{"id":"https://openalex.org/W7171868912","doi":"https://doi.org/10.48550/arxiv.2607.27066","title":"SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence","display_name":"SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence","publication_year":2026,"publication_date":"2026-07-29","ids":{"openalex":"https://openalex.org/W7171868912","doi":"https://doi.org/10.48550/arxiv.2607.27066"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.27066","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27066","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.27066","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144031948","display_name":"Chuanzhi Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chuanzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144086163","display_name":"Zihan Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Zihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144021881","display_name":"Huiqi Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Huiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144043156","display_name":"Chengkun Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Chengkun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144024000","display_name":"Zhanlin Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Zhanlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067576518","display_name":"Pengfei Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143993516","display_name":"Weidong Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Weidong","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":0.8572999835014343,"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":0.8572999835014343,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.020400000736117363,"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":0.019700000062584877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6624000072479248},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5491999983787537},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5358999967575073},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4043999910354614},{"id":"https://openalex.org/keywords/quality-assessment","display_name":"Quality assessment","score":0.39309999346733093},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.37779998779296875},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3686999976634979},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.33309999108314514}],"concepts":[{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6624000072479248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5655999779701233},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5491999983787537},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40119999647140503},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.39309999346733093},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C124056412","wikidata":"https://www.wikidata.org/wiki/Q3320364","display_name":"Scientific evidence","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.27066","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27066","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.27066","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27066","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,"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"},"sustainable_development_goals":[{"score":0.6738741993904114,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"figure":[1,14,42,60,85,133,141,226],"assessment":[2,38,135,227],"in":[3,136],"peer":[4],"review":[5],"differs":[6],"fundamentally":[7],"from":[8,109],"general":[9],"image":[10,37],"quality":[11,43,52,134],"evaluation:":[12],"a":[13,28,59,127,140,167,177,183,197],"must":[15],"be":[16],"visually":[17],"legible,":[18],"faithfully":[19],"support":[20],"the":[21,62,190,203],"manuscript's":[22],"claims,":[23],"and":[24,78,97,122,146,153,159,182,217,234],"communicate":[25],"evidence":[26,236],"with":[27,92,156,166,193,207,242],"clear":[29],"visual":[30,96,232],"hierarchy.":[31],"However,":[32],"if":[33],"we":[34],"apply":[35],"traditional":[36],"methods":[39,67],"to":[40],"scientific":[41,64,107,225],"assessment,":[44],"limitations":[45],"emerge:":[46],"classic":[47],"IQA":[48],"models":[49],"capture":[50],"perceptual":[51],"or":[53],"aesthetics":[54],"but":[55],"cannot":[56],"judge":[57],"whether":[58],"serves":[61],"paper's":[63],"argument;":[65],"CLIP-based":[66],"assess":[68],"generic":[69],"image-text":[70],"correspondence,":[71],"yet":[72],"lack":[73],"understanding":[74],"of":[75,95,105,180,187],"manuscript":[76,137,235],"context;":[77],"zero-shot":[79],"LLM/VLM":[80],"judges,":[81],"when":[82],"repurposed":[83],"for":[84],"scoring,":[86],"often":[87],"yield":[88],"overly":[89],"concentrated":[90],"scores":[91],"limited":[93],"fusion":[94],"textual":[98],"evidence.":[99,138],"We":[100,124],"introduce":[101],"an":[102],"annotated":[103],"dataset":[104],"3,857":[106],"figures":[108],"peer-reviewed":[110],"conference":[111],"papers,":[112],"each":[113],"rated":[114],"along":[115],"four":[116],"peer-review-oriented":[117],"dimensions:":[118],"Clarity,":[119],"Relevance,":[120],"Informativeness,":[121],"Structure.":[123],"propose":[125],"SciFigAlign,":[126],"fine-tuned":[128],"multimodal":[129],"scorer":[130],"that":[131,212,224],"grounds":[132],"Given":[139],"crop,":[142],"caption,":[143],"citing":[144],"paragraphs,":[145],"light":[147],"paper":[148],"context,":[149],"SciFigAlign":[150,175],"fine-tunes":[151],"CLIP":[152],"SciBERT":[154],"end-to-end":[155],"per-modality":[157],"cross-attention":[158],"CubeMLP":[160],"fusion,":[161],"jointly":[162],"optimizing":[163],"SmoothL1":[164],"regression":[165],"within-paper":[168,184],"ranking":[169,218],"hinge":[170],"loss.":[171],"Under":[172],"paper-level":[173],"splits,":[174],"achieves":[176],"macro":[178],"MAE":[179,208],"0.3524":[181],"pairwise":[185],"accuracy":[186],"81.64%":[188],"on":[189],"test":[191],"set":[192],"n":[194],"=":[195],"396,":[196],"59%":[198],"relative":[199],"error":[200],"reduction":[201],"over":[202],"best":[204],"LLM-as-judge":[205],"baseline":[206],"0.864.":[209],"Ablations":[210],"confirm":[211],"manuscript-grounded":[213],"inputs,":[214],"citing-context":[215],"denoising,":[216],"supervision":[219],"are":[220],"all":[221],"critical,":[222],"showing":[223],"requires":[228],"learned":[229],"alignment":[230],"between":[231],"content":[233],"rather":[237],"than":[238],"prompting":[239],"alone,":[240],"even":[241],"state-of-the-art":[243],"VLMs.":[244]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2026-07-31T00:00:00"}