{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QMCOOXMQKQPMNDPTO3WYNOH2JK","short_pith_number":"pith:QMCOOXMQ","schema_version":"1.0","canonical_sha256":"8304e75d90541ec68df376ed86b8fa4a8268449e2ce522bb283b3432d3073a7d","source":{"kind":"arxiv","id":"2605.28977","version":1},"attestation_state":"computed","paper":{"title":"Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonia \\v{S}ar\\v{c}evi\\'c, Nikolina Frid","submitted_at":"2026-05-27T18:32:57Z","abstract_excerpt":"Recent advances in deep learning have enabled increasingly accurate electroencephalography (EEG)-based classification of Major Depressive Disorder (MDD), but the decision-making processes of high-capacity models remain difficult to interpret. This study investigates multiple post-hoc explainability methods applied to an InceptionTime architecture trained for EEG-based MDD detection. The analysis includes Shapley-based, gradient-based, and perturbation-based attribution approaches: DeepSHAP, Integrated Gradients, GradCAM, Occlusion, and Permutation Feature Importance. Explainability analysis wa"},"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":"2605.28977","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T18:32:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"470a3ed27b3eb417f37ec009746f8688123eac4f79de02e86c7e1eaa85c31121","abstract_canon_sha256":"60247a2545f5088c66dfb6f4090d11a6ea8127d1379989abce4043977b5c3c2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:42.186811Z","signature_b64":"OqZlosPulIvkENGpGHi9sBhLi1J7e5/WAPPwW4t2rAOEq8JYVgoIz09OWDr95SR37zqqtVEMFrLDp6XdmYoLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8304e75d90541ec68df376ed86b8fa4a8268449e2ce522bb283b3432d3073a7d","last_reissued_at":"2026-05-29T01:04:42.186350Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:42.186350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonia \\v{S}ar\\v{c}evi\\'c, Nikolina Frid","submitted_at":"2026-05-27T18:32:57Z","abstract_excerpt":"Recent advances in deep learning have enabled increasingly accurate electroencephalography (EEG)-based classification of Major Depressive Disorder (MDD), but the decision-making processes of high-capacity models remain difficult to interpret. This study investigates multiple post-hoc explainability methods applied to an InceptionTime architecture trained for EEG-based MDD detection. The analysis includes Shapley-based, gradient-based, and perturbation-based attribution approaches: DeepSHAP, Integrated Gradients, GradCAM, Occlusion, and Permutation Feature Importance. Explainability analysis wa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28977","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/2605.28977/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":"2605.28977","created_at":"2026-05-29T01:04:42.186427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28977v1","created_at":"2026-05-29T01:04:42.186427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28977","created_at":"2026-05-29T01:04:42.186427+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMCOOXMQKQPM","created_at":"2026-05-29T01:04:42.186427+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMCOOXMQKQPMNDPT","created_at":"2026-05-29T01:04:42.186427+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMCOOXMQ","created_at":"2026-05-29T01:04:42.186427+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/QMCOOXMQKQPMNDPTO3WYNOH2JK","json":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK.json","graph_json":"https://pith.science/api/pith-number/QMCOOXMQKQPMNDPTO3WYNOH2JK/graph.json","events_json":"https://pith.science/api/pith-number/QMCOOXMQKQPMNDPTO3WYNOH2JK/events.json","paper":"https://pith.science/paper/QMCOOXMQ"},"agent_actions":{"view_html":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK","download_json":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK.json","view_paper":"https://pith.science/paper/QMCOOXMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28977&json=true","fetch_graph":"https://pith.science/api/pith-number/QMCOOXMQKQPMNDPTO3WYNOH2JK/graph.json","fetch_events":"https://pith.science/api/pith-number/QMCOOXMQKQPMNDPTO3WYNOH2JK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK/action/storage_attestation","attest_author":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK/action/author_attestation","sign_citation":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK/action/citation_signature","submit_replication":"https://pith.science/pith/QMCOOXMQKQPMNDPTO3WYNOH2JK/action/replication_record"}},"created_at":"2026-05-29T01:04:42.186427+00:00","updated_at":"2026-05-29T01:04:42.186427+00:00"}