{"id":"https://openalex.org/W7223182121","doi":"https://doi.org/10.31233/osf.io/69js3_v1","title":"Cross-clade limits of melanosome-based color prediction: a cautionary machine learning study","display_name":"Cross-clade limits of melanosome-based color prediction: a cautionary machine learning study","publication_year":2026,"publication_date":"2026-10-22","ids":{"openalex":"https://openalex.org/W7223182121","doi":"https://doi.org/10.31233/osf.io/69js3_v1"},"language":"en","primary_location":{"id":"doi:10.31233/osf.io/69js3_v1","doi":"https://doi.org/10.31233/osf.io/69js3_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31233/osf.io/69js3_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400732","display_name":"PaleoRxiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"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/10.31233/osf.io/69js3_v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159254167","display_name":"Ahnaf Usaid Chowdhury","orcid":"https://orcid.org/0009-0001-5795-7335","observed_orcids":["https://orcid.org/0009-0001-5795-7335"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahnaf Usaid Chowdhury","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-5795-7335","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5159249528","display_name":"Tanvir Shahriar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanvir Shahriar","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/T10955","display_name":"Paleontology and Evolutionary Biology","score":0.7968999743461609,"subfield":{"id":"https://openalex.org/subfields/1911","display_name":"Paleontology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10955","display_name":"Paleontology and Evolutionary Biology","score":0.7968999743461609,"subfield":{"id":"https://openalex.org/subfields/1911","display_name":"Paleontology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11144","display_name":"melanin and skin pigmentation","score":0.0877000018954277,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11354","display_name":"Evolution and Paleontology Studies","score":0.019200000911951065,"subfield":{"id":"https://openalex.org/subfields/1911","display_name":"Paleontology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/melanosomes","display_name":"melanosomes","score":0.8309999704360962},{"id":"https://openalex.org/keywords/theropods","display_name":"theropod dinosaurs","score":0.7459999918937683},{"id":"https://openalex.org/keywords/psittacosaurus","display_name":"Psittacosaurus","score":0.8489999771118164},{"id":"https://openalex.org/keywords/diplodocus","display_name":"Diplodocus","score":0.9959999918937683},{"id":"https://openalex.org/keywords/minority-class-oversampling","display_name":"minority class oversampling","score":0.6710000038146973},{"id":"https://openalex.org/keywords/smote","display_name":"SMOTE","score":0.9330000281333923},{"id":"https://openalex.org/keywords/synthetic-minority-oversampling","display_name":"synthetic minority oversampling","score":0.546999990940094},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.4779999852180481},{"id":"https://openalex.org/keywords/machine-learning-bias","display_name":"machine learning bias","score":0.4410000145435333},{"id":"https://openalex.org/keywords/color-prediction","display_name":"color prediction","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8198000192642212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7092999815940857},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6442999839782715},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5807999968528748},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.5034000277519226},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46219998598098755},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C78397625","wikidata":"https://www.wikidata.org/wiki/Q192487","display_name":"Discriminant","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.3174999952316284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3091000020503998},{"id":"https://openalex.org/C52620605","wikidata":"https://www.wikidata.org/wiki/Q7268357","display_name":"Quadratic