{"id":"https://openalex.org/W7203498486","doi":"https://doi.org/10.48550/arxiv.2608.13112","title":"Towards Physics-Faithful Generation of Scientific Diagrams","display_name":"Towards Physics-Faithful Generation of Scientific Diagrams","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203498486","doi":"https://doi.org/10.48550/arxiv.2608.13112"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.13112","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13112","pdf_url":"https://arxiv.org/pdf/2608.13112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.13112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127893217","display_name":"Minghui Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Minghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139709676","display_name":"Jinxin Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Jinxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010151006","display_name":"Yifan Chang","orcid":"https://orcid.org/0000-0003-2820-0840","observed_orcids":["https://orcid.org/0000-0003-2820-0840"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122344811","display_name":"Liangliang Zhao","orcid":"https://orcid.org/0009-0004-8994-4303","observed_orcids":["https://orcid.org/0009-0004-8994-4303"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Liangliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113380881","display_name":"Yuandong Pu","orcid":"https://orcid.org/0000-0003-3764-0370","observed_orcids":["https://orcid.org/0000-0003-3764-0370"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pu, Yuandong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133716607","display_name":"Qian Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147184491","display_name":"Ming Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128789880","display_name":"Hanxiao Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hanxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127968425","display_name":"Yun Gu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132727025","display_name":"Yirong Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yirong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151839941","display_name":"Yu Qiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770109","display_name":"Bo Zhang","orcid":"https://orcid.org/0000-0001-8052-782X","observed_orcids":["https://orcid.org/0000-0001-8052-782X","https://orcid.org/0000-0002-9795-4673","https://orcid.org/0009-0002-0171-4905","https://orcid.org/0009-0005-3354-8018"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008886708","display_name":"Xiangchao Yan","orcid":"https://orcid.org/0009-0006-6644-0211","observed_orcids":["https://orcid.org/0009-0006-6644-0211"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xiangchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121234725","display_name":"Bin Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122987735","display_name":"Yihao Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yihao","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6640999913215637,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6640999913215637,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3303000032901764,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.8880000114440918},{"id":"https://openalex.org/keywords/physics-diagrams","display_name":"physics diagrams","score":0.5329999923706055},{"id":"https://openalex.org/keywords/chain-of-thought-prompting","display_name":"chain-of-thought prompting","score":0.8080000281333923},{"id":"https://openalex.org/keywords/structured-supervision","display_name":"structured supervision","score":0.5839999914169312},{"id":"https://openalex.org/keywords/multimodal-models","display_name":"multimodal models","score":0.6909999847412109},{"id":"https://openalex.org/keywords/physics-education","display_name":"physics education","score":0.5009999871253967}],"concepts":[{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5952000021934509},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5077000260353088},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.43720000982284546},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C194583477","wikidata":"https://www.wikidata.org/wiki/Q408891","display_name":"Physical law","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36559998989105225},{"id":"https://openalex.org/C6314898","wikidata":"https://www.wikidata.org/wiki/Q14632398","display_name":"Physical