{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A7LT55KH6UWYQ7CH2FMQDO4VM7","short_pith_number":"pith:A7LT55KH","schema_version":"1.0","canonical_sha256":"07d73ef547f52d887c47d15901bb9567fd0ec88c5457faae2cefac8162f4b9b9","source":{"kind":"arxiv","id":"2508.13672","version":2},"attestation_state":"computed","paper":{"title":"ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanjin Wang, Hamid Laga, Kok Wai Wong, Marco Fisichella, Rehan Raza","submitted_at":"2025-08-19T09:18:20Z","abstract_excerpt":"Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior locally using interpretable surrogate models. However, LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues, especially in scenarios with limited training data. In such cases, data scarcity can result in the generation of unrealistic variations