{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IZJS7LCTBRGZ65J4MSB4ZNS65B","short_pith_number":"pith:IZJS7LCT","schema_version":"1.0","canonical_sha256":"46532fac530c4d9f753c6483ccb65ee85ae614dcbc23d71901270eaa8a3cb206","source":{"kind":"arxiv","id":"2412.18952","version":1},"attestation_state":"computed","paper":{"title":"Bridging Interpretability and Robustness Using LIME-Guided Model Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abdullah Rakin, Longwei Wang, Navid Nayyem","submitted_at":"2024-12-25T17:32:45Z","abstract_excerpt":"This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities, including susceptibility to adversarial attacks, over-reliance on spurious correlations, and a lack of transparency in their decision-making processes. To address these limitations, we propose a novel framework that leverages Local Interpretable Model-Agnostic Explanations (LIME) to systematically enhance model robustness. By identifying and mitigating the influence"},"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":"2412.18952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-25T17:32:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"83cd6f6b142d47149943b9afd54b7c46445c3e9e5beb9942bdbd798294177808","abstract_canon_sha256":"7558327a43906f61760341e2482a8fbf305d9003da18ed47046aaac99da30357"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:13.711843Z","signature_b64":"JOm17JFe1Pt5uA7mcPYOzhembzmAHiaULjy4XiYZwkqRhd34Efx0HP/v+Olt2jpfSM9O8bZ/uS8vAmEd1trDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46532fac530c4d9f753c6483ccb65ee85ae614dcbc23d71901270eaa8a3cb206","last_reissued_at":"2026-07-05T09:54:13.711416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:13.711416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Interpretability and Robustness Using LIME-Guided Model Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abdullah Rakin, Longwei Wang, Navid Nayyem","submitted_at":"2024-12-25T17:32:45Z","abstract_excerpt":"This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities, including susceptibility to adversarial attacks, over-reliance on spurious correlations, and a lack of transparency in their decision-making processes. To address these limitations, we propose a novel framework that leverages Local Interpretable Model-Agnostic Explanations (LIME) to systematically enhance model robustness. By identifying and mitigating the influence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18952","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/2412.18952/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":"2412.18952","created_at":"2026-07-05T09:54:13.711475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18952v1","created_at":"2026-07-05T09:54:13.711475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18952","created_at":"2026-07-05T09:54:13.711475+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZJS7LCTBRGZ","created_at":"2026-07-05T09:54:13.711475+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZJS7LCTBRGZ65J4","created_at":"2026-07-05T09:54:13.711475+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZJS7LCT","created_at":"2026-07-05T09:54:13.711475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07903","citing_title":"Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B","json":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B.json","graph_json":"https://pith.science/api/pith-number/IZJS7LCTBRGZ65J4MSB4ZNS65B/graph.json","events_json":"https://pith.science/api/pith-number/IZJS7LCTBRGZ65J4MSB4ZNS65B/events.json","paper":"https://pith.science/paper/IZJS7LCT"},"agent_actions":{"view_html":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B","download_json":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B.json","view_paper":"https://pith.science/paper/IZJS7LCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18952&json=true","fetch_graph":"https://pith.science/api/pith-number/IZJS7LCTBRGZ65J4MSB4ZNS65B/graph.json","fetch_events":"https://pith.science/api/pith-number/IZJS7LCTBRGZ65J4MSB4ZNS65B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B/action/storage_attestation","attest_author":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B/action/author_attestation","sign_citation":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B/action/citation_signature","submit_replication":"https://pith.science/pith/IZJS7LCTBRGZ65J4MSB4ZNS65B/action/replication_record"}},"created_at":"2026-07-05T09:54:13.711475+00:00","updated_at":"2026-07-05T09:54:13.711475+00:00"}