{"id":"https://openalex.org/W7224089476","doi":"https://doi.org/10.5281/zenodo.23749316","title":"A Ceiling Score Is Not a Physical Inference: Why Pretrained Video Encoders Look Physically Competent on One Benchmark and Near Chance on Its Successor, What a Clean Scene Lets a Readout Read Off, and the Rankability Checks a Physics Evaluation Owes","display_name":"A Ceiling Score Is Not a Physical Inference: Why Pretrained Video Encoders Look Physically Competent on One Benchmark and Near Chance on Its Successor, What a Clean Scene Lets a Readout Read Off, and the Rankability Checks a Physics Evaluation Owes","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224089476","doi":"https://doi.org/10.5281/zenodo.23749316"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23749316","doi":"https://doi.org/10.5281/zenodo.23749316","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23749316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23749316","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147720734","display_name":"Pranay M. Mahendrakar","orcid":"https://orcid.org/0009-0003-7224-029X","observed_orcids":["https://orcid.org/0009-0003-7224-029X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mahendrakar, Pranay","raw_affiliation_strings":["SONYTECH"],"raw_orcid":"https://orcid.org/0009-0003-7224-029X","affiliations":[{"raw_affiliation_string":"SONYTECH","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5147720734"],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16590000689029694,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16590000689029694,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10530000180006027,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.07840000092983246,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.5870000123977661},{"id":"https://openalex.org/keywords/caliper","display_name":"caliper","score":0.6190000176429749},{"id":"https://openalex.org/keywords/linear-readout","display_name":"linear readout","score":0.40700000524520874},{"id":"https://openalex.org/keywords/model-ranking","display_name":"model ranking","score":0.35100001096725464}],"concepts":[{"id":"https://openalex.org/C2777489069","wikidata":"https://www.wikidata.org/wiki/Q1589822","display_name":"Ceiling (cloud)","level":2,"score":0.6650000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492999792098999},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5442000031471252},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.5041000247001648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3928999900817871},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.387800008058548},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C191290158","wikidata":"https://www.wikidata.org/wiki/Q14773596","display_name":"Ceiling effect","level":3,"score":0.3154999911785126},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C173633133","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw score","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25380000472068787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25130000710487366}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23749316","doi":"https://doi.org/10.5281/zenodo.23749316","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23749316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23749317","doi":"https://doi.org/10.5281/zenodo.23749317","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23749317","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"doi:10.5281/zenodo.23749316","doi":"https://doi.org/10.5281/zenodo.23749316","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23749316","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"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/W7212005859","https://openalex.org/W7164052345","https://openalex.org/W7128484902","https://openalex.org/W7023850468","https://openalex.org/W4386247688","https://openalex.org/W4417438290","https://openalex.org/W7223709464","https://openalex.org/W7090911099","https://openalex.org/W7125516733","https://openalex.org/W4407