science","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C186399060","wikidata":"https://www.wikidata.org/wiki/Q959962","display_name":"Diagram","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29499998688697815},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2639000117778778},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C153185123","wikidata":"https://www.wikidata.org/wiki/Q1391624","display_name":"Sequence diagram","level":4,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.13112","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13112","pdf_url":"https://arxiv.org/pdf/2608.13112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.13112","doi":"https://doi.org/10.48550/arxiv.2608.13112","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.13112","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.13112","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13112","pdf_url":"https://arxiv.org/pdf/2608.13112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7163070210","https://openalex.org/W7166885304","https://openalex.org/W7169873252","https://openalex.org/W7166641753","https://openalex.org/W4404781666","https://openalex.org/W7130589636","https://openalex.org/W7162682709","https://openalex.org/W4415537217","https://openalex.org/W4387804034","https://openalex.org/W4416037874"],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1],"has":[2],"reached":[3],"photorealistic":[4],"quality,":[5],"yet":[6],"state-of-the-art":[7],"systems":[8],"remain":[9],"unreliable":[10],"at":[11,148],"producing":[12],"scientific":[13,63,244],"diagrams,":[14],"whose":[15,182],"value":[16],"depends":[17],"not":[18],"on":[19,22,41,230],"appearance":[20],"but":[21,55],"physical":[23,216,240],"faithfulness:":[24],"correct":[25],"force":[26,105],"directions,":[27],"valid":[28],"coordinate":[29],"systems,":[30],"consistent":[31],"thermodynamic":[32],"states,":[33,207],"and":[34,62,72,112,135,159,172,206,229],"equations":[35],"matching":[36],"the":[37,224,239],"depicted":[38],"scenario.":[39],"Trained":[40],"web":[42],"imagery":[43],"with":[44,122],"physically":[45,57,132],"shallow":[46],"captions,":[47],"generic":[48],"models":[49],"produce":[50],"diagrams":[51],"that":[52,87,126,234],"look":[53],"plausible":[54],"are":[56,184],"wrong,":[58],"harmful":[59],"in":[60],"education":[61],"communication.":[64],"We":[65,178],"present":[66],"Princigram,":[67],"a":[68,84,89,119,151,174,209],"physics-faithful":[69],"scientific-diagram":[70],"generator,":[71],"its":[73,203],"data":[74],"pipeline.":[75],"Our":[76],"central":[77],"advance":[78],"is":[79],"Structured":[80],"Physical":[81],"Chain-of-Thought":[82],"(SP-CoT):":[83],"per-subdiscipline":[85],"schema":[86,121],"decomposes":[88,213],"physics":[90,164,225],"diagram":[91,194],"into":[92,214],"an":[93,196],"explicit":[94,235],"multi-step":[95],"reasoning":[96,134],"chain":[97],"across":[98],"six":[99],"subdisciplines,":[100],"from":[101,131,186],"scene":[102],"identification":[103],"through":[104],"or":[106],"process":[107],"analysis":[108],"to":[109],"governing":[110],"laws":[111],"synthesis.":[113],"Unlike":[114],"free-form":[115],"chain-of-thought,":[116],"SP-CoT":[117],"follows":[118],"fixed":[120],"strict":[123],"fidelity":[124],"rules":[125],"separate":[127],"visually":[128],"grounded":[129],"facts":[130,217],"inferred":[133],"type":[136],"all":[137],"mathematics":[138],"symbolically;":[139],"it":[140,156],"serves":[141],"both":[142],"as":[143,150],"dense":[144],"training":[145],"supervision":[146,237],"and,":[147],"inference,":[149],"structured":[152,191],"\"thinking\"":[153],"prompt.":[154],"With":[155],"we":[157],"curate":[158],"structurally":[160],"annotate":[161],"4.3":[162],"million":[163],"images,":[165],"of":[166,199,227,242],"which":[167],"115,037":[168],"carry":[169],"expert-level":[170],"annotation,":[171],"adapt":[173],"unified":[175],"multimodal":[176],"backbone.":[177],"further":[179],"introduce":[180],"VeriphyT2IBench,":[181,231],"questions":[183,201],"derived":[185],"each":[187,193],"held-out":[188],"diagram's":[189],"own":[190],"annotation:":[192],"becomes":[195],"item-specific":[197],"bank":[198],"binary":[200],"about":[202],"objects,":[204],"forces,":[205],"so":[208],"judge":[210],"model's":[211],"score":[212],"named":[215],"rather":[218],"than":[219],"one":[220],"holistic":[221],"number.":[222],"On":[223],"subset":[226],"GenExam":[228],"Princigram":[232],"shows":[233],"physics-structured":[236],"improves":[238],"faithfulness":[241],"generated":[243],"diagrams.":[245]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-15T00:00:00"}