{"id":"https://openalex.org/W7212445698","doi":"https://doi.org/10.26434/chemrxiv.15009099/v1","title":"When Is a Molecule a Duplicate? Identity Policy Determines What a Benchmark Audit Finds","display_name":"When Is a Molecule a Duplicate? Identity Policy Determines What a Benchmark Audit Finds","publication_year":2026,"publication_date":"2026-09-20","ids":{"openalex":"https://openalex.org/W7212445698","doi":"https://doi.org/10.26434/chemrxiv.15009099/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009099/v1","doi":"https://doi.org/10.26434/chemrxiv.15009099/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009099/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009099/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","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009099/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151584406","display_name":"Md. Rahul Reza Roktim","orcid":"https://orcid.org/0009-0003-6518-0495","observed_orcids":["https://orcid.org/0009-0003-6518-0495"]},"institutions":[{"id":"https://openalex.org/I200606013","display_name":"Daffodil International University","ror":"https://ror.org/052t4a858","country_code":"BD","type":"education","lineage":["https://openalex.org/I200606013"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Md. Rahul Reza Roktim","raw_affiliation_strings":["Daffodil International University","Department of Pharmacy"],"raw_orcid":"https://orcid.org/0009-0003-6518-0495","affiliations":[{"raw_affiliation_string":"Daffodil International University","institution_ids":["https://openalex.org/I200606013"]},{"raw_affiliation_string":"Department of Pharmacy","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5151584406"],"corresponding_institution_ids":["https://openalex.org/I200606013"],"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":0.9336000084877014,"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":0.9336000084877014,"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/T11719","display_name":"Data Quality and Management","score":0.031099999323487282,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.007699999958276749,"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/duplicate-records","display_name":"duplicate records","score":0.597000002861023},{"id":"https://openalex.org/keywords/molecular-identity","display_name":"molecular identity","score":0.8379999995231628},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.5239999890327454},{"id":"https://openalex.org/keywords/moleculenet","display_name":"MoleculeNet","score":0.9269999861717224},{"id":"https://openalex.org/keywords/inchikey","display_name":"InChIKey","score":0.7110000252723694},{"id":"https://openalex.org/keywords/domain-of-applicability","display_name":"domain of applicability","score":0.7250000238418579},{"id":"https://openalex.org/keywords/stereochemistry","display_name":"stereochemistry","score":0.5889999866485596},{"id":"https://openalex.org/keywords/machine-learning-benchmark","display_name":"machine learning benchmark","score":0.546999990940094},{"id":"https://openalex.org/keywords/data-quality-audit","display_name":"data quality audit","score":0.39399999380111694},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.767799973487854},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7139000296592712},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6942999958992004},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.424699991941452},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3952000141143799},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3483000099658966},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2700999975204468},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.26434/chemrxiv.15009099/v1","doi":"https://doi.org/10.26434/chemrxiv.15009099/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009099/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009099/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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"doi:10.5281/zenodo.22738114","doi":"https://doi.org/10.5281/zenodo.22738114","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22738114","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Software"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15009099/v1","doi":"https://doi.org/10.26434/chemrxiv.15009099/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009099/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009099/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","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212445698.pdf","grobid_xml":"https://content.openalex.org/works/W7212445698.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W2008505552","https://openalex.org/W2076498053","https://openalex.org/W2169678694","https://openalex.org/W2406943157","https://openalex.org/W2461470610","https://openalex.org/W2461620095","https://openalex.org/W2594183968","https://openalex.org/W2909063104","https://openalex.org/W3082081167","https://openalex.org/W4388455891","https://openalex.org/W7170036715"],"related_works":["https://openalex.org/W7220651318","https://openalex.org/W7170036715","https://openalex.org/W2181696534","https://openalex.org/W7171779720","https://openalex.org/W7167617122","https://openalex.org/W4411532053","https://openalex.org/W2122709242","https://openalex.org/W7162396506","https://openalex.org/W2620259134","https://openalex.org/W7214994452"],"abstract_inverted_index":{"Reports":[0],"of":[1,15,27,31,95],"duplicate":[2,22,119,131],"or":[3],"redundant":[4],"records":[5],"in":[6,103,215],"molecular":[7,32,64],"machine-learning":[8],"benchmarks":[9,54],"are":[10,19],"routinely":[11],"presented":[12],"as":[13,78,126,169,225],"properties":[14],"the":[16,25,46,75,101,109,116,134,147,170,222,237],"datasets.":[17],"They":[18],"not.":[20],"A":[21,150],"count":[23,233],"is":[24,139],"output":[26],"an":[28,79,206,226,240],"operational":[29],"definition":[30],"identity":[33,60,89,138,223],"applied":[34],"to":[35,114],"a":[36,58,84,92,197],"dataset,":[37],"and":[38,70,86,106,160,183,246],"different":[39,43,198],"defensible":[40],"definitions":[41],"return":[42],"answers":[44],"from":[45,180,201],"same":[47],"file.":[48],"We":[49,220],"audited":[50],"seven":[51],"MoleculeNet":[52],"[3]":[53],"(52,144":[55],"records)":[56,195],"under":[57,205],"four-level":[59],"hierarchy":[61],"\u2014":[62,73],"canonical":[63],"graph,":[65],"fragment":[66],"parent,":[67],"charge-normalised":[68],"parent":[69,72],"tautomer-normalised":[71,135],"with":[74,87,100],"Standard":[76],"InChIKey":[77],"orthogonal":[80],"comparator":[81],"rather":[82,248],"than":[83,249],"rung,":[85],"derived":[88],"withheld":[90],"outside":[91],"declared":[93,148],"domain":[94,157],"applicability.":[96],"Duplicate-group":[97],"counts":[98],"moved":[99],"level":[102,136],"every":[104,142,231],"benchmark,":[105],"for":[107,141],"three":[108],"audit":[110,241],"changed":[111],"its":[112],"answer":[113],"whether":[115],"benchmark":[117],"contains":[118],"compounds":[120],"at":[121,133],"all.":[122],"Domain":[123],"choice":[124],"mattered":[125],"much:":[127],"HIV":[128],"reports":[129],"330":[130],"groups":[132],"when":[137],"asserted":[140],"record,":[143],"against":[144],"124":[145,168],"on":[146],"domain.":[149],"post":[151],"hoc":[152],"sensitivity":[153],"analysis":[154],"found":[155],"that":[156,188],"under-covered":[158],"main-group":[159],"f-block":[161],"metal-associated":[162],"structures,":[163],"giving":[164],"109":[165],"without":[166],"displacing":[167],"prespecified":[171],"result.":[172],"Of":[173],"295":[174],"merge":[175],"events,":[176],"179":[177],"were":[178,185],"decidable":[179],"structure":[181],"alone":[182],"116":[184],"policy-dependent;":[186],"across":[187],"complete":[189],"census,":[190],"19":[191,214],"events":[192],"(16.4%;":[193],"41":[194],"received":[196],"benchmark-equivalence":[199],"decision":[200],"transition-appropriate":[202],"official-InChI":[203],"arbitration":[204],"endpoint":[207],"rulebook":[208],"fixed":[209],"before":[210],"final":[211],"classification,":[212],"all":[213],"one":[216],"benchmark's":[217],"stereochemical":[218],"subset.":[219],"publish":[221],"policy":[224],"executable,":[227],"fingerprinted":[228],"contract":[229],"reproducing":[230],"reported":[232],"exactly":[234],"(434/434),":[235],"so":[236],"assumptions":[238],"behind":[239],"statistic":[242],"can":[243],"be":[244],"inspected":[245],"re-executed":[247],"inferred.":[250]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-14T00:00:00"}
