{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I7PYFLCVQSJ6NPP7YUZZH7NNJB","short_pith_number":"pith:I7PYFLCV","schema_version":"1.0","canonical_sha256":"47df82ac558493e6bdffc53393fdad487f0ac6e590f02d09f0576c8ed5dff559","source":{"kind":"arxiv","id":"2107.13509","version":2},"attestation_state":"computed","paper":{"title":"The Who in XAI: How AI Background Shapes Perceptions of AI Explanations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.HC","authors_text":"I-Hsiang Lee, Larry Chan, Mark O. Riedl, Michael Muller, Q. Vera Liao, Samir Passi, Upol Ehsan","submitted_at":"2021-07-28T17:32:04Z","abstract_excerpt":"Explainability of AI systems is critical for users to take informed actions. Understanding \"who\" opens the black-box of AI is just as important as opening it. We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. Quantitatively, we share user perceptions along five dimensions. Qualitatively, we describe how AI background can influence interpretations, elucidating the differences through lenses of appropriation and cognitive heuristics. We find that (1) both groups showed unwarranted faith in numbers for"},"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":"2107.13509","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2021-07-28T17:32:04Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"d52d321858bea94482f671ee86c29d80690d09c5c01538e0716dd7ae7b267780","abstract_canon_sha256":"98f93034c880736801ecfef7898a16b59eefbe09e9dbe4656c8c036f42bb9fb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:38.315586Z","signature_b64":"KNIWLVPJhv9PnHKF9vCxUj3ZAWq7MVyvzfHqf6OWKwriMxnYzuq3Jvg+RzsOfl0VP9capdIubl+3plHey3J0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47df82ac558493e6bdffc53393fdad487f0ac6e590f02d09f0576c8ed5dff559","last_reissued_at":"2026-07-05T07:52:38.315050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:38.315050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Who in XAI: How AI Background Shapes Perceptions of AI Explanations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.HC","authors_text":"I-Hsiang Lee, Larry Chan, Mark O. Riedl, Michael Muller, Q. Vera Liao, Samir Passi, Upol Ehsan","submitted_at":"2021-07-28T17:32:04Z","abstract_excerpt":"Explainability of AI systems is critical for users to take informed actions. Understanding \"who\" opens the black-box of AI is just as important as opening it. We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. Quantitatively, we share user perceptions along five dimensions. Qualitatively, we describe how AI background can influence interpretations, elucidating the differences through lenses of appropriation and cognitive heuristics. We find that (1) both groups showed unwarranted faith in numbers for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.13509","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.13509/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":"2107.13509","created_at":"2026-07-05T07:52:38.315125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.13509v2","created_at":"2026-07-05T07:52:38.315125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.13509","created_at":"2026-07-05T07:52:38.315125+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7PYFLCVQSJ6","created_at":"2026-07-05T07:52:38.315125+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7PYFLCVQSJ6NPP7","created_at":"2026-07-05T07:52:38.315125+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7PYFLCV","created_at":"2026-07-05T07:52:38.315125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03693","citing_title":"Designing Effective AI Explanations for Misinformation Detection: A Comparative Study of Content, Social, and Combined Explanations","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB","json":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB.json","graph_json":"https://pith.science/api/pith-number/I7PYFLCVQSJ6NPP7YUZZH7NNJB/graph.json","events_json":"https://pith.science/api/pith-number/I7PYFLCVQSJ6NPP7YUZZH7NNJB/events.json","paper":"https://pith.science/paper/I7PYFLCV"},"agent_actions":{"view_html":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB","download_json":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB.json","view_paper":"https://pith.science/paper/I7PYFLCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.13509&json=true","fetch_graph":"https://pith.science/api/pith-number/I7PYFLCVQSJ6NPP7YUZZH7NNJB/graph.json","fetch_events":"https://pith.science/api/pith-number/I7PYFLCVQSJ6NPP7YUZZH7NNJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB/action/storage_attestation","attest_author":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB/action/author_attestation","sign_citation":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB/action/citation_signature","submit_replication":"https://pith.science/pith/I7PYFLCVQSJ6NPP7YUZZH7NNJB/action/replication_record"}},"created_at":"2026-07-05T07:52:38.315125+00:00","updated_at":"2026-07-05T07:52:38.315125+00:00"}