classifier","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.31233/osf.io/69js3_v1","doi":"https://doi.org/10.31233/osf.io/69js3_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31233/osf.io/69js3_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400732","display_name":"PaleoRxiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:share.osf.io:6096ff74-8673-451a-b591-64c6b845ed2e","doi":null,"is_oa":true,"landing_page_url":"https://osf.io/69js3","pdf_url":null,"source":{"id":"https://openalex.org/S4306400732","display_name":"PaleoRxiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.31233/osf.io/69js3_v1","doi":"https://doi.org/10.31233/osf.io/69js3_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31233/osf.io/69js3_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400732","display_name":"PaleoRxiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"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/W4380481463","https://openalex.org/W3096399826","https://openalex.org/W7118411592","https://openalex.org/W2491563781","https://openalex.org/W6960402843","https://openalex.org/W2106419115","https://openalex.org/W2899116136","https://openalex.org/W4412686868","https://openalex.org/W7080840337","https://openalex.org/W7126258625"],"abstract_inverted_index":{"Reconstructing":[0],"dinosaur":[1],"coloration":[2],"from":[3],"fossilized":[4],"melanosomes":[5],"has":[6],"revolutionized":[7],"paleontology,":[8],"but":[9,181],"most":[10],"predictive":[11],"models":[12,21,112],"are":[13,175,182],"trained":[14,35],"exclusively":[15],"on":[16,49,68],"modern":[17,51],"birds.":[18],"Whether":[19],"these":[20],"generalize":[22],"across":[23,185],"clade":[24,186],"boundaries":[25,187],"to":[26,102,114,151],"non-theropod":[27,104],"dinosaurs":[28],"remains":[29],"a":[30,95,131,160,196,209],"critical,":[31],"untested":[32],"question.":[33],"We":[34,194],"Quadratic":[36],"Discriminant":[37],"Analysis":[38],"(QDA),":[39],"Support":[40],"Vector":[41],"Machine":[42],"(SVM),":[43],"and":[44,63,65,85,107,119,125,143,204],"Random":[45],"Forest":[46],"(RF)":[47],"classifiers":[48,174],"342":[50],"bird":[52],"melanosome":[53],"measurements":[54],"spanning":[55],"five":[56],"color":[57,202],"categories":[58],"(black,":[59],"brown,":[60],"gray,":[61],"iridescent,":[62],"yellow)":[64],"validated":[66],"them":[67],"eight":[69],"theropod":[70],"fossils":[71],"with":[72,117,153],"known":[73],"coloration.":[74],"QDA":[75],"achieved":[76],"75%":[77],"validation":[78],"accuracy":[79],"(6/8":[80],"correct),":[81],"SVM":[82,118],"62.5%":[83],"(5/8),":[84],"RF":[86,120],"12.5%":[87],"(1/8)":[88],"this":[89],"reflects":[90],"the":[91,134,154,166],"destabilizing":[92],"effect":[93],"of":[94,213],"severely":[96],"under-sampled":[97],"minority":[98],"class.":[99],"When":[100],"applied":[101,192],"four":[103],"specimens":[105],"(Psittacosaurus":[106],"juvenile":[108],"Diplodocus),":[109],"all":[110],"three":[111,139],"collapsed":[113],"predicting":[115],"\"yellow\",":[116],"confidence":[121],"probabilities":[122],"between":[123],"0.46":[124],"0.70.":[126],"This":[127],"uniform":[128],"collapse":[129],"is":[130,191],"synthetic":[132],"artifact:":[133],"yellow":[135],"class":[136,156],"contained":[137],"only":[138,177],"original":[140],"training":[141],"samples,":[142],"Synthetic":[144],"Minority":[145],"Oversampling":[146],"Technique":[147],"(SMOTE)":[148],"inflated":[149],"it":[150],"parity":[152],"largest":[155],"(~173":[157],"samples),":[158],"creating":[159],"spurious":[161],"decision":[162],"region":[163],"that":[164,172],"intersects":[165],"fossil":[167],"morphospace.":[168],"Our":[169],"results":[170],"demonstrate":[171],"aspect-ratio-based":[173],"not":[176],"limited":[178],"within":[179],"theropods":[180],"actively":[183],"misleading":[184],"when":[188],"minority-class":[189,206],"oversampling":[190,207],"naively.":[193],"establish":[195],"cautionary,":[197],"reproducible":[198],"benchmark":[199],"for":[200],"deep-time":[201],"reconstruction":[203],"identify":[205],"as":[208],"previously":[210],"unrecognized":[211],"source":[212],"systematic":[214],"error":[215],"in":[216],"paleocolor":[217],"machine":[218],"learning.":[219]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-22T00:00:00"}
