{"id":"https://openalex.org/W7196988028","doi":"https://doi.org/10.48550/arxiv.2608.04567","title":"STRIVE: Probing Reasoning Limits in Graded Plausibility Generation and Evaluation","display_name":"STRIVE: Probing Reasoning Limits in Graded Plausibility Generation and Evaluation","publication_year":2026,"publication_date":"2026-08-05","ids":{"openalex":"https://openalex.org/W7196988028","doi":"https://doi.org/10.48550/arxiv.2608.04567"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.04567","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.04567","pdf_url":"https://arxiv.org/pdf/2608.04567","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2608.04567","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009879110","display_name":"Bhiman Kumar Baghel","orcid":"https://orcid.org/0000-0002-6439-5844","observed_orcids":["https://orcid.org/0000-0002-6439-5844"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baghel, Bhiman Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138874282","display_name":"Anna Chrabaszcz","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chrabaszcz, Anna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130388234","display_name":"Tessa Warren","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Warren, Tessa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087674777","display_name":"Michael Walsh Dickey","orcid":"https://orcid.org/0000-0002-9068-3313","observed_orcids":["https://orcid.org/0000-0002-9068-3313"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dickey, Michael Walsh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064229496","display_name":"Haley C. Dresang","orcid":"https://orcid.org/0000-0002-8085-2662","observed_orcids":["https://orcid.org/0000-0002-8085-2662"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dresang, Haley C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5146009392","display_name":"Xiang Lorraine Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiang Lorraine","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/T10181","display_name":"Natural Language Processing Techniques","score":0.38530001044273376,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.38530001044273376,"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/T10028","display_name":"Topic Modeling","score":0.22750000655651093,"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/T12694","display_name":"Categorization, perception, and language","score":0.1793999969959259,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/event-knowledge","display_name":"event knowledge","score":0.6010000109672546},{"id":"https://openalex.org/keywords/event-frames","display_name":"event frames","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.8137000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419999837875366},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5634999871253967},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3968000113964081},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2987896495","wikidata":"https://www.wikidata.org/wiki/Q5416716","display_name":"Event data","level":3,"score":0.2628999948501587},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.04567","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.04567","pdf_url":"https://arxiv.org/pdf/2608.04567","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.04567","doi":"https://doi.org/10.48550/arxiv.2608.04567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.04567","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.04567","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.04567","pdf_url":"https://arxiv.org/pdf/2608.04567","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.7189489006996155}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6910849093","https://openalex.org/W4385570607","https://openalex.org/W3155600250","https://openalex.org/W7126415460","https://openalex.org/W7138839459","https://openalex.org/W4389070894","https://openalex.org/W4403556315","https://openalex.org/W4401865497","https://openalex.org/W4404579415","https://openalex.org/W4409362528"],"abstract_inverted_index":{"Event":[0],"knowledge":[1,16],"concerns":[2],"who":[3],"does":[4],"what":[5],"to":[6,12,138,186],"whom.":[7],"Psycholinguists":[8],"use":[9],"event-plausibility":[10],"judgments":[11],"examine":[13],"how":[14],"this":[15,136],"supports":[17],"human":[18,160,178],"language":[19],"processing.":[20],"To":[21],"isolate":[22],"plausibility":[23,38,69,151],"effects,":[24],"these":[25],"studies":[26],"require":[27],"controlled":[28,65],"event":[29,34,43,66,88,93],"sets":[30,49,67,116],"in":[31],"which":[32],"one":[33,92,98],"slot":[35,99],"varies":[36],"across":[37,110],"levels":[39],"while":[40,100],"all":[41,102],"other":[42],"features":[44],"remain":[45,153],"fixed.":[46,104],"Constructing":[47],"such":[48],"manually":[50],"is":[51],"labor-intensive.":[52],"We":[53],"therefore":[54],"introduce":[55],"STRIVE,":[56],"an":[57],"LLM-based":[58],"framework":[59],"for":[60,177,197],"jointly":[61],"generating":[62],"and":[63,132,162,195],"evaluating":[64],"crossing":[68],"class":[70],"(plausible":[71],"vs.":[72,79],"implausible)":[73],"with":[74,107],"intended":[75],"classification":[76],"difficulty":[77],"(easy":[78],"hard).":[80],"Given":[81],"a":[82,86,128,175,183],"verb,":[83],"STRIVE":[84,181],"constructs":[85],"shared":[87],"frame,":[89],"then":[90],"produces":[91],"per":[94],"condition":[95],"by":[96,190],"varying":[97],"holding":[101],"others":[103],"In":[105],"experiments":[106],"six":[108],"models":[109],"60":[111],"verbs,":[112],"GPT-5.1":[113],"produced":[114],"high-quality":[115],"only":[117,167],"16.7%":[118],"of":[119],"the":[120,123,150,158,163,171],"time":[121],"using":[122],"baseline":[124],"generation":[125,194],"prompt.":[126],"Adding":[127],"global":[129],"reasoning":[130,141],"scratchpad":[131],"evaluator-guided":[133],"refinement":[134],"raised":[135],"rate":[137],"75.0%.":[139],"Greater":[140],"effort":[142,189],"also":[143],"improved":[144],"evaluator--human":[145],"agreement.":[146],"Nevertheless,":[147],"events":[148],"near":[149],"boundary":[152],"most":[154],"difficult.":[155],"They":[156],"elicit":[157],"greatest":[159],"disagreement,":[161],"best":[164],"evaluator":[165],"reaches":[166],"57%":[168],"accuracy":[169],"on":[170],"implausible-hard":[172],"condition,":[173],"indicating":[174],"need":[176],"input.":[179],"Overall,":[180],"offers":[182],"scalable":[184],"approach":[185],"reducing":[187],"manual":[188],"automating":[191],"initial":[192],"event-set":[193],"evaluation":[196],"psycholinguistic":[198],"studies.":[199]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-07T00:00:00"}