{"id":"https://openalex.org/W4414769259","doi":"https://doi.org/10.48550/arxiv.2505.00808","title":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","display_name":"A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W4414769259","doi":"https://doi.org/10.48550/arxiv.2505.00808"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.00808","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00808","pdf_url":"https://arxiv.org/pdf/2505.00808","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.00808","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114336088","display_name":"Kola Ayonrinde","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayonrinde, Kola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119823551","display_name":"Louis Jaburi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaburi, Louis","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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"}},{"id":"https://openalex.org/T10778","display_name":"Philosophy and History of Science","score":0.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.9769999980926514},{"id":"https://openalex.org/keywords/neural-network-interpretability","display_name":"neural network interpretability","score":0.8140000104904175},{"id":"https://openalex.org/keywords/causal-explanation","display_name":"causal explanation","score":0.8500000238418579}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9832000136375427},{"id":"https://openalex.org/C116222747","wikidata":"https://www.wikidata.org/wiki/Q220888","display_name":"Falsifiability","level":2,"score":0.8098000288009644},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.551800012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5493999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5184999704360962},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C2778638050","wikidata":"https://www.wikidata.org/wiki/Q5421252","display_name":"Explanatory model","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C192465680","wikidata":"https://www.wikidata.org/wiki/Q1413450","display_name":"Precondition","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C110099512","wikidata":"https://www.wikidata.org/wiki/Q59115","display_name":"Philosophy of science","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C47822265","wikidata":"https://www.wikidata.org/wiki/Q854457","display_name":"Complex system","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.00808","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00808","pdf_url":"https://arxiv.org/pdf/2505.00808","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.2505.00808","doi":"https://doi.org/10.48550/arxiv.2505.00808","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.00808","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:2505.00808","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.00808","pdf_url":"https://arxiv.org/pdf/2505.00808","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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415230859","https://openalex.org/W4414771228","https://openalex.org/W7162951806","https://openalex.org/W7212321902","https://openalex.org/W4399115130","https://openalex.org/W7160929303","https://openalex.org/W4406059511","https://openalex.org/W7147361271","https://openalex.org/W7202232122","https://openalex.org/W7212150409"],"abstract_inverted_index":{"Mechanistic":[0,18,63,114],"Interpretability":[1,19,64],"aims":[2],"to":[3,25,82],"understand":[4],"neural":[5,29,78],"networks":[6,30],"through":[7],"causal":[8],"explanations.":[9],"We":[10,40,58,94],"argue":[11,105],"for":[12,110],"the":[13,67,96,111],"Explanatory":[14,44,99],"View":[15],"Hypothesis:":[16],"that":[17,43],"research":[20],"is":[21,56,106],"a":[22,54,60,101,107],"principled":[23],"approach":[24],"understanding":[26],"models":[27],"because":[28],"contain":[31],"implicit":[32],"explanations":[33,76],"which":[34,103],"can":[35],"be":[36],"extracted":[37],"and":[38,74,89],"understood.":[39],"hence":[41],"show":[42],"Faithfulness,":[45],"an":[46,51],"assessment":[47],"of":[48,62,69,77,98,113],"how":[49],"well":[50],"explanation":[52],"fits":[53],"model,":[55],"well-defined.":[57],"propose":[59],"definition":[61],"(MI)":[65],"as":[66],"practice":[68],"producing":[70],"Model-level,":[71],"Ontic,":[72],"Causal-Mechanistic,":[73],"Falsifiable":[75],"networks,":[79],"allowing":[80],"us":[81],"distinguish":[83],"MI":[84],"from":[85],"other":[86],"interpretability":[87],"paradigms":[88],"detail":[90],"MI's":[91],"inherent":[92],"limits.":[93],"formulate":[95],"Principle":[97],"Optimism,":[100],"conjecture":[102],"we":[104],"necessary":[108],"precondition":[109],"success":[112],"Interpretability.":[115]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
