{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4IHAJBYGYJGDJU74ZX7BWJBOP3","short_pith_number":"pith:4IHAJBYG","schema_version":"1.0","canonical_sha256":"e20e048706c24c34d3fccdfe1b242e7ed51cc5db8fdb4afaec2184c42ec8cb3e","source":{"kind":"arxiv","id":"2306.03048","version":3},"attestation_state":"computed","paper":{"title":"From Robustness to Explainability and Back Again","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Joao Marques-Silva, Xuanxiang Huang","submitted_at":"2023-06-05T17:21:05Z","abstract_excerpt":"Formal explainability guarantees the rigor of computed explanations, and so it is paramount in domains where rigor is critical, including those deemed high-risk. Unfortunately, since its inception formal explainability has been hampered by poor scalability. At present, this limitation still holds true for some families of classifiers, the most significant being deep neural networks. This paper addresses the poor scalability of formal explainability and proposes novel efficient algorithms for computing formal explanations. The novel algorithm computes explanations by answering instead a number "},"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":"2306.03048","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-05T17:21:05Z","cross_cats_sorted":[],"title_canon_sha256":"2d94a9602f001f9b09194cf63176d870887411ff9ef417e49f18d10f5b732818","abstract_canon_sha256":"18af08844fa75671395827a01910c86304a69c80b02a6f7feb6590e6912d7897"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:22.607113Z","signature_b64":"Dg+IIUxWnUlHx+q1Qts0TJjx0o7uGBKxLo7hOkzQQDZwQPffBTnHxcEu1nKN0hwBXhDFm+uOc6dhQvzBu4wcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e20e048706c24c34d3fccdfe1b242e7ed51cc5db8fdb4afaec2184c42ec8cb3e","last_reissued_at":"2026-07-05T09:43:22.606448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:22.606448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Robustness to Explainability and Back Again","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Joao Marques-Silva, Xuanxiang Huang","submitted_at":"2023-06-05T17:21:05Z","abstract_excerpt":"Formal explainability guarantees the rigor of computed explanations, and so it is paramount in domains where rigor is critical, including those deemed high-risk. Unfortunately, since its inception formal explainability has been hampered by poor scalability. At present, this limitation still holds true for some families of classifiers, the most significant being deep neural networks. This paper addresses the poor scalability of formal explainability and proposes novel efficient algorithms for computing formal explanations. The novel algorithm computes explanations by answering instead a number "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03048","kind":"arxiv","version":3},"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/2306.03048/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":"2306.03048","created_at":"2026-07-05T09:43:22.606548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03048v3","created_at":"2026-07-05T09:43:22.606548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03048","created_at":"2026-07-05T09:43:22.606548+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IHAJBYGYJGD","created_at":"2026-07-05T09:43:22.606548+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IHAJBYGYJGDJU74","created_at":"2026-07-05T09:43:22.606548+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IHAJBYG","created_at":"2026-07-05T09:43:22.606548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.13985","citing_title":"Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptoms","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3","json":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3.json","graph_json":"https://pith.science/api/pith-number/4IHAJBYGYJGDJU74ZX7BWJBOP3/graph.json","events_json":"https://pith.science/api/pith-number/4IHAJBYGYJGDJU74ZX7BWJBOP3/events.json","paper":"https://pith.science/paper/4IHAJBYG"},"agent_actions":{"view_html":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3","download_json":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3.json","view_paper":"https://pith.science/paper/4IHAJBYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03048&json=true","fetch_graph":"https://pith.science/api/pith-number/4IHAJBYGYJGDJU74ZX7BWJBOP3/graph.json","fetch_events":"https://pith.science/api/pith-number/4IHAJBYGYJGDJU74ZX7BWJBOP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3/action/storage_attestation","attest_author":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3/action/author_attestation","sign_citation":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3/action/citation_signature","submit_replication":"https://pith.science/pith/4IHAJBYGYJGDJU74ZX7BWJBOP3/action/replication_record"}},"created_at":"2026-07-05T09:43:22.606548+00:00","updated_at":"2026-07-05T09:43:22.606548+00:00"}