{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KE5UN6PMZFCGWCPS3ZMKGULXHB","short_pith_number":"pith:KE5UN6PM","canonical_record":{"source":{"id":"2605.27618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T19:38:10Z","cross_cats_sorted":[],"title_canon_sha256":"73187c13768921288e684c052fe260346ec1a859a8243efc4a3a095e11734d4c","abstract_canon_sha256":"f3f797de262418063a6a5dc8e61dac338006b3c9b9a0d743b945dcb0dfa93475"},"schema_version":"1.0"},"canonical_sha256":"513b46f9ecc9446b09f2de58a35177387e6d8c2fa16fcd41a4d9e8d790e49679","source":{"kind":"arxiv","id":"2605.27618","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27618","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27618v1","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27618","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"KE5UN6PMZFCG","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"KE5UN6PMZFCGWCPS","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"KE5UN6PM","created_at":"2026-05-28T01:04:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KE5UN6PMZFCGWCPS3ZMKGULXHB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T19:38:10Z","cross_cats_sorted":[],"title_canon_sha256":"73187c13768921288e684c052fe260346ec1a859a8243efc4a3a095e11734d4c","abstract_canon_sha256":"f3f797de262418063a6a5dc8e61dac338006b3c9b9a0d743b945dcb0dfa93475"},"schema_version":"1.0"},"canonical_sha256":"513b46f9ecc9446b09f2de58a35177387e6d8c2fa16fcd41a4d9e8d790e49679","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:18.423875Z","signature_b64":"I7zhVrcmZuFhqj5jNDKR5wfs4FaYhswkJ7XJfHlu4PIwDfGw400rF/8eNUfHx9f4Zc2mtXNMwyd9Fihq/4A4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"513b46f9ecc9446b09f2de58a35177387e6d8c2fa16fcd41a4d9e8d790e49679","last_reissued_at":"2026-05-28T01:04:18.423202Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:18.423202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27618","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":"2026-05-28T01:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iSokHvAm4p+VOaAw7BhHL2PxJtJ9vuqVGA3kWrWHnEXzSLMWzhtAhVVDdN7nkCFZwVEUJ1UItomfkFAWuA1zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:19:56.767182Z"},"content_sha256":"22b787ad699a2de1965f5954387405015613c2f28c945ab70cb0fb09ec58a590","schema_version":"1.0","event_id":"sha256:22b787ad699a2de1965f5954387405015613c2f28c945ab70cb0fb09ec58a590"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KE5UN6PMZFCGWCPS3ZMKGULXHB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eva Maia, Isabel Pra\\c{c}a, Jo\\~ao Vitorino, Tom\\'as Pereira","submitted_at":"2026-05-26T19:38:10Z","abstract_excerpt":"Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable. An explanation can appear plausible to humans but fail to capture the internal reasoning of a model, particularly when dealing with complex tabular data. This paper studies the trustworthiness of local explainability techniques when applied to complex tabular classification tasks, considering evaluated metrics for three main properties: faithfulness to the model's predictions, robustness to input data variations, and com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27618","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/2605.27618/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":"2026-05-28T01:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MqZYvC5awMKKd9MRypydXchszBI/YwNgiU1mRBiZpvSHtHNKoywm3qlvFVVx7g233hlEAqIH7/5lx9FySxCkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:19:56.767588Z"},"content_sha256":"1142a85708b80c7838459acf530ba789f748d3cd7462017541dfbd28a28d743c","schema_version":"1.0","event_id":"sha256:1142a85708b80c7838459acf530ba789f748d3cd7462017541dfbd28a28d743c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KE5UN6PMZFCGWCPS3ZMKGULXHB/bundle.json","state_url":"https://pith.science/pith/KE5UN6PMZFCGWCPS3ZMKGULXHB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KE5UN6PMZFCGWCPS3ZMKGULXHB/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":"2026-05-30T13:19:56Z","links":{"resolver":"https://pith.science/pith/KE5UN6PMZFCGWCPS3ZMKGULXHB","bundle":"https://pith.science/pith/KE5UN6PMZFCGWCPS3ZMKGULXHB/bundle.json","state":"https://pith.science/pith/KE5UN6PMZFCGWCPS3ZMKGULXHB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KE5UN6PMZFCGWCPS3ZMKGULXHB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KE5UN6PMZFCGWCPS3ZMKGULXHB","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":"f3f797de262418063a6a5dc8e61dac338006b3c9b9a0d743b945dcb0dfa93475","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T19:38:10Z","title_canon_sha256":"73187c13768921288e684c052fe260346ec1a859a8243efc4a3a095e11734d4c"},"schema_version":"1.0","source":{"id":"2605.27618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27618","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27618v1","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27618","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"KE5UN6PMZFCG","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"KE5UN6PMZFCGWCPS","created_at":"2026-05-28T01:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"KE5UN6PM","created_at":"2026-05-28T01:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:1142a85708b80c7838459acf530ba789f748d3cd7462017541dfbd28a28d743c","target":"graph","created_at":"2026-05-28T01:04:18Z","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/2605.27618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable. An explanation can appear plausible to humans but fail to capture the internal reasoning of a model, particularly when dealing with complex tabular data. This paper studies the trustworthiness of local explainability techniques when applied to complex tabular classification tasks, considering evaluated metrics for three main properties: faithfulness to the model's predictions, robustness to input data variations, and com","authors_text":"Eva Maia, Isabel Pra\\c{c}a, Jo\\~ao Vitorino, Tom\\'as Pereira","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T19:38:10Z","title":"Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27618","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":"sha256:22b787ad699a2de1965f5954387405015613c2f28c945ab70cb0fb09ec58a590","target":"record","created_at":"2026-05-28T01:04:18Z","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":"f3f797de262418063a6a5dc8e61dac338006b3c9b9a0d743b945dcb0dfa93475","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T19:38:10Z","title_canon_sha256":"73187c13768921288e684c052fe260346ec1a859a8243efc4a3a095e11734d4c"},"schema_version":"1.0","source":{"id":"2605.27618","kind":"arxiv","version":1}},"canonical_sha256":"513b46f9ecc9446b09f2de58a35177387e6d8c2fa16fcd41a4d9e8d790e49679","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"513b46f9ecc9446b09f2de58a35177387e6d8c2fa16fcd41a4d9e8d790e49679","first_computed_at":"2026-05-28T01:04:18.423202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:18.423202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I7zhVrcmZuFhqj5jNDKR5wfs4FaYhswkJ7XJfHlu4PIwDfGw400rF/8eNUfHx9f4Zc2mtXNMwyd9Fihq/4A4Aw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:18.423875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22b787ad699a2de1965f5954387405015613c2f28c945ab70cb0fb09ec58a590","sha256:1142a85708b80c7838459acf530ba789f748d3cd7462017541dfbd28a28d743c"],"state_sha256":"d67d8561ee8cc40c797ec2716e4c3b9c2aebe010f1f219e28b3a0bbdac38ee21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOII2YRkW8v0ybY7IAbu8VLbr13By3f5KHB7hL+47dilqp5Vs97tS+6pkXRbdi9lSSY8G/K9FKY0hbgEtGNiDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:19:56.769758Z","bundle_sha256":"307f2ce5f49d9be6e8689eeb6b0af824578e40ac1888bd745fc6018974b652e2"}}