{"id":"https://openalex.org/W7202264535","doi":"https://doi.org/10.48550/arxiv.2608.10764","title":"FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding","display_name":"FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7202264535","doi":"https://doi.org/10.48550/arxiv.2608.10764"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.10764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10764","pdf_url":"https://arxiv.org/pdf/2608.10764","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.10764","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120307469","display_name":"Fufangchen Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Fufangchen","raw_affiliation_strings":["AMAP , Alibaba Group","State Key Laboratory of Networking and Switching Technology , BUPT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , BUPT","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078503620","display_name":"Jinhu Fu","orcid":"https://orcid.org/0000-0002-8484-9997","observed_orcids":["https://orcid.org/0000-0002-8484-9997"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu, Jinhu","raw_affiliation_strings":["AMAP , Alibaba Group","State Key Laboratory of Networking and Switching Technology , BUPT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , BUPT","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059032251","display_name":"Jiachen Lei","orcid":"https://orcid.org/0009-0003-1508-637X","observed_orcids":["https://orcid.org/0009-0003-1508-637X"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei, Jiachen","raw_affiliation_strings":["AMAP , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121160149","display_name":"Jiahong Wu","orcid":"https://orcid.org/0000-0001-8583-0414","observed_orcids":["https://orcid.org/0000-0001-8583-0414"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Jiahong","raw_affiliation_strings":["AMAP , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512474","display_name":"Xiangxiang Chu","orcid":"https://orcid.org/0000-0003-2548-0605","observed_orcids":["https://orcid.org/0000-0003-2548-0605"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu, Xiangxiang","raw_affiliation_strings":["AMAP , Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP , Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101573676","display_name":"Danfeng Yan","orcid":"https://orcid.org/0000-0002-6553-3444","observed_orcids":["https://orcid.org/0000-0002-6553-3444"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":"CN","type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Danfeng","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology , BUPT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology , BUPT","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0,"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":0.0,"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/counterfactual-thinking","display_name":"counterfactual reasoning","score":0.5540000200271606},{"id":"https://openalex.org/keywords/open-ended-question-answering","display_name":"open-ended question answering","score":0.7450000047683716},{"id":"https://openalex.org/keywords/video-captioning","display_name":"video captioning","score":0.8809999823570251},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"commonsense reasoning","score":0.6069999933242798}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9520000219345093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7578999996185303},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7107999920845032},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6162999868392944},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.5716999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5708000063896179},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5275999903678894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5198000073432922},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C101097943","wikidata":"https://www.wikidata.org/wiki/Q5176983","display_name":"Counterintuitive","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.4392000138759613},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C2776904630","wikidata":"https://www.wikidata.org/wiki/Q356336","display_name":"Adept","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.10764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10764","pdf_url":"https://arxiv.org/pdf/2608.10764","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.2608.10764","doi":"https://doi.org/10.48550/arxiv.2608.10764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.10764","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:2608.10764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10764","pdf_url":"https://arxiv.org/pdf/2608.10764","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202264535.pdf","grobid_xml":"https://content.openalex.org/works/W7202264535.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2789580031","https://openalex.org/W2975545243","https://openalex.org/W2978723076","https://openalex.org/W4327810158","https://openalex.org/W4391631327","https://openalex.org/W4403572874","https://openalex.org/W4404330874","https://openalex.org/W4409361147","https://openalex.org/W4416035957","https://openalex.org/W4416184586","https://openalex.org/W4416780398","https://openalex.org/W4417250113","https://openalex.org/W4417308744","https://openalex.org/W4417309012","https://openalex.org/W6910686112","https://openalex.org/W6948369276","https://openalex.org/W7077911270","https://openalex.org/W7087381673","https://openalex.org/W7106807532","https://openalex.org/W7119523234","https://openalex.org/W7120177137","https://openalex.org/W7147062200"],"related_works":["https://openalex.org/W7106807532","https://openalex.org/W4412888718","https://openalex.org/W7048617544","https://openalex.org/W4388444444","https://openalex.org/W7164049360","https://openalex.org/W7117969963","https://openalex.org/W4403770699","https://openalex.org/W4416258227","https://openalex.org/W4416771397","https://openalex.org/W7119705465"],"abstract_inverted_index":{"Counterfactual":[0],"video":[1,207],"understanding":[2],"evaluates":[3],"whether":[4],"models":[5],"grasp":[6],"physical":[7],"and":[8,24,51,94,120,151,165,177,185],"commonsense":[9],"regularities.":[10],"However,":[11],"existing":[12,110],"multiple-choice":[13],"question":[14,117],"(MCQ)":[15],"benchmarks":[16],"inadvertently":[17],"leak":[18],"target":[19],"events":[20],"through":[21],"their":[22],"questions":[23],"candidate":[25],"options.":[26],"This":[27],"reduces":[28],"the":[29,68,89,137,183],"core":[30],"challenge":[31],"from":[32,159],"active":[33],"discovery":[34,50],"to":[35,91,162],"text-guided":[36],"verification.":[37],"In":[38,155],"this":[39,100,192],"paper,":[40],"we":[41,76,102],"present":[42],"FADE,":[43],"an":[44,58,105],"effective":[45,106],"training":[46,61],"framework":[47,194],"for":[48,201],"counterfactual":[49,206],"explanation.":[52],"Our":[53,128],"method":[54],"is":[55,175],"built":[56],"on":[57,149,179],"evidence-first,":[59],"two-stage":[60],"paradigm.":[62],"First,":[63],"evidence-internalized":[64],"supervised":[65],"fine-tuning":[66],"grounds":[67],"model's":[69],"predictions":[70],"in":[71,204],"decisive":[72],"visual":[73],"anomalies.":[74],"Second,":[75],"apply":[77],"a":[78,198],"fading-anchor":[79],"reinforcement":[80],"learning":[81],"strategy":[82],"that":[83,108],"progressively":[84],"removes":[85],"textual":[86],"guidance,":[87],"compelling":[88],"model":[90,168],"independently":[92],"discover":[93],"explain":[95],"evidence.":[96],"To":[97],"rigorously":[98],"evaluate":[99],"capability,":[101],"also":[103],"introduce":[104],"pipeline":[107],"converts":[109],"MCQ":[111],"datasets":[112],"into":[113],"aligned":[114],"MCQ,":[115],"open-ended":[116],"answering":[118],"(OQA),":[119],"captioning":[121],"tasks":[122,148],"without":[123],"requiring":[124],"additional":[125],"data":[126],"curation.":[127],"simple":[129,193],"approach":[130],"yields":[131],"strong":[132],"results.":[133],"Using":[134],"Qwen3-VL-8B":[135],"as":[136,197],"baseline,":[138],"FADE":[139],"achieves":[140],"state-of-the-art":[141],"strict":[142],"paired":[143],"scores":[144],"across":[145],"all":[146],"three":[147],"DualityVidQA-test":[150],"IPV-Bench,":[152],"outperforming":[153],"GPT-5.6.":[154,189],"specific,":[156],"when":[157],"transitioning":[158],"constrained":[160],"MCQs":[161],"unconstrained":[163,205],"OQA":[164],"captioning,":[166],"our":[167],"demonstrates":[169],"remarkable":[170],"robustness.":[171],"Its":[172],"performance":[173],"retention":[174],"90.4%":[176],"67.4%":[178],"DualityVidQA-test-substantially":[180],"higher":[181],"than":[182],"48.1%":[184],"30.7%":[186],"retained":[187],"by":[188],"We":[190],"hope":[191],"can":[195],"serve":[196],"solid":[199],"baseline":[200],"future":[202],"research":[203],"understanding.":[208]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-13T00:00:00"}