{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OREY2UOEPVMRRC5A5FS77ETT6K","short_pith_number":"pith:OREY2UOE","schema_version":"1.0","canonical_sha256":"74498d51c47d59188ba0e965ff9273f2bca97cd459adfc69008a550eb3d89285","source":{"kind":"arxiv","id":"2507.13090","version":1},"attestation_state":"computed","paper":{"title":"MUPAX: Multidimensional Problem Agnostic eXplainable AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Felice Franchini, Giuseppe Pirlo, Irina Voiculescu, Vincenzo Dentamaro","submitted_at":"2025-07-17T12:59:27Z","abstract_excerpt":"Robust XAI techniques should ideally be simultaneously deterministic, model agnostic, and guaranteed to converge. We propose MULTIDIMENSIONAL PROBLEM AGNOSTIC EXPLAINABLE AI (MUPAX), a deterministic, model agnostic explainability technique, with guaranteed convergency. MUPAX measure theoretic formulation gives principled feature importance attribution through structured perturbation analysis that discovers inherent input patterns and eliminates spurious relationships. We evaluate MUPAX on an extensive range of data modalities and tasks: audio classification (1D), image classification (2D), vol"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.13090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T12:59:27Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"35f87a8c3b08f7b1c0b5340c441fbd1d9a377cfbbf0ff704b3d546a43861f976","abstract_canon_sha256":"0c30ba80c65d65a5b2b7149cdfc685f6456df18eb8feb1ced4ae61c5702365b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:54.581086Z","signature_b64":"+yMqU3aPFpkK1LL/eGaK/etguCxp/QrXEr1CbMaYWheAaFSpWePE5pVEZRIfK5KueK+BPRMm5WCTiJJxgGTSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74498d51c47d59188ba0e965ff9273f2bca97cd459adfc69008a550eb3d89285","last_reissued_at":"2026-07-05T11:38:54.580599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:54.580599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUPAX: Multidimensional Problem Agnostic eXplainable AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Felice Franchini, Giuseppe Pirlo, Irina Voiculescu, Vincenzo Dentamaro","submitted_at":"2025-07-17T12:59:27Z","abstract_excerpt":"Robust XAI techniques should ideally be simultaneously deterministic, model agnostic, and guaranteed to converge. We propose MULTIDIMENSIONAL PROBLEM AGNOSTIC EXPLAINABLE AI (MUPAX), a deterministic, model agnostic explainability technique, with guaranteed convergency. MUPAX measure theoretic formulation gives principled feature importance attribution through structured perturbation analysis that discovers inherent input patterns and eliminates spurious relationships. We evaluate MUPAX on an extensive range of data modalities and tasks: audio classification (1D), image classification (2D), vol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13090","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.13090/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.13090","created_at":"2026-07-05T11:38:54.580652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13090v1","created_at":"2026-07-05T11:38:54.580652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13090","created_at":"2026-07-05T11:38:54.580652+00:00"},{"alias_kind":"pith_short_12","alias_value":"OREY2UOEPVMR","created_at":"2026-07-05T11:38:54.580652+00:00"},{"alias_kind":"pith_short_16","alias_value":"OREY2UOEPVMRRC5A","created_at":"2026-07-05T11:38:54.580652+00:00"},{"alias_kind":"pith_short_8","alias_value":"OREY2UOE","created_at":"2026-07-05T11:38:54.580652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K","json":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K.json","graph_json":"https://pith.science/api/pith-number/OREY2UOEPVMRRC5A5FS77ETT6K/graph.json","events_json":"https://pith.science/api/pith-number/OREY2UOEPVMRRC5A5FS77ETT6K/events.json","paper":"https://pith.science/paper/OREY2UOE"},"agent_actions":{"view_html":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K","download_json":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K.json","view_paper":"https://pith.science/paper/OREY2UOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13090&json=true","fetch_graph":"https://pith.science/api/pith-number/OREY2UOEPVMRRC5A5FS77ETT6K/graph.json","fetch_events":"https://pith.science/api/pith-number/OREY2UOEPVMRRC5A5FS77ETT6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K/action/storage_attestation","attest_author":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K/action/author_attestation","sign_citation":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K/action/citation_signature","submit_replication":"https://pith.science/pith/OREY2UOEPVMRRC5A5FS77ETT6K/action/replication_record"}},"created_at":"2026-07-05T11:38:54.580652+00:00","updated_at":"2026-07-05T11:38:54.580652+00:00"}