{"id":"https://openalex.org/W7208730883","doi":"https://doi.org/10.26434/chemrxiv.15008282/v1","title":"PXRD-Diff: diagnosing the encoder bottleneck in diffusion-based powder-diffraction structure inversion, with classical autoindexing as a drop-in remedy","display_name":"PXRD-Diff: diagnosing the encoder bottleneck in diffusion-based powder-diffraction structure inversion, with classical autoindexing as a drop-in remedy","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208730883","doi":"https://doi.org/10.26434/chemrxiv.15008282/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008282/v1","doi":"https://doi.org/10.26434/chemrxiv.15008282/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008282/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008282/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.15008282/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135027870","display_name":"Frank Cai","orcid":"https://orcid.org/0009-0003-0041-1459","observed_orcids":["https://orcid.org/0009-0003-0041-1459"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Frank Cai","raw_affiliation_strings":["Purdue University"],"raw_orcid":"https://orcid.org/0009-0003-0041-1459","affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5135027870"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"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":0.5170999765396118,"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":0.5170999765396118,"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":0.47920000553131104,"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/T10464","display_name":"Crystal structures of chemical compounds","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/powder-x-ray-diffraction","display_name":"X-ray powder diffraction","score":0.9089999794960022},{"id":"https://openalex.org/keywords/conditional-diffusion-models","display_name":"conditional diffusion models","score":0.7129999995231628},{"id":"https://openalex.org/keywords/crystal-structure-prediction","display_name":"crystal structure prediction","score":0.5889999866485596},{"id":"https://openalex.org/keywords/global-pooling","display_name":"global pooling","score":0.621999979019165},{"id":"https://openalex.org/keywords/bragg-peak-position","display_name":"Bragg peak position","score":0.6869999766349792},{"id":"https://openalex.org/keywords/conditional-variational-autoencoder","display_name":"conditional variational autoencoder","score":0.5929999947547913},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.3370000123977661}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6159999966621399},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5623999834060669},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5052000284194946},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C2781204021","wikidata":"https://www.wikidata.org/wiki/Q6497091","display_name":"Lattice (music)","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38519999384880066},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.31859999895095825},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C207114421","wikidata":"https://www.wikidata.org/wiki/Q133900","display_name":"Diffraction","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C206194317","wikidata":"https://www.wikidata.org/wiki/Q1138624","display_name":"Convex hull","level":3,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008282/v1","doi":"https://doi.org/10.26434/chemrxiv.15008282/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008282/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008282/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.15008282/v1","doi":"https://doi.org/10.26434/chemrxiv.15008282/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008282/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008282/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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208730883.pdf","grobid_xml":"https://content.openalex.org/works/W7208730883.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2036427959","https://openalex.org/W4402634311","https://openalex.org/W4406472463","https://openalex.org/W4407185785","https://openalex.org/W4407760863","https://openalex.org/W4417034743","https://openalex.org/W7140298902"],"related_works":["https://openalex.org/W7133324920","https://openalex.org/W7164812227","https://openalex.org/W7168171440","https://openalex.org/W7131820431","https://openalex.org/W4413106461","https://openalex.org/W7221818538","https://openalex.org/W4404104095","https://openalex.org/W7140280470","https://openalex.org/W4407185785","https://openalex.org/W7204207550"],"abstract_inverted_index":{"Inverting":[0],"a":[1,9,33,72,127,137,173,184,191,247],"one-dimensional":[2],"powder":[3],"X-ray":[4],"diffraction":[5],"(PXRD)":[6],"pattern":[7],"to":[8,142,180],"three-dimensional":[10],"crystal":[11],"structure":[12],"remains":[13],"an":[14],"open":[15],"problem,":[16],"and":[17,47,50,136,229,251,258],"recent":[18],"generative":[19],"approaches":[20],"report":[21],"results":[22],"under":[23],"mutually":[24],"incompatible":[25],"protocols":[26],"with":[27,172],"failure":[28,249],"modes":[29],"seldom":[30],"catalogued.":[31],"PXRD-Diff,":[32],"3.7":[34],"M-parameter":[35],"conditional":[36],"diffusion":[37],"model":[38],"trained":[39],"on":[40,218],"the":[41,55,67,87,111,120,160,168,197,210,214,241,244,252,259],"CDVAE":[42],"MP-20":[43],"split,":[44],"is":[45,65,110,199],"presented,":[46],"DiffractGPT,":[48],"PXRDnet":[49,230],"deCIFer":[51,221],"are":[52,240,263],"reproduced":[53],"through":[54],"same":[56],"pymatgen":[57],"StructureMatcher":[58],"harness.":[59],"The":[60,108,238],"central,":[61],"statistically":[62],"robust":[63],"finding":[64],"mechanistic:":[66],"learned":[68,169,185],"PXRD":[69],"encoder":[70],"reaches":[71,222],"0.007":[73],"normalised":[74],"auxiliary":[75],"lattice-regression":[76],"loss":[77],"in":[78,209],"isolation,":[79],"yet":[80],"substituting":[81],"that":[82,114,187],"head\u2019s":[83],"own":[84],"lattice":[85,170],"into":[86],"sampler":[88],"recovers":[89,188],"only":[90],"1.2":[91],"%":[92,144,152,164,182,224,228],"of":[93],"structures,":[94],"because":[95],"its":[96],"~1.1":[97],"\u00c5":[98,133],"length":[99],"error":[100],"shifts":[101],"every":[102],"Bragg":[103,261],"peak":[104,117],"by":[105],"~15":[106],"%.":[107],"limiter":[109],"global":[112],"pooling":[113],"discards":[115],"absolute":[116],"positions,":[118],"not":[119],"denoiser":[121],"alone.":[122],"A":[123],"perturbation":[124],"study":[125],"locates":[126],"sharp":[128],"sensitivity":[129,215],"knee":[130],"at":[131,145],"~0.5":[132],"cell":[134],"error,":[135],"true-lattice":[138],"oracle":[139],"lifts":[140],"match":[141,179],"4.5":[143],"n":[146],"=":[147],"1000":[148],"(three":[149],"seeds;":[150],"95":[151],"Wilson":[153],"confidence":[154],"interval":[155],"[3.8,":[156],"5.3]),":[157],"disjoint":[158],"from":[159,183],"no-true-lattice":[161,178],"indexer\u2019s":[162],"1.5":[163,181],"[1.2,":[165],"2.0].":[166],"Replacing":[167],"head":[171,186],"classical":[174],"Q-space":[175],"autoindexer":[176],"raises":[177],"essentially":[189],"nothing;":[190],"three-seed":[192],"paired":[193],"McNemar":[194],"test":[195],"confirms":[196],"gain":[198],"significant":[200],"(p":[201],"<":[202],"10\u22124;":[203],"27":[204],"fixed,":[205],"none":[206],"broken),":[207],"concentrated":[208],"high-symmetry":[211],"systems":[212],"below":[213],"knee.":[216],"Reproduced":[217],"one":[219],"harness,":[220],"73.8":[223],"match,":[225],"DiffractGPT":[226],"18.9":[227],"30.0":[231],"%,":[232],"leaving":[233],"PXRD-Diff":[234],"12\u201346":[235],"times":[236],"behind.":[237],"contributions":[239],"encoder-bottleneck":[242],"diagnosis,":[243],"classical-indexer":[245],"drop-in,":[246],"four-item":[248],"catalogue":[250],"shared":[253],"evaluation":[254],"harness;":[255],"code,":[256],"checkpoints":[257],"differentiable":[260],"simulator":[262],"released.":[264]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-05T00:00:00"}