{"id":"https://openalex.org/W4415230859","doi":"https://doi.org/10.1609/aies.v8i1.36547","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability","display_name":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415230859","doi":"https://doi.org/10.1609/aies.v8i1.36547"},"language":"en","primary_location":{"id":"doi:10.1609/aies.v8i1.36547","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36547","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36547/38685","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AIES/article/download/36547/38685","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114336088","display_name":"Kola Ayonrinde","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087931","display_name":"Institute for Security Studies","ror":"https://ror.org/004zjze34","country_code":"KE","type":"nonprofit","lineage":["https://openalex.org/I4210087931","https://openalex.org/I4210093398"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Kola Ayonrinde","raw_affiliation_strings":["UK AI Security Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UK AI Security Institute","institution_ids":["https://openalex.org/I4210087931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119823551","display_name":"Louis Jaburi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louis Jaburi","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24987323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"1","first_page":"265","last_page":"278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14351","display_name":"Statistical and Computational Modeling","score":0.7856000065803528,"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/T14351","display_name":"Statistical and Computational Modeling","score":0.7856000065803528,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6917999982833862,"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 and History of Science","score":0.6353999972343445,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.9848999977111816},{"id":"https://openalex.org/keywords/falsifiability","display_name":"Falsifiability","score":0.8086000084877014},{"id":"https://openalex.org/keywords/explanatory-model","display_name":"Explanatory model","score":0.42820000648498535},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3788999915122986},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.35120001435279846},{"id":"https://openalex.org/keywords/precondition","display_name":"Precondition","score":0.3375000059604645}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9848999977111816},{"id":"https://openalex.org/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.8086000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5688999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5273000001907349},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.46799999475479126},{"id":"https://openalex.org/C2778638050","wikidata":"https://www.wikidata.org/wiki/Q5421252","display_name":"Explanatory model","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3569999933242798},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C192465680","wikidata":"https://www.wikidata.org/wiki/Q1413450","display_name":"Precondition","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.28600001335144043},{"id":"https://openalex.org/C2777402642","wikidata":"https://www.wikidata.org/wiki/Q2557224","display_name":"Explanatory power","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aies.v8i1.36547","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36547","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36547/38685","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/36547","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AIES/article/view/36547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3065-8365","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aies.v8i1.36547","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36547","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36547/38685","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337253","display_name":"Instituto de Ciencias del Mar y Limnolog\u00eda, Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415230859.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mechanistic":[0,19,66,117],"Interpretability":[1,20,67],"aims":[2],"to":[3,27,85],"understand":[4],"neural":[5,32,81],"net-":[6],"works":[7],"through":[8],"causal":[9],"explanations.":[10],"We":[11,43,61,97],"argue":[12,108],"for":[13,113],"the":[14,70,99,114],"Explanatory":[15,47,102],"View":[16],"Hypothesis:":[17],"that":[18,46],"re-":[21],"search":[22],"is":[23,59,109],"a":[24,57,63,104,110],"principled":[25],"approach":[26],"understanding":[28],"models":[29],"be-":[30],"cause":[31],"networks":[33],"contain":[34],"implicit":[35],"explanations":[36,79],"which":[37,106],"can":[38],"be":[39],"extracted":[40],"and":[41,77,92],"understood.":[42],"hence":[44],"show":[45],"Faithfulness,":[48],"an":[49,54],"assessment":[50],"of":[51,65,72,80,101,116],"how":[52],"well":[53],"explanation":[55],"fits":[56],"model,":[58],"well-defined.":[60],"propose":[62],"definition":[64],"(MI)":[68],"as":[69],"practice":[71],"producing":[73],"Model-level,":[74],"Ontic,":[75],"Causal-Mechanistic,":[76],"Falsifiable":[78],"networks,":[82],"allowing":[83],"us":[84],"distinguish":[86],"MI":[87],"from":[88],"other":[89],"interpretability":[90],"paradigms":[91],"detail":[93],"MI\u2019s":[94],"inherent":[95],"limits.":[96],"formulate":[98],"Principle":[100],"Optimism,":[103],"conjecture":[105],"we":[107],"necessary":[111],"precondition":[112],"success":[115],"Interpretability.":[118]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-16T00:00:00"}