{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RG2Y75JTHVYYYADIZ2F2AZERYM","short_pith_number":"pith:RG2Y75JT","schema_version":"1.0","canonical_sha256":"89b58ff5333d718c0068ce8ba06491c30afb3c8a588f84585fea4b8ed4ceab83","source":{"kind":"arxiv","id":"2106.13976","version":1},"attestation_state":"computed","paper":{"title":"Explanatory Pluralism in Explainable AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yiheng Yao","submitted_at":"2021-06-26T09:02:06Z","abstract_excerpt":"The increasingly widespread application of AI models motivates increased demand for explanations from a variety of stakeholders. However, this demand is ambiguous because there are many types of 'explanation' with different evaluative criteria. In the spirit of pluralism, I chart a taxonomy of types of explanation and the associated XAI methods that can address them. When we look to expose the inner mechanisms of AI models, we develop Diagnostic-explanations. When we seek to render model output understandable, we produce Explication-explanations. When we wish to form stable generalizations of "},"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":"2106.13976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-26T09:02:06Z","cross_cats_sorted":[],"title_canon_sha256":"6d327e55d3df65d78cfc83e133b5def12bf1bf680925790e57cab6569ab9ce3c","abstract_canon_sha256":"c4b6ed8712ff25dba923494202742f7d06661e693f1409f268a22343a37b7493"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:30.458397Z","signature_b64":"jKEL/FrXUGyxWt5Y2SS2WGP/8AtCaJXR7Jz2MBGIP/YV0cPq0fdFagQ66zR3yujqL6ZD/h/e1L6s33/KfEPNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89b58ff5333d718c0068ce8ba06491c30afb3c8a588f84585fea4b8ed4ceab83","last_reissued_at":"2026-07-05T02:52:30.457905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:30.457905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explanatory Pluralism in Explainable AI","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yiheng Yao","submitted_at":"2021-06-26T09:02:06Z","abstract_excerpt":"The increasingly widespread application of AI models motivates increased demand for explanations from a variety of stakeholders. However, this demand is ambiguous because there are many types of 'explanation' with different evaluative criteria. In the spirit of pluralism, I chart a taxonomy of types of explanation and the associated XAI methods that can address them. When we look to expose the inner mechanisms of AI models, we develop Diagnostic-explanations. When we seek to render model output understandable, we produce Explication-explanations. When we wish to form stable generalizations of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13976","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/2106.13976/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":"2106.13976","created_at":"2026-07-05T02:52:30.457967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13976v1","created_at":"2026-07-05T02:52:30.457967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13976","created_at":"2026-07-05T02:52:30.457967+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG2Y75JTHVYY","created_at":"2026-07-05T02:52:30.457967+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG2Y75JTHVYYYADI","created_at":"2026-07-05T02:52:30.457967+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG2Y75JT","created_at":"2026-07-05T02:52:30.457967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.20086","citing_title":"Evaluating Actionability in Explainable AI","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM","json":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM.json","graph_json":"https://pith.science/api/pith-number/RG2Y75JTHVYYYADIZ2F2AZERYM/graph.json","events_json":"https://pith.science/api/pith-number/RG2Y75JTHVYYYADIZ2F2AZERYM/events.json","paper":"https://pith.science/paper/RG2Y75JT"},"agent_actions":{"view_html":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM","download_json":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM.json","view_paper":"https://pith.science/paper/RG2Y75JT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13976&json=true","fetch_graph":"https://pith.science/api/pith-number/RG2Y75JTHVYYYADIZ2F2AZERYM/graph.json","fetch_events":"https://pith.science/api/pith-number/RG2Y75JTHVYYYADIZ2F2AZERYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM/action/storage_attestation","attest_author":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM/action/author_attestation","sign_citation":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM/action/citation_signature","submit_replication":"https://pith.science/pith/RG2Y75JTHVYYYADIZ2F2AZERYM/action/replication_record"}},"created_at":"2026-07-05T02:52:30.457967+00:00","updated_at":"2026-07-05T02:52:30.457967+00:00"}