{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JRIB3K5GB4MDRWIOUEMZFQPPUY","short_pith_number":"pith:JRIB3K5G","schema_version":"1.0","canonical_sha256":"4c501daba60f1838d90ea11992c1efa610700b7a6daf3a8ef94c9c65bfa66a9e","source":{"kind":"arxiv","id":"2412.05592","version":1},"attestation_state":"computed","paper":{"title":"From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anna Hedstr\\\"om, Kristoffer Wickstr{\\o}m, Marina Marie-Claire H\\\"ohne","submitted_at":"2024-12-07T09:14:46Z","abstract_excerpt":"The lack of ground truth explanation labels is a fundamental challenge for quantitative evaluation in explainable artificial intelligence (XAI). This challenge becomes especially problematic when evaluation methods have numerous hyperparameters that must be specified by the user, as there is no ground truth to determine an optimal hyperparameter selection. It is typically not feasible to do an exhaustive search of hyperparameters so researchers typically make a normative choice based on similar studies in the literature, which provides great flexibility for the user. In this work, we illustrat"},"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":"2412.05592","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-07T09:14:46Z","cross_cats_sorted":[],"title_canon_sha256":"8110fa9ed0e7a688b355cd04acc017a38a86c70f17ec146f544706f79dfb7dac","abstract_canon_sha256":"3f8007ef37d8e6c3fd8354d008c79250af9d9a7dd1c7d8774caa7b5335618d4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:05.876630Z","signature_b64":"VoGUPHk6ydwrsyWOqgFEiM1zflq47vBH/tuRYq+0qsszeoxdfz55e0YYAm/Ji4g/0aSQCnNtUgkpKLHKrycpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c501daba60f1838d90ea11992c1efa610700b7a6daf3a8ef94c9c65bfa66a9e","last_reissued_at":"2026-07-05T09:46:05.876194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:05.876194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anna Hedstr\\\"om, Kristoffer Wickstr{\\o}m, Marina Marie-Claire H\\\"ohne","submitted_at":"2024-12-07T09:14:46Z","abstract_excerpt":"The lack of ground truth explanation labels is a fundamental challenge for quantitative evaluation in explainable artificial intelligence (XAI). This challenge becomes especially problematic when evaluation methods have numerous hyperparameters that must be specified by the user, as there is no ground truth to determine an optimal hyperparameter selection. It is typically not feasible to do an exhaustive search of hyperparameters so researchers typically make a normative choice based on similar studies in the literature, which provides great flexibility for the user. In this work, we illustrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05592","kind":"arxiv","version":1},"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/2412.05592/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":"2412.05592","created_at":"2026-07-05T09:46:05.876247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05592v1","created_at":"2026-07-05T09:46:05.876247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05592","created_at":"2026-07-05T09:46:05.876247+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRIB3K5GB4MD","created_at":"2026-07-05T09:46:05.876247+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRIB3K5GB4MDRWIO","created_at":"2026-07-05T09:46:05.876247+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRIB3K5G","created_at":"2026-07-05T09:46:05.876247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10490","citing_title":"On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY","json":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY.json","graph_json":"https://pith.science/api/pith-number/JRIB3K5GB4MDRWIOUEMZFQPPUY/graph.json","events_json":"https://pith.science/api/pith-number/JRIB3K5GB4MDRWIOUEMZFQPPUY/events.json","paper":"https://pith.science/paper/JRIB3K5G"},"agent_actions":{"view_html":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY","download_json":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY.json","view_paper":"https://pith.science/paper/JRIB3K5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05592&json=true","fetch_graph":"https://pith.science/api/pith-number/JRIB3K5GB4MDRWIOUEMZFQPPUY/graph.json","fetch_events":"https://pith.science/api/pith-number/JRIB3K5GB4MDRWIOUEMZFQPPUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY/action/storage_attestation","attest_author":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY/action/author_attestation","sign_citation":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY/action/citation_signature","submit_replication":"https://pith.science/pith/JRIB3K5GB4MDRWIOUEMZFQPPUY/action/replication_record"}},"created_at":"2026-07-05T09:46:05.876247+00:00","updated_at":"2026-07-05T09:46:05.876247+00:00"}