{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:523LYYI7UO4DSKT4RMRADQJMT2","short_pith_number":"pith:523LYYI7","schema_version":"1.0","canonical_sha256":"eeb6bc611fa3b8392a7c8b2201c12c9e9528d93cb9a87077abb93b57c9c34f8a","source":{"kind":"arxiv","id":"2506.01059","version":1},"attestation_state":"computed","paper":{"title":"XAI-Units: Benchmarking Explainability Methods with Unit Tests","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Dejl, Carlos Ignacio Villalobos S\\'anchez, Dekai Zhang, Francesca Toni, Jun Rui Lee, Michael David Hollins, Sadegh Emami, Timothy C. H. Wong","submitted_at":"2025-06-01T15:58:27Z","abstract_excerpt":"Feature attribution (FA) methods are widely used in explainable AI (XAI) to help users understand how the inputs of a machine learning model contribute to its outputs. However, different FA models often provide disagreeing importance scores for the same model. In the absence of ground truth or in-depth knowledge about the inner workings of the model, it is often difficult to meaningfully determine which of the different FA methods produce more suitable explanations in different contexts. As a step towards addressing this issue, we introduce the open-source XAI-Units benchmark, specifically des"},"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":"2506.01059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T15:58:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc75e005d24c1c12c145674835bee217bd131fa82a0fff90990511837780f549","abstract_canon_sha256":"d865b4855296c62e0b0512da4fdb779d4b58da1525b8871197f30c54efb1ea39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:45.295489Z","signature_b64":"oAON4pPjSF7RLsDDHdGBhXQZGzwtJ1oScKfKGrO4Mu598QxfP5Xsbr0YbeKKiXZuwMMBWRVWf5UifTJakKNnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeb6bc611fa3b8392a7c8b2201c12c9e9528d93cb9a87077abb93b57c9c34f8a","last_reissued_at":"2026-07-05T11:13:45.294980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:45.294980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XAI-Units: Benchmarking Explainability Methods with Unit Tests","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam Dejl, Carlos Ignacio Villalobos S\\'anchez, Dekai Zhang, Francesca Toni, Jun Rui Lee, Michael David Hollins, Sadegh Emami, Timothy C. H. Wong","submitted_at":"2025-06-01T15:58:27Z","abstract_excerpt":"Feature attribution (FA) methods are widely used in explainable AI (XAI) to help users understand how the inputs of a machine learning model contribute to its outputs. However, different FA models often provide disagreeing importance scores for the same model. In the absence of ground truth or in-depth knowledge about the inner workings of the model, it is often difficult to meaningfully determine which of the different FA methods produce more suitable explanations in different contexts. As a step towards addressing this issue, we introduce the open-source XAI-Units benchmark, specifically des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01059","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/2506.01059/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":"2506.01059","created_at":"2026-07-05T11:13:45.295040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01059v1","created_at":"2026-07-05T11:13:45.295040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01059","created_at":"2026-07-05T11:13:45.295040+00:00"},{"alias_kind":"pith_short_12","alias_value":"523LYYI7UO4D","created_at":"2026-07-05T11:13:45.295040+00:00"},{"alias_kind":"pith_short_16","alias_value":"523LYYI7UO4DSKT4","created_at":"2026-07-05T11:13:45.295040+00:00"},{"alias_kind":"pith_short_8","alias_value":"523LYYI7","created_at":"2026-07-05T11:13:45.295040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2","json":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2.json","graph_json":"https://pith.science/api/pith-number/523LYYI7UO4DSKT4RMRADQJMT2/graph.json","events_json":"https://pith.science/api/pith-number/523LYYI7UO4DSKT4RMRADQJMT2/events.json","paper":"https://pith.science/paper/523LYYI7"},"agent_actions":{"view_html":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2","download_json":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2.json","view_paper":"https://pith.science/paper/523LYYI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01059&json=true","fetch_graph":"https://pith.science/api/pith-number/523LYYI7UO4DSKT4RMRADQJMT2/graph.json","fetch_events":"https://pith.science/api/pith-number/523LYYI7UO4DSKT4RMRADQJMT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2/action/storage_attestation","attest_author":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2/action/author_attestation","sign_citation":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2/action/citation_signature","submit_replication":"https://pith.science/pith/523LYYI7UO4DSKT4RMRADQJMT2/action/replication_record"}},"created_at":"2026-07-05T11:13:45.295040+00:00","updated_at":"2026-07-05T11:13:45.295040+00:00"}