{"id":"https://openalex.org/W7214938314","doi":"https://doi.org/10.26434/chemrxiv.15009668/v1","title":"RealBind: a leakage-controlled benchmark for experimental PXRD and Raman structure retrieval","display_name":"RealBind: a leakage-controlled benchmark for experimental PXRD and Raman structure retrieval","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214938314","doi":"https://doi.org/10.26434/chemrxiv.15009668/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15009668/v1","doi":"https://doi.org/10.26434/chemrxiv.15009668/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009668/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009668/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":"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://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009668/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153578967","display_name":"Preyansh Srivastava","orcid":"https://orcid.org/0009-0004-5229-9320","observed_orcids":["https://orcid.org/0009-0004-5229-9320"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Preyansh Srivastava","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0004-5229-9320","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5153578967"],"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/T11948","display_name":"Machine Learning in Materials Science","score":0.7871000170707703,"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":0.7871000170707703,"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/T12613","display_name":"X-ray Diffraction in Crystallography","score":0.2003999948501587,"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":0.0010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/powder-x-ray-diffraction","display_name":"X-ray powder diffraction","score":0.9210000038146973},{"id":"https://openalex.org/keywords/raman-spectra","display_name":"Raman spectra","score":0.9049999713897705},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5799999833106995},{"id":"https://openalex.org/keywords/leakage-control","display_name":"leakage control","score":0.6890000104904175},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.5339999794960022},{"id":"https://openalex.org/keywords/mineral-spectra","display_name":"mineral spectra","score":0.5180000066757202}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6693999767303467},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5837000012397766},{"id":"https://openalex.org/C40003534","wikidata":"https://www.wikidata.org/wiki/Q862228","display_name":"Raman spectroscopy","level":2,"score":0.58160001039505},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C185039092","wikidata":"https://www.wikidata.org/wiki/Q376044","display_name":"Powder diffraction","level":2,"score":0.49939998984336853},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.4050999879837036},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3878999948501587},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C207114421","wikidata":"https://www.wikidata.org/wiki/Q133900","display_name":"Diffraction","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32899999618530273},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C169573571","wikidata":"https://www.wikidata.org/wiki/Q466824","display_name":"Raman scattering","level":3,"score":0.32499998807907104},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C113196181","wikidata":"https://www.wikidata.org/wiki/Q485223","display_name":"Analytical Chemistry (journal)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.25110000371932983},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15009668/v1","doi":"https://doi.org/10.26434/chemrxiv.15009668/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009668/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009668/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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15009668/v1","doi":"https://doi.org/10.26434/chemrxiv.15009668/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15009668/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15009668/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":"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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214938314.pdf","grobid_xml":"https://content.openalex.org/works/W7214938314.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W4407479096","https://openalex.org/W4411467589","https://openalex.org/W4414656358","https://openalex.org/W4416191329","https://openalex.org/W4416786980","https://openalex.org/W7160646963","https://openalex.org/W7160997105","https://openalex.org/W7164812227","https://openalex.org/W7167928097"],"related_works":["https://openalex.org/W7133324920","https://openalex.org/W7221818538","https://openalex.org/W7164812227","https://openalex.org/W4402634311","https://openalex.org/W4414656358","https://openalex.org/W4403051164","https://openalex.org/W4406080844","https://openalex.org/W7162765823","https://openalex.org/W7163384766","https://openalex.org/W4412174138"],"abstract_inverted_index":{"We":[0,44],"present":[1],"RealBind,":[2],"a":[3,68,72,125,135,200],"benchmark":[4],"for":[5,238],"retrieving":[6],"crystal":[7],"structures":[8,133],"from":[9,191],"experimental":[10,34,235],"powder":[11],"X-ray":[12],"diffraction":[13],"(PXRD)":[14],"and":[15,32,49,52,59,112,155,163,171,220],"Raman":[16,35],"spectra.":[17],"It":[18],"contains":[19],"3,288":[20],"curated":[21],"candidate":[22,102,169],"structures,":[23],"of":[24,37,130,179,196],"which":[25,38,227],"1,468":[26],"have":[27,134,199],"linked":[28,41],"measured":[29,88],"PXRD":[30,78],"patterns,":[31,103],"16,005":[33],"spectra,":[36],"10,547":[39],"are":[40],"to":[42,95,193],"structures.":[43,231],"provide":[45],"quality-control":[46],"records,":[47],"prototype-held-out":[48,70,150],"composition-held-out":[50],"splits,":[51],"evaluation":[53,219],"protocols":[54],"that":[55,144],"state":[56],"candidate-library":[57],"size":[58],"the":[60,108,113,120,149,160,168,175,180,217,223],"chemical":[61],"information":[62],"available":[63],"at":[64],"retrieval":[65],"time.":[66],"On":[67],"492-candidate":[69],"library,":[71,226],"contrastive":[73],"model":[74,162],"trained":[75,161],"on":[76,82,87,119,143,148,209,222],"simulated":[77,83,101],"reaches":[79,206],"78.5%":[80],"Recall@10":[81,94,118,140,190,208],"queries":[84,165,198],"but":[85],"5.3%":[86],"queries;":[89],"physics-inspired":[90],"corruption":[91],"raises":[92,189],"measured-query":[93,139],"34.4%.":[96],"A":[97,203],"model-free":[98],"correlation":[99],"against":[100,213],"with":[104,242],"no":[105,229],"preprocessing":[106],"beyond":[107],"common":[109],"Q-grid":[110],"resampling":[111],"measuredwindow":[114],"mask,":[115],"achieves":[116],"82.8%":[117],"same":[121],"test":[122,132,153,236],"library.":[123],"In":[124],"separate":[126],"split":[127,145],"comparison,":[128],"44%":[129],"random-split":[131],"structure-matched":[136],"training":[137],"counterpart;":[138],"is":[141],"59.1%":[142],"versus":[146],"20.7%":[147],"split,":[151],"although":[152],"populations":[154],"libraries":[156],"also":[157],"differ.":[158],"Holding":[159],"420":[164],"fixed,":[166],"restricting":[167],"library":[170],"pre-screening":[172],"candidates":[173,215],"by":[174],"ground-truth":[176],"element":[177],"set":[178],"query\u2019s":[181],"structure,":[182],"used":[183],"as":[184],"an":[185,234],"oracle":[186],"chemistry-conditioned":[187],"diagnostic,":[188],"27.1%":[192],"99.1%;":[194],"37.6%":[195],"filtered":[197],"single":[201],"candidate.":[202],"Raman-to-structure":[204],"baseline":[205],"34.7%":[207],"heldout":[210],"mineral":[211],"spectra":[212],"979":[214],"in":[216],"pooled":[218],"45.7%":[221],"485-candidate":[224],"test-only":[225],"includes":[228],"validation":[230],"RealBind":[232],"provides":[233],"bed":[237],"comparing":[239],"learned":[240],"methods":[241],"simple":[243],"simulation-based":[244],"matching":[245],"under":[246],"explicit,":[247],"leakage-aware":[248],"protocols.":[249]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-01T00:00:00"}