{"id":"https://openalex.org/W7163698676","doi":"https://doi.org/10.48550/arxiv.2606.05966","title":"Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs","display_name":"Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163698676","doi":"https://doi.org/10.48550/arxiv.2606.05966"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.05966","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05966","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.05966","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137934419","display_name":"Tianyi Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010951535","display_name":"Zhuoyi Lin","orcid":"https://orcid.org/0000-0003-4942-160X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zhuoyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138015301","display_name":"Zeyu Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137996879","display_name":"Tianyi Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137964054","display_name":"Yew-Soon Ong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ong, Yew-Soon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138009749","display_name":"Ivor Tsang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsang, Ivor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137981320","display_name":"Haiyan Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Haiyan","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":0.6193000078201294,"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":0.6193000078201294,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15880000591278076,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10656","display_name":"Child and Animal Learning Development","score":0.027799999341368675,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.902999997138977},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.6367999911308289},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.548799991607666},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.46630001068115234},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.3986999988555908},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39800000190734863},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.3294999897480011}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.902999997138977},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.6367999911308289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5978999733924866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698000192642212},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C116860108","wikidata":"https://www.wikidata.org/wiki/Q5054575","display_name":"Causal theory of reference","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.05966","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05966","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.05966","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05966","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"and":[1,45,54,71,104,131,167,179],"reasoning":[2,93,111,153,165],"about":[3],"the":[4,8,96,133],"physical":[5,22,194],"world":[6],"is":[7,59],"foundation":[9,186],"of":[10,39,74,108,121],"intelligent":[11],"behavior,":[12],"yet":[13],"state-of-the-art":[14],"vision-language":[15],"models":[16],"(VLMs)":[17],"still":[18],"fail":[19],"at":[20],"causal":[21,64,75,98,110,129,155,177],"reasoning,":[23],"often":[24],"producing":[25],"plausible":[26],"but":[27],"incorrect":[28],"answers.":[29],"To":[30,138],"address":[31,139],"this":[32,114],"gap,":[33],"we":[34,80,116,142],"introduce":[35],"CausalPhys,":[36],"a":[37,82,90,118,184],"benchmark":[38],"over":[40],"3,000":[41],"carefully":[42],"curated":[43],"video-":[44],"image-based":[46],"questions":[47],"spanning":[48],"four":[49],"domains:":[50],"Perception,":[51],"Anticipation,":[52],"Intervention,":[53],"Goal":[55],"Orientation.":[56],"Each":[57],"question":[58],"paired":[60],"with":[61,95,154],"an":[62],"expert-annotated":[63],"graph":[65],"capturing":[66,128],"object-attribute-event":[67],"dependencies,":[68],"enabling":[69,105],"interpretable":[70],"fine-grained":[72],"evaluation":[73],"understanding.":[76],"Building":[77],"on":[78],"this,":[79],"formulate":[81],"causal-graph-grounded":[83],"metric":[84],"that":[85,160],"quantitatively":[86],"measures":[87],"how":[88],"well":[89],"model's":[91],"chain-of-thought":[92],"aligns":[94,151],"correct":[97],"relations,":[99],"moving":[100],"beyond":[101],"answer-only":[102],"accuracy":[103,166],"systematic":[106,125],"diagnosis":[107],"VLMs'":[109],"failures.":[112],"Using":[113],"metric,":[115],"conduct":[117],"comprehensive":[119],"analysis":[120],"leading":[122],"VLMs,":[123],"revealing":[124],"gaps":[126],"in":[127],"dependencies":[130],"underscoring":[132],"need":[134],"for":[135,187],"causality-aware":[136],"learning.":[137],"these":[140],"limitations,":[141],"further":[143],"propose":[144],"Causal":[145],"Rationale-informed":[146],"Fine-Tuning":[147],"(CRFT),":[148],"which":[149],"explicitly":[150],"VLM":[152],"structures.":[156],"Extensive":[157],"experiments":[158],"demonstrate":[159],"CRFT":[161],"substantially":[162],"enhances":[163],"both":[164],"interpretability":[168],"across":[169],"multiple":[170],"model":[171],"backbones.":[172],"By":[173],"unifying":[174],"dataset":[175],"curation,":[176],"evaluation,":[178],"causality-informed":[180],"learning,":[181],"CausalPhys":[182],"establishes":[183],"strong":[185],"advancing":[188],"modern":[189],"VLMs":[190],"toward":[191],"causally":[192],"grounded":[193],"reasoning.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-06T00:00:00"}