{"id":"https://openalex.org/W7212321902","doi":"https://doi.org/10.31234/osf.io/tjahb_v1","title":"Mechanistic Interpretability Needs a Logic of Inference","display_name":"Mechanistic Interpretability Needs a Logic of Inference","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212321902","doi":"https://doi.org/10.31234/osf.io/tjahb_v1"},"language":"en","primary_location":{"id":"doi:10.31234/osf.io/tjahb_v1","doi":"https://doi.org/10.31234/osf.io/tjahb_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/tjahb_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.31234/osf.io/tjahb_v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140263117","display_name":"Zhimin Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhimin Hu","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151343903","display_name":"Chen Jiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027684697","display_name":"Hanbo Xie","orcid":"https://orcid.org/0000-0003-1133-8544","observed_orcids":["https://orcid.org/0000-0003-1133-8544"]},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanbo Xie","raw_affiliation_strings":["University of Arizona"],"raw_orcid":"https://orcid.org/0000-0003-1133-8544","affiliations":[{"raw_affiliation_string":"University of Arizona","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063748873","display_name":"N. Apurva Ratan Murty","orcid":"https://orcid.org/0000-0003-2191-797X","observed_orcids":["https://orcid.org/0000-0003-2191-797X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"N Apurva Ratan Murty","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2191-797X","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036602199","display_name":"Sashank Varma","orcid":"https://orcid.org/0000-0002-1107-0982","observed_orcids":["https://orcid.org/0000-0002-1107-0982"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sashank Varma","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9990000128746033,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9990000128746033,"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/T10778","display_name":"Philosophy of Biology and Scientific Explanation","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1207","display_name":"History and Philosophy of Science"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mechanistic-interpretability","display_name":"mechanistic interpretability","score":0.9990000128746033},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.6579999923706055},{"id":"https://openalex.org/keywords/mechanistic-explanation","display_name":"mechanistic explanation","score":0.6209999918937683},{"id":"https://openalex.org/keywords/neural-circuits","display_name":"neural circuits","score":0.4449999928474426},{"id":"https://openalex.org/keywords/population-dynamics","display_name":"population dynamics","score":0.49799999594688416},{"id":"https://openalex.org/keywords/testable-hypotheses","display_name":"testable hypotheses","score":0.722000002861023},{"id":"https://openalex.org/keywords/cumulative-knowledge","display_name":"cumulative knowledge","score":0.5239999890327454}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9642000198364258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668000221252441},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6492000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5814999938011169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.31234/osf.io/tjahb_v1","doi":"https://doi.org/10.31234/osf.io/tjahb_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/tjahb_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:share.osf.io:094a50cb-b088-4d26-868b-b0f455e8b2a4","doi":null,"is_oa":true,"landing_page_url":"https://osf.io/tjahb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.31234/osf.io/tjahb_v1","doi":"https://doi.org/10.31234/osf.io/tjahb_v1","is_oa":true,"landing_page_url":"https://doi.org/10.31234/osf.io/tjahb_v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401687","display_name":"PsyArXiv (OSF Preprints)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2799848540","host_organization_name":"Center for Open Science","host_organization_lineage":["https://openalex.org/I2799848540"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"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/W4414769259","https://openalex.org/W4406949968","https://openalex.org/W4399115130","https://openalex.org/W7202232122","https://openalex.org/W7147361271","https://openalex.org/W4415230859","https://openalex.org/W7171662369","https://openalex.org/W7161957609","https://openalex.org/W7162951806","https://openalex.org/W4414771228"],"abstract_inverted_index":{"Neural":[0],"networks":[1],"are":[2,17],"increasingly":[3],"studied":[4],"not":[5],"merely":[6],"as":[7,11],"predictive":[8],"systems,":[9],"but":[10],"complex":[12,91],"systems":[13],"whose":[14],"internal":[15],"computations":[16],"themselves":[18],"objects":[19],"of":[20,74,110,134],"scientific":[21,120],"inquiry.":[22],"Recent":[23],"progress":[24],"in":[25,122],"mechanistic":[26,67,111],"interpretability":[27,129],"(MI)":[28],"has":[29],"made":[30],"it":[31,125,139],"possible":[32],"to":[33,62,78,145,160],"identify":[34,83],"neurons,":[35],"features,":[36],"circuits,":[37],"population":[38],"structures,":[39],"and":[40,76,82,98,138],"dynamical":[41],"patterns":[42],"associated":[43],"with":[44],"model":[45,61,163],"behavior.":[46],"As":[47],"these":[48],"tools":[49],"improve,":[50],"attention":[51],"is":[52,157],"shifting":[53],"from":[54,90],"what":[55,162],"can":[56],"be":[57],"observed":[58],"inside":[59],"a":[60,102,106,116],"how":[63],"those":[64,141],"observations":[65],"support":[66],"explanations.":[68],"We":[69,94],"examine":[70],"the":[71,152,167],"parallel":[72],"efforts":[73],"neuroscience":[75],"MI":[77,156],"address":[79],"this":[80],"question":[81],"recurring":[84],"inferential":[85],"bottlenecks":[86],"when":[87],"inferring":[88],"mechanisms":[89,135,142,164],"neural":[92],"systems.":[93],"propose":[95],"five":[96],"principles":[97,114],"organize":[99],"them":[100],"into":[101,131],"recursive":[103],"logic":[104],"for":[105],"more":[107],"rigorous":[108],"procedure":[109],"inference.":[112],"These":[113],"provide":[115],"framework":[117],"that":[118],"supports":[119],"discovery":[121],"two":[123],"senses:":[124],"helps":[126],"turn":[127],"local":[128],"findings":[130],"cumulative":[132],"knowledge":[133],"within":[136],"models,":[137],"makes":[140],"sufficiently":[143],"precise":[144],"generate":[146],"testable":[147],"hypotheses":[148],"about":[149,166],"domains":[150],"beyond":[151,155],"models.":[153],"Evidence":[154],"ultimately":[158],"required":[159],"establish":[161],"reveal":[165],"world.":[168]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-12T00:00:00"}