{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YQIRZDBSX7FTGWS4WB3YXZ6YUQ","short_pith_number":"pith:YQIRZDBS","schema_version":"1.0","canonical_sha256":"c4111c8c32bfcb335a5cb0778be7d8a41dc46e33c702511914826682e3668569","source":{"kind":"arxiv","id":"1812.04608","version":2},"attestation_state":"computed","paper":{"title":"Metrics for Explainable AI: Challenges and Prospects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gary Klein, Jordan Litman, Robert R. Hoffman, Shane T. Mueller","submitted_at":"2018-12-11T18:50:02Z","abstract_excerpt":"The question addressed in this paper is: If we present to a user an AI system that explains how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? In other words, how do we know that an explanainable AI system (XAI) is any good? Our focus is on the key concepts of measurement. We discuss specific methods for evaluating: (1) the goodness of explanations, (2) whether users are satisfied by explanations, (3) how well users understand the AI systems, (4) how curiosity motivates the search for explanations, (5) whether the user's tr"},"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":"1812.04608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-12-11T18:50:02Z","cross_cats_sorted":[],"title_canon_sha256":"f3d4a114605f910e3fd15e2fad90557c27f3ee1d43184b5c2677be69ccec35fe","abstract_canon_sha256":"9208a0803375d8efac85e1ac474b11d2b6070dc40f874792823b33aa4421ec37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:58.608547Z","signature_b64":"FDyERQr5wGWBngXX+pgWY8oQUJqDm4kvI18eQb1awU3sgizvG4qPqKgufIq4eQLX1j1xrvcA5uh29KIkZjbeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4111c8c32bfcb335a5cb0778be7d8a41dc46e33c702511914826682e3668569","last_reissued_at":"2026-05-17T23:54:58.608064Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:58.608064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metrics for Explainable AI: Challenges and Prospects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gary Klein, Jordan Litman, Robert R. Hoffman, Shane T. Mueller","submitted_at":"2018-12-11T18:50:02Z","abstract_excerpt":"The question addressed in this paper is: If we present to a user an AI system that explains how it works, how do we know whether the explanation works and the user has achieved a pragmatic understanding of the AI? In other words, how do we know that an explanainable AI system (XAI) is any good? Our focus is on the key concepts of measurement. We discuss specific methods for evaluating: (1) the goodness of explanations, (2) whether users are satisfied by explanations, (3) how well users understand the AI systems, (4) how curiosity motivates the search for explanations, (5) whether the user's tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04608","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1812.04608","created_at":"2026-05-17T23:54:58.608142+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.04608v2","created_at":"2026-05-17T23:54:58.608142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04608","created_at":"2026-05-17T23:54:58.608142+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQIRZDBSX7FT","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQIRZDBSX7FTGWS4","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQIRZDBS","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.18849","citing_title":"INSIGHTS: Demonstration-Based Summaries of Time Series Predictors","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2509.08667","citing_title":"Minimal Data, Maximum Clarity: A Heuristic for Explaining Optimization","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2512.15791","citing_title":"Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Study","ref_index":223,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03237","citing_title":"The Persuasion Paradox: When LLM Explanations Fail to Improve Human-AI Team Performance","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2602.24176","citing_title":"Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14207","citing_title":"What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11161","citing_title":"Interpretability Can Be Actionable","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27539","citing_title":"Knowledge Affordances for Hybrid Human-AI Information Seeking","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23842","citing_title":"Reheat Nachos for Dinner? Evaluating AI Support for Cross-Cultural Communication of Neologisms","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07896","citing_title":"What if AI systems weren't chatbots?","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05790","citing_title":"Improving Explanations: Applying the Feature Understandability Scale for Cost-Sensitive Feature Selection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09444","citing_title":"Confidence Without Competence in AI-Assisted Knowledge Work","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ","json":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ.json","graph_json":"https://pith.science/api/pith-number/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/graph.json","events_json":"https://pith.science/api/pith-number/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/events.json","paper":"https://pith.science/paper/YQIRZDBS"},"agent_actions":{"view_html":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ","download_json":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ.json","view_paper":"https://pith.science/paper/YQIRZDBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.04608&json=true","fetch_graph":"https://pith.science/api/pith-number/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/action/storage_attestation","attest_author":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/action/author_attestation","sign_citation":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/action/citation_signature","submit_replication":"https://pith.science/pith/YQIRZDBSX7FTGWS4WB3YXZ6YUQ/action/replication_record"}},"created_at":"2026-05-17T23:54:58.608142+00:00","updated_at":"2026-05-17T23:54:58.608142+00:00"}