{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VY52ADUHVPD4JY3XWDZRSMC6XK","short_pith_number":"pith:VY52ADUH","schema_version":"1.0","canonical_sha256":"ae3ba00e87abc7c4e377b0f319305eba8c2aa21649baf367bde8de4419f264ee","source":{"kind":"arxiv","id":"2404.11875","version":2},"attestation_state":"computed","paper":{"title":"Concept Induction using LLMs: a user experiment for assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adrita Barua, Cara Widmer, Pascal Hitzler","submitted_at":"2024-04-18T03:22:02Z","abstract_excerpt":"Explainable Artificial Intelligence (XAI) poses a significant challenge in providing transparent and understandable insights into complex AI models. Traditional post-hoc algorithms, while useful, often struggle to deliver interpretable explanations. Concept-based models offer a promising avenue by incorporating explicit representations of concepts to enhance interpretability. However, existing research on automatic concept discovery methods is often limited by lower-level concepts, costly human annotation requirements, and a restricted domain of background knowledge. In this study, we explore "},"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":"2404.11875","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T03:22:02Z","cross_cats_sorted":[],"title_canon_sha256":"774e86aaf63b5296c4b4bc240d0eb6cb819dbf44dc5a9f6d2f6bbe65fde5b34d","abstract_canon_sha256":"b8ee7731805d5e46138a80996b2e78446f4bc3b5a21a0577e6b876d5d5645e85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:58.847237Z","signature_b64":"vR82QbRO/ScMdyZqLv0pxDeq3EA6L6panG1WbVdICb98h43bBiz2Qeg3dUaIdFmZx6GPzq0fU5GHrLizYXIwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3ba00e87abc7c4e377b0f319305eba8c2aa21649baf367bde8de4419f264ee","last_reissued_at":"2026-07-05T09:09:58.846739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:58.846739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept Induction using LLMs: a user experiment for assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adrita Barua, Cara Widmer, Pascal Hitzler","submitted_at":"2024-04-18T03:22:02Z","abstract_excerpt":"Explainable Artificial Intelligence (XAI) poses a significant challenge in providing transparent and understandable insights into complex AI models. Traditional post-hoc algorithms, while useful, often struggle to deliver interpretable explanations. Concept-based models offer a promising avenue by incorporating explicit representations of concepts to enhance interpretability. However, existing research on automatic concept discovery methods is often limited by lower-level concepts, costly human annotation requirements, and a restricted domain of background knowledge. In this study, we explore "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11875","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/2404.11875/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":"2404.11875","created_at":"2026-07-05T09:09:58.846792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11875v2","created_at":"2026-07-05T09:09:58.846792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11875","created_at":"2026-07-05T09:09:58.846792+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY52ADUHVPD4","created_at":"2026-07-05T09:09:58.846792+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY52ADUHVPD4JY3X","created_at":"2026-07-05T09:09:58.846792+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY52ADUH","created_at":"2026-07-05T09:09:58.846792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12240","citing_title":"Mind the XAI Gap: A Human-Centered LLM Framework for Democratizing Explainable AI","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK","json":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK.json","graph_json":"https://pith.science/api/pith-number/VY52ADUHVPD4JY3XWDZRSMC6XK/graph.json","events_json":"https://pith.science/api/pith-number/VY52ADUHVPD4JY3XWDZRSMC6XK/events.json","paper":"https://pith.science/paper/VY52ADUH"},"agent_actions":{"view_html":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK","download_json":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK.json","view_paper":"https://pith.science/paper/VY52ADUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11875&json=true","fetch_graph":"https://pith.science/api/pith-number/VY52ADUHVPD4JY3XWDZRSMC6XK/graph.json","fetch_events":"https://pith.science/api/pith-number/VY52ADUHVPD4JY3XWDZRSMC6XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK/action/storage_attestation","attest_author":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK/action/author_attestation","sign_citation":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK/action/citation_signature","submit_replication":"https://pith.science/pith/VY52ADUHVPD4JY3XWDZRSMC6XK/action/replication_record"}},"created_at":"2026-07-05T09:09:58.846792+00:00","updated_at":"2026-07-05T09:09:58.846792+00:00"}