{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DWJMI6TDQQV5PBA3YUG4CGEKAG","short_pith_number":"pith:DWJMI6TD","schema_version":"1.0","canonical_sha256":"1d92c47a63842bd7841bc50dc1188a01ae700654c199acb787c6c852950b5e70","source":{"kind":"arxiv","id":"2305.02012","version":3},"attestation_state":"computed","paper":{"title":"A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ahmed Salih, Gloria Menegaz, Ilaria Boscolo Galazzo, Karim Lekadir, Petia Radeva, Steffen E. Petersen, Zahra Raisi-Estabragh","submitted_at":"2023-05-03T10:04:46Z","abstract_excerpt":"eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end-users into their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, we discuss the way the explainability metrics of these two methods are generated and propose a framewor"},"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":"2305.02012","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-05-03T10:04:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fec301f145bfb623c8f2437b0a62da1817e1060328506ab4f68ee2f40eeefdc3","abstract_canon_sha256":"8642c420a1f40837fd09ae535021410c62a10ec2dc96a947c3902ebe384a6e53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:35.188784Z","signature_b64":"gqYXexWWzH5YNlxo4NEbSdy8di8XqqyUPgAgIE8lNjtlUyTFFWrwaKW05LrF21JLdpaAkpMkJg/FxHPv2UdWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d92c47a63842bd7841bc50dc1188a01ae700654c199acb787c6c852950b5e70","last_reissued_at":"2026-07-05T08:37:35.188300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:35.188300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ahmed Salih, Gloria Menegaz, Ilaria Boscolo Galazzo, Karim Lekadir, Petia Radeva, Steffen E. Petersen, Zahra Raisi-Estabragh","submitted_at":"2023-05-03T10:04:46Z","abstract_excerpt":"eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end-users into their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, we discuss the way the explainability metrics of these two methods are generated and propose a framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02012","kind":"arxiv","version":3},"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/2305.02012/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":"2305.02012","created_at":"2026-07-05T08:37:35.188364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02012v3","created_at":"2026-07-05T08:37:35.188364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02012","created_at":"2026-07-05T08:37:35.188364+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWJMI6TDQQV5","created_at":"2026-07-05T08:37:35.188364+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWJMI6TDQQV5PBA3","created_at":"2026-07-05T08:37:35.188364+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWJMI6TD","created_at":"2026-07-05T08:37:35.188364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00233","citing_title":"Ethical AI: Towards Defining a Collective Evaluation Framework","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG","json":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG.json","graph_json":"https://pith.science/api/pith-number/DWJMI6TDQQV5PBA3YUG4CGEKAG/graph.json","events_json":"https://pith.science/api/pith-number/DWJMI6TDQQV5PBA3YUG4CGEKAG/events.json","paper":"https://pith.science/paper/DWJMI6TD"},"agent_actions":{"view_html":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG","download_json":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG.json","view_paper":"https://pith.science/paper/DWJMI6TD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02012&json=true","fetch_graph":"https://pith.science/api/pith-number/DWJMI6TDQQV5PBA3YUG4CGEKAG/graph.json","fetch_events":"https://pith.science/api/pith-number/DWJMI6TDQQV5PBA3YUG4CGEKAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG/action/storage_attestation","attest_author":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG/action/author_attestation","sign_citation":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG/action/citation_signature","submit_replication":"https://pith.science/pith/DWJMI6TDQQV5PBA3YUG4CGEKAG/action/replication_record"}},"created_at":"2026-07-05T08:37:35.188364+00:00","updated_at":"2026-07-05T08:37:35.188364+00:00"}