{"id":"https://openalex.org/W7214062097","doi":"https://doi.org/10.26434/chemrxiv.15009293/v1","title":"A Reported Featurizer Ranking Instability Is Noise Between Inseparable Arms","display_name":"A Reported Featurizer Ranking Instability Is Noise Between Inseparable Arms","publication_year":2026,"publication_date":"2026-09-22","ids":{"openalex":"https://openalex.org/W7214062097","doi":"https://doi.org/10.26434/chemrxiv.15009293/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009293/v1","doi":"https://doi.org/10.26434/chemrxiv.15009293/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009293/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009293/v1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009293/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5150490732","display_name":"Phani Kumar Balagam","orcid":"https://orcid.org/0009-0007-6762-399X","observed_orcids":["https://orcid.org/0009-0007-6762-399X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Phani Kumar Balagam","raw_affiliation_strings":["Independent researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5150490732"],"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.9404000043869019,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9404000043869019,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.01730000041425228,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00570000009611249,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/representation-comparison","display_name":"representation comparison","score":0.6269999742507935},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"data deduplication","score":0.6930000185966492},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.4580000042915344}],"concepts":[{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5759999752044678},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5264000296592712},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5187000036239624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4772999882698059},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.4503999948501587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.438400000333786},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4246000051498413},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.38940000534057617},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C2984485829","wikidata":"https://www.wikidata.org/wiki/Q100766421","display_name":"Noise level","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C26263659","wikidata":"https://www.wikidata.org/wiki/Q1886131","display_name":"Random seed","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15009293/v1","doi":"https://doi.org/10.26434/chemrxiv.15009293/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009293/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009293/v1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15009293/v1","doi":"https://doi.org/10.26434/chemrxiv.15009293/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009293/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009293/v1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337472","display_name":"National Center for Advancing Translational Sciences","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214062097.pdf","grobid_xml":"https://content.openalex.org/works/W7214062097.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1988037271","https://openalex.org/W2019678805","https://openalex.org/W2049610662","https://openalex.org/W2060531713","https://openalex.org/W2076498053","https://openalex.org/W2117897510","https://openalex.org/W2329862012","https://openalex.org/W2594183968"],"related_works":["https://openalex.org/W2740606810","https://openalex.org/W7034032257","https://openalex.org/W7166849082","https://openalex.org/W2758404062","https://openalex.org/W4411532053","https://openalex.org/W7140797120","https://openalex.org/W2129815403","https://openalex.org/W3044965819","https://openalex.org/W3128030921","https://openalex.org/W7000488451"],"abstract_inverted_index":{"Representation":[0],"comparisons":[1],"are":[2],"commonly":[3],"published":[4],"from":[5],"one":[6,9,31],"split":[7,27],"at":[8],"seed":[10],"on":[11],"uncurated":[12],"public":[13],"sets.":[14],"Repeating":[15],"one,":[16,30],"the":[17,26,50],"count":[18],"of":[19,63],"endpoints":[20],"whose":[21,46],"best":[22],"featurizer":[23],"changes":[24],"with":[25],"read":[28],"three,":[29],"and":[32,38,40],"three":[33],"under":[34],"two":[35],"choices,":[36],"seeds":[37],"deduplication,":[39],"every":[41],"reorder":[42],"lay":[43],"between":[44],"arms":[45],"intervals":[47],"overlap.":[48],"Only":[49],"fingerprint":[51],"baseline":[52],"separated":[53],"anywhere,":[54],"by":[55],"being":[56],"worse;":[57],"duplicates":[58],"placed":[59],"up":[60],"to":[61],"3.8%":[62],"random-split":[64],"test":[65],"rows":[66],"in":[67],"training.":[68],"A":[69],"four-step":[70],"remedy":[71],"is":[72],"given.":[73]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-23T00:00:00"}