id":"https://openalex.org/W7213462128","doi":"https://doi.org/10.26434/chemrxiv.15008972/v1","title":"Benchmark Label Definition, Not Model Capability, Explains a Machine-Learning Advantage over TD-DFT for \u03bbmax Prediction","display_name":"Benchmark Label Definition, Not Model Capability, Explains a Machine-Learning Advantage over TD-DFT for \u03bbmax Prediction","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213462128","doi":"https://doi.org/10.26434/chemrxiv.15008972/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008972/v1","doi":"https://doi.org/10.26434/chemrxiv.15008972/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008972/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.26434/chemrxiv.15008972/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093698010","display_name":"Md Sahanawaz","orcid":"https://orcid.org/0009-0000-6615-5441","observed_orcids":["https://orcid.org/0009-0000-6615-5441","https://orcid.org/0009-0008-0694-6952"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Md Sahanawaz","raw_affiliation_strings":["Science and Humanities, Sheikhpara ARM Polytechnic, Sheikhpara, Murshidabad, West Bengal, India, 742409"],"raw_orcid":"https://orcid.org/0009-0000-6615-5441","affiliations":[{"raw_affiliation_string":"Science and Humanities, Sheikhpara ARM Polytechnic, Sheikhpara, Murshidabad, West Bengal, India, 742409","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5093698010"],"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/T11948","display_name":"Machine Learning in Materials Science","score":0.6039999723434448,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.6039999723434448,"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"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.1720000058412552,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.14090000092983246,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"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/uv-vis-spectroscopy","display_name":"UV-Vis spectroscopy","score":0.7400000095367432},{"id":"https://openalex.org/keywords/gaussian-process-regression","display_name":"Gaussian process regression","score":0.7680000066757202},{"id":"https://openalex.org/keywords/morgan-fingerprints","display_name":"Morgan fingerprints","score":0.9509999752044678},{"id":"https://openalex.org/keywords/out-of-sample-generalization","display_name":"out-of-sample generalization","score":0.5709999799728394},{"id":"https://openalex.org/keywords/vertical-excitation-energies","display_name":"vertical excitation energies","score":0.5950000286102295},{"id":"https://openalex.org/keywords/photoswitches","display_name":"photoswitches","score":0.7519999742507935}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5781999826431274},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5601000189781189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5483999848365784},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C91528185","wikidata":"https://www.wikidata.org/wiki/Q520952","display_name":"Maxima","level":3,"score":0.4449999928474426},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4429999887943268},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.43810001015663147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42989999055862427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4262999892234802},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C152365726","wikidata":"https://www.wikidata.org/wiki/Q1048589","display_name":"Density functional theory","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3433000147342682},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2969000041484833},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.2937999963760376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2728999853134155},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C125287762","wikidata":"https://www.wikidata.org/wiki/Q1758948","display_name":"Absorption (acoustics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008972/v1","doi":"https://doi.org/10.26434/chemrxiv.15008972/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008972/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15008972/v1","doi":"https://doi.org/10.26434/chemrxiv.15008972/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008972/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403257581","https://openalex.org/W7203758840","https://openalex.org/W4404499589","https://openalex.org/W6884302750","https://openalex.org/W4417335106","https://openalex.org/W7163988928","https://openalex.org/W3205047255","https://openalex.org/W7140656488","https://openalex.org/W4251003250","https://openalex.org/W7222801990"],"abstract_inverted_index":{"Machine-learning":[0],"models":[1],"trained":[2,69],"on":[3,30,70,154,171,198],"literature-mined":[4,77],"UV-Vis":[5],"data":[6],"are":[7,204],"frequently":[8],"reported":[9,94,316],"to":[10,134,176],"outperform":[11],"time-dependent":[12],"density":[13],"functional":[14,272],"theory":[15],"(TD-DFT)":[16],"for":[17],"predicting":[18],"absorption":[19],"maxima":[20],"(\u03bb":[21],"max":[22],").":[23],"Such":[24],"comparisons":[25],"usually":[26],"evaluate":[27],"the":[28,34,75,79,86,93,100,103,126,138,144,177,190,202,205,236,244,297,301,309,328,337,340],"model":[29,90,140,314],"held-out":[31],"molecules":[32],"from":[33,74,308],"same":[35,139],"corpus":[36],"that":[37,82],"supplied":[38],"its":[39,291,333,345],"training":[40,150,310],"labels,":[41],"and":[42,125,157,222,284,332,344],"they":[43],"set":[44,303],"experimental":[45],"labels":[46],"of":[47,55,85,257,300,327,336],"heterogeneous":[48],"transition":[49],"type":[50],"against":[51,111,120,243,262],"computed":[52,264],"vertical":[53,196],"excitations":[54,197],"a":[56,61,167,267,271],"single":[57],"electronic":[58],"transition.":[59],"Using":[60],"Gaussian":[62],"process":[63],"(GP)":[64],"with":[65,149,166,224,294],"256-bit":[66],"Morgan":[67],"fingerprints,":[68],"6,878":[71],"curated":[72],"compounds":[73],"Beard":[76],"database,":[78],"study":[80],"shows":[81],"two":[83],"features":[84],"benchmark,":[87],"rather":[88,269,304],"than":[89,270,305],"capability,":[91],"govern":[92],"margin.":[95],"On":[96,235],"leakage-free":[97],"in-corpus":[98,254],"holdouts":[99],"GP":[101,274],"outperforms":[102],"quantum-chemical":[104,251],"references":[105],"(RMSE":[106],"87.3":[107],"vs":[108,117,217,233],"108.7":[109],"nm":[110,119,169,219,242,250,261],"TD-DFT,":[112],"n":[113,122],"=":[114,123,152,164,231],"36;":[115],"81.6":[116],"117.1":[118],"sTDA,":[121],"1,011),":[124],"advantage":[127],"survives":[128],"Bemis\u2013Murcko":[129],"scaffold":[130],"splitting.":[131],"Applied":[132],"unchanged":[133],"genuinely":[135],"external":[136,282,343],"corpora,":[137],"keeps":[141],"working":[142],"where":[143,159],"label":[145,191,298,330,346],"convention":[146,347],"is":[147,161,214,277,342,348],"compatible":[148],"(R\u00b2":[151,163],"+0.209":[153],"5,811":[155],"compounds)":[156],"fails":[158],"it":[160],"not":[162,186,286],"\u22120.269":[165],"+53.5":[168],"offset":[170,213],"318":[172],"photoswitches":[173],"labelled":[174],"specifically":[175],"E":[178],"-isomer":[179],"\u03c0\u2192\u03c0*":[180],"transition);":[181],"chemical":[182],"novelty":[183],"alone":[184],"does":[185,285],"break":[187],"it,":[188],"reassigning":[189],"does.":[192],"Against":[193],"published":[194],"\u03c9B97X-D3":[195],"5,501":[199],"training-disjoint":[200],"compounds,":[201],"calculations":[203],"more":[206],"accurate":[207],"predictor":[208],"once":[209],"each":[210],"method\u2019s":[211],"removable":[212],"discounted":[215],"(\u224858":[216],"95":[218],"residual":[220],"scatter)":[221],"correlate":[223],"experiment":[225],"nearly":[226],"twice":[227],"as":[228,325],"strongly":[229],"(r":[230],"0.85":[232],"0.46).":[234],"transition-specific":[237],"corpus,":[238],"CAM-B3LYP/6-31G**":[239],"reaches":[240],"25.4":[241],"GP\u2019s":[245],"80.9":[246],"nm.":[247],"The":[248],"57\u201365":[249],"underestimation":[252],"seen":[253],"reappears":[255],"out":[256],"sample":[258],"at":[259],"\u221261.9":[260],"independently":[263],"values,":[265],"supporting":[266],"definitional":[268],"origin.":[273],"predictive":[275],"uncertainty":[276],"poorly":[278],"calibrated":[279],"in":[280],"all":[281],"regimes":[283],"reliably":[287],"identify":[288],"high-error":[289],"predictions;":[290],"apparent":[292],"correlation":[293],"error":[295],"reflects":[296],"variance":[299],"evaluation":[302],"structural":[306],"distance":[307],"distribution.":[311],"For":[312],"this":[313],"class,":[315],"margins":[317],"over":[318],"quantum":[319],"chemistry":[320],"should":[321],"therefore":[322],"be":[323],"regarded":[324],"properties":[326],"benchmark\u2014its":[329],"definition":[331],"same-corpus":[334],"provenance,not":[335],"method,":[338],"unless":[339],"benchmark":[341],"stated.":[349]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-17T00:00:00"}