{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SVJSCDGHNGP2N4V7YNO26XDZH7","short_pith_number":"pith:SVJSCDGH","schema_version":"1.0","canonical_sha256":"9553210cc7699fa6f2bfc35daf5c793ffefee6e378e1c85ff044702f8447f954","source":{"kind":"arxiv","id":"2401.12576","version":2},"attestation_state":"computed","paper":{"title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Josef van Genabith, Leonhard Hennig, Nils Feldhus, Qianli Wang, Sebastian M\\\"oller, Tatiana Anikina","submitted_at":"2024-01-23T09:11:07Z","abstract_excerpt":"Interpretability tools that offer explanations in the form of a dialogue have demonstrated their efficacy in enhancing users' understanding (Slack et al., 2023; Shen et al., 2023), as one-off explanations may fall short in providing sufficient information to the user. Current solutions for dialogue-based explanations, however, often require external tools and modules and are not easily transferable to tasks they were not designed for. With LLMCheckup, we present an easily accessible tool that allows users to chat with any state-of-the-art large language model (LLM) about its behavior. We enabl"},"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":"2401.12576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T09:11:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c48ede29166ad8b52c169cc2e57ec61cdaea1f392f58e886b1065616787cfcac","abstract_canon_sha256":"a9b04a69a9c21527b2093a74bfabfde049f3e256a90c6949b613b77e4c9632ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:42.890090Z","signature_b64":"chZiAroer59DPxZCn0wMwTvXiaeZR5ktFcbcv/lv7ciHzQwD7vJZYHMXJmbLSyhBmggYnKoxwerbTcntSyP2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9553210cc7699fa6f2bfc35daf5c793ffefee6e378e1c85ff044702f8447f954","last_reissued_at":"2026-07-05T08:11:42.889565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:42.889565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Josef van Genabith, Leonhard Hennig, Nils Feldhus, Qianli Wang, Sebastian M\\\"oller, Tatiana Anikina","submitted_at":"2024-01-23T09:11:07Z","abstract_excerpt":"Interpretability tools that offer explanations in the form of a dialogue have demonstrated their efficacy in enhancing users' understanding (Slack et al., 2023; Shen et al., 2023), as one-off explanations may fall short in providing sufficient information to the user. Current solutions for dialogue-based explanations, however, often require external tools and modules and are not easily transferable to tasks they were not designed for. With LLMCheckup, we present an easily accessible tool that allows users to chat with any state-of-the-art large language model (LLM) about its behavior. We enabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12576","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/2401.12576/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":"2401.12576","created_at":"2026-07-05T08:11:42.889624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12576v2","created_at":"2026-07-05T08:11:42.889624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12576","created_at":"2026-07-05T08:11:42.889624+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVJSCDGHNGP2","created_at":"2026-07-05T08:11:42.889624+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVJSCDGHNGP2N4V7","created_at":"2026-07-05T08:11:42.889624+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVJSCDGH","created_at":"2026-07-05T08:11:42.889624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02920","citing_title":"Visual-Conversational Interface for Evidence-Based Explanation of Diabetes Risk Prediction","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7","json":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7.json","graph_json":"https://pith.science/api/pith-number/SVJSCDGHNGP2N4V7YNO26XDZH7/graph.json","events_json":"https://pith.science/api/pith-number/SVJSCDGHNGP2N4V7YNO26XDZH7/events.json","paper":"https://pith.science/paper/SVJSCDGH"},"agent_actions":{"view_html":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7","download_json":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7.json","view_paper":"https://pith.science/paper/SVJSCDGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12576&json=true","fetch_graph":"https://pith.science/api/pith-number/SVJSCDGHNGP2N4V7YNO26XDZH7/graph.json","fetch_events":"https://pith.science/api/pith-number/SVJSCDGHNGP2N4V7YNO26XDZH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7/action/storage_attestation","attest_author":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7/action/author_attestation","sign_citation":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7/action/citation_signature","submit_replication":"https://pith.science/pith/SVJSCDGHNGP2N4V7YNO26XDZH7/action/replication_record"}},"created_at":"2026-07-05T08:11:42.889624+00:00","updated_at":"2026-07-05T08:11:42.889624+00:00"}