{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PVEUUYAO26MYAUKIF3BKPESIZW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3761405b0d850156cc28151a17b5bf6fa3ecb9ff97421c349fd8138efcfbb8ca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T17:21:48Z","title_canon_sha256":"b2f4f743de2b3428e2c17950853c7a6d345f2503f3a0bee9a2bd7f35a43b92df"},"schema_version":"1.0","source":{"id":"2605.18681","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18681","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18681v1","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18681","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"PVEUUYAO26MY","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"PVEUUYAO26MYAUKI","created_at":"2026-05-20T00:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"PVEUUYAO","created_at":"2026-05-20T00:06:14Z"}],"graph_snapshots":[{"event_id":"sha256:317dfcb3d8881482cd46d20635e92d7710a18b8641de8d344496316de962900b","target":"graph","created_at":"2026-05-20T00:06:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.115781Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18681/integrity.json","findings":[],"snapshot_sha256":"0d182dd2f5d84f1b15c054289b830e403a5a95822ecb7461158975f853685481","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Explainable AI (XAI) techniques are increasingly important for the validation and responsible use of modern deep learning models, but are difficult to evaluate due to the lack of good ground-truth to compare against. We propose a framework that serves as a quantifiable metric for the quality of XAI methods, based on continuous input perturbation. Our metric formally considers the sufficiency and necessity of the attributed information to the model's decision-making, and we illustrate a range of cases where it aligns better with human intuitions of explanation quality than do existing metrics.\n","authors_text":"Amritpal Singh, Andrey Barsky, Dimosthenis Karatzas, Ernest Valveny, Mohamed Ali Souibgui","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T17:21:48Z","title":"Learning Quantifiable Visual Explanations Without Ground-Truth"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18681","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a8300becf39570bb0b29c31fdf396719562875adacd0b4410629dbc1e683b370","target":"record","created_at":"2026-05-20T00:06:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3761405b0d850156cc28151a17b5bf6fa3ecb9ff97421c349fd8138efcfbb8ca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-18T17:21:48Z","title_canon_sha256":"b2f4f743de2b3428e2c17950853c7a6d345f2503f3a0bee9a2bd7f35a43b92df"},"schema_version":"1.0","source":{"id":"2605.18681","kind":"arxiv","version":1}},"canonical_sha256":"7d494a600ed7998051482ec2a79248cda9c1f06a9565f7cbce04c37ca5bbdc68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d494a600ed7998051482ec2a79248cda9c1f06a9565f7cbce04c37ca5bbdc68","first_computed_at":"2026-05-20T00:06:14.573061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:14.573061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tdULb5Cz0nk+AyH3qyXlBs597zPEynaleQ9rNoMkw+y0uQTqZZOJHQ90KRAxEmAwjT7mldNKoZtNE8p9VUjBAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:14.573849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18681","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8300becf39570bb0b29c31fdf396719562875adacd0b4410629dbc1e683b370","sha256:317dfcb3d8881482cd46d20635e92d7710a18b8641de8d344496316de962900b"],"state_sha256":"c76f0c56ff377d6c13f5025501611056870d75a2f1dd7fb29a807c9997ba8823"}