{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UOTIKRXZ43M5CH4EWHMODECY4V","short_pith_number":"pith:UOTIKRXZ","canonical_record":{"source":{"id":"2506.06330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T01:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"b7149b1768859419e4e1ba214f22a274783984ae9e7407dd094eca7961331232","abstract_canon_sha256":"72fa97d543931ec8d866dcc80815040bff0cdc9cb0c4b499547811f6dbad66a5"},"schema_version":"1.0"},"canonical_sha256":"a3a68546f9e6d9d11f84b1d8e19058e55d11621b0e2bf5d8ed16b162bfe30dd3","source":{"kind":"arxiv","id":"2506.06330","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06330","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06330v1","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06330","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"UOTIKRXZ43M5","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"UOTIKRXZ43M5CH4E","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"UOTIKRXZ","created_at":"2026-07-05T11:17:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UOTIKRXZ43M5CH4EWHMODECY4V","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T01:12:23Z","cross_cats_sorted":[],"title_canon_sha256":"b7149b1768859419e4e1ba214f22a274783984ae9e7407dd094eca7961331232","abstract_canon_sha256":"72fa97d543931ec8d866dcc80815040bff0cdc9cb0c4b499547811f6dbad66a5"},"schema_version":"1.0"},"canonical_sha256":"a3a68546f9e6d9d11f84b1d8e19058e55d11621b0e2bf5d8ed16b162bfe30dd3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:48.150899Z","signature_b64":"aJJK+JmVtCN41OMwlJPBolmMcWXPrvLRACPKEvbJ/1zYC67qoRDdius/DghiGIVhRrMF0YZu8SiVHt6d9ns2Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a68546f9e6d9d11f84b1d8e19058e55d11621b0e2bf5d8ed16b162bfe30dd3","last_reissued_at":"2026-07-05T11:17:48.150495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:48.150495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06330","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukJa3CJuRss6o/Q/YIGAxjfo0RCh4moJKBWjxyaez8Et4M2UBSeWYl2daNfcjPLE4S36/fwspKc7YWhcqT+PBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:51.791099Z"},"content_sha256":"098db533808344e15c2298cc8fc771ce18e1fe4db80fea221815410b01d8d87c","schema_version":"1.0","event_id":"sha256:098db533808344e15c2298cc8fc771ce18e1fe4db80fea221815410b01d8d87c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UOTIKRXZ43M5CH4EWHMODECY4V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ExplainBench: A Benchmark Framework for Local Model Explanations in Fairness-Critical Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James Afful","submitted_at":"2025-05-31T01:12:23Z","abstract_excerpt":"As machine learning systems are increasingly deployed in high-stakes domains such as criminal justice, finance, and healthcare, the demand for interpretable and trustworthy models has intensified. Despite the proliferation of local explanation techniques, including SHAP, LIME, and counterfactual methods, there exists no standardized, reproducible framework for their comparative evaluation, particularly in fairness-sensitive settings.\n  We introduce ExplainBench, an open-source benchmarking suite for systematic evaluation of local model explanations across ethically consequential datasets. Expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06330","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/2506.06330/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xdi5u7ahR2dh3Y08ktExQxFoJq4OeK5HSgd1e+vR29/rXvNOiHIhd/R2azsCh349kXrNmSWoyBw0SCnzsI9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:18:51.791593Z"},"content_sha256":"41bf27c6241115b437cb2ead4f6a8229ba5500de001d594f89801450f4361ec6","schema_version":"1.0","event_id":"sha256:41bf27c6241115b437cb2ead4f6a8229ba5500de001d594f89801450f4361ec6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOTIKRXZ43M5CH4EWHMODECY4V/bundle.json","state_url":"https://pith.science/pith/UOTIKRXZ43M5CH4EWHMODECY4V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOTIKRXZ43M5CH4EWHMODECY4V/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:18:51Z","links":{"resolver":"https://pith.science/pith/UOTIKRXZ43M5CH4EWHMODECY4V","bundle":"https://pith.science/pith/UOTIKRXZ43M5CH4EWHMODECY4V/bundle.json","state":"https://pith.science/pith/UOTIKRXZ43M5CH4EWHMODECY4V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOTIKRXZ43M5CH4EWHMODECY4V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UOTIKRXZ43M5CH4EWHMODECY4V","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":"72fa97d543931ec8d866dcc80815040bff0cdc9cb0c4b499547811f6dbad66a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T01:12:23Z","title_canon_sha256":"b7149b1768859419e4e1ba214f22a274783984ae9e7407dd094eca7961331232"},"schema_version":"1.0","source":{"id":"2506.06330","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06330","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06330v1","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06330","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_12","alias_value":"UOTIKRXZ43M5","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_16","alias_value":"UOTIKRXZ43M5CH4E","created_at":"2026-07-05T11:17:48Z"},{"alias_kind":"pith_short_8","alias_value":"UOTIKRXZ","created_at":"2026-07-05T11:17:48Z"}],"graph_snapshots":[{"event_id":"sha256:41bf27c6241115b437cb2ead4f6a8229ba5500de001d594f89801450f4361ec6","target":"graph","created_at":"2026-07-05T11:17:48Z","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":[],"endpoint":"/pith/2506.06330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As machine learning systems are increasingly deployed in high-stakes domains such as criminal justice, finance, and healthcare, the demand for interpretable and trustworthy models has intensified. Despite the proliferation of local explanation techniques, including SHAP, LIME, and counterfactual methods, there exists no standardized, reproducible framework for their comparative evaluation, particularly in fairness-sensitive settings.\n  We introduce ExplainBench, an open-source benchmarking suite for systematic evaluation of local model explanations across ethically consequential datasets. Expl","authors_text":"James Afful","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T01:12:23Z","title":"ExplainBench: A Benchmark Framework for Local Model Explanations in Fairness-Critical Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06330","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":"sha256:098db533808344e15c2298cc8fc771ce18e1fe4db80fea221815410b01d8d87c","target":"record","created_at":"2026-07-05T11:17:48Z","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":"72fa97d543931ec8d866dcc80815040bff0cdc9cb0c4b499547811f6dbad66a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T01:12:23Z","title_canon_sha256":"b7149b1768859419e4e1ba214f22a274783984ae9e7407dd094eca7961331232"},"schema_version":"1.0","source":{"id":"2506.06330","kind":"arxiv","version":1}},"canonical_sha256":"a3a68546f9e6d9d11f84b1d8e19058e55d11621b0e2bf5d8ed16b162bfe30dd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3a68546f9e6d9d11f84b1d8e19058e55d11621b0e2bf5d8ed16b162bfe30dd3","first_computed_at":"2026-07-05T11:17:48.150495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:48.150495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aJJK+JmVtCN41OMwlJPBolmMcWXPrvLRACPKEvbJ/1zYC67qoRDdius/DghiGIVhRrMF0YZu8SiVHt6d9ns2Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:48.150899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06330","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:098db533808344e15c2298cc8fc771ce18e1fe4db80fea221815410b01d8d87c","sha256:41bf27c6241115b437cb2ead4f6a8229ba5500de001d594f89801450f4361ec6"],"state_sha256":"f03b01e15cf6f5f350df4ea37e49b650f382c006c1cb6ad0085cc8a536a6076f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ivbuYBgqIGZrhLWZNXjtqHNNVqGAQFcZloTDBxCsfTk0ZUW3v4lbBchcgq70qY0mRLjeNxHxGMmmaZr+t/gyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:18:51.795797Z","bundle_sha256":"69c38524b42488e53b7e8ff4143b8742f9dfc50b8a685e4a29e190cb124be643"}}