719570"],"abstract_inverted_index":{"(c)":[0],"2026":[1,132],"Pranay":[2],"Mahendrakar.":[3],"Licensed":[4],"under":[5],"CC":[6],"BY":[7],"4.0.":[8],"Life":[9],"of":[10,25,34,127,156],"Research":[11],"Pretrained":[12],"video":[13,73],"and":[14,47,55,93,113,148,166,168,176,185,230,252,261,344],"image":[15],"encoders":[16],"are":[17,37,263],"now":[18],"chosen":[19],"as":[20,53,341],"the":[21,32,85,104,157,182,208,213,225,232,244,247,254,259,274,290,308,320,330],"perception":[22],"front":[23],"end":[24],"world":[26],"models":[27,236],"for":[28,50],"manipulation":[29],"partly":[30],"on":[31,84,110,159,243,295,333],"strength":[33],"evaluations":[35],"that":[36,66,95,135,162,191,207,215,224,231,348],"said":[38],"to":[39,70,189],"measure":[40],"physical":[41],"understanding:":[42],"violation-of-expectation":[43,335],"benchmarks,":[44],"outcome-prediction":[45],"tasks,":[46],"linear":[48,327],"probes":[49],"properties":[51,298],"such":[52],"mass":[54,165],"friction.":[56],"The":[57,239,310],"published":[58,187,314],"verdicts":[59,193],"disagree":[60],"sharply.":[61],"A":[62,130,199],"2025":[63],"study":[64,133],"reports":[65],"a":[67,75,123,137,144,160,216,270,292,317,322,326,338],"model":[68,106,115],"trained":[69],"predict":[71],"masked":[72],"in":[74,136,212,299,316],"learned":[76],"representation":[77,281],"space":[78],"separates":[79,319],"possible":[80],"from":[81,221,329],"impossible":[82],"events":[83],"original":[86],"IntPhys":[87,111,287],"benchmark":[88,305],"with":[89,279],"98":[90],"percent":[91,109,120],"accuracy,":[92],"concludes":[94],"intuitive":[96],"physics":[97,200],"can":[98,202,234],"emerge":[99],"without":[100],"built-in":[101],"core":[102],"knowledge;":[103],"same":[105],"scores":[107],"53.75":[108],"2,":[112],"no":[114,304],"tested":[116],"there":[117],"clears":[118],"60":[119],"overall":[121],"against":[122],"human":[124],"majority":[125],"vote":[126],"96.44":[128],"percent.":[129],"September":[131],"finds":[134],"clean,":[138],"fixed-camera":[139],"scene":[140,324],"eight":[141],"representations,":[142],"including":[143],"randomly":[145],"initialised":[146],"network":[147],"raw":[149],"pixels,":[150],"all":[151],"land":[152],"within":[153],"0.02":[154],"R^2":[155,172],"ceiling":[158],"task":[161],"requires":[163],"inferring":[164],"friction,":[167],"spread":[169],"across":[170],"0.50":[171],"once":[173],"camera,":[174],"lighting":[175],"clutter":[177],"vary.":[178],"In":[179],"this":[180],"analysis":[181],"author":[183],"reviews":[184],"synthesises":[186],"results":[188,241,256],"show":[190],"these":[192],"do":[194],"not":[195],"answer":[196],"one":[197,285],"question.":[198],"score":[201],"certify":[203],"four":[204],"different":[205,331],"things:":[206],"outcome":[209],"is":[210,228,289],"legible":[211],"input,":[214],"latent":[217],"property":[218,227],"was":[219],"identified":[220,226],"interaction":[222,277],"history,":[223],"used,":[229],"instrument":[233],"rank":[235],"at":[237],"all.":[238],"positive":[240],"concentrate":[242,257],"first.":[245],"On":[246],"latent-property":[248],"benchmarks":[249],"(Physion++,":[250],"ComPhy":[251],"ExPhy)":[253],"negative":[255],"where":[258],"second":[260],"third":[262],"required,":[264],"while":[265],"CALIPER's":[266],"swap":[267],"control":[268],"shows":[269],"fitted":[271],"readout":[272,328],"using":[273],"object's":[275],"own":[276],"history":[278],"every":[280],"tested,":[282],"an":[283,342],"untrained":[284],"included;":[286],"2":[288],"exception,":[291],"near-chance":[293],"result":[294],"largely":[296],"object-intrinsic":[297],"more":[300],"complex":[301],"scenes.":[302],"Almost":[303],"has":[306],"demonstrated":[307],"fourth.":[309],"paper":[311],"consolidates":[312],"30":[313],"measurements":[315],"table,":[318],"shortcut":[321],"clean":[323],"offers":[325],"failure":[332],"harder":[334],"scenes,":[336],"states":[337],"rankability":[339],"audit":[340],"algorithm,":[343],"proposes":[345],"five":[346],"tests":[347],"would":[349],"settle":[350],"what":[351],"remains":[352],"open.":[353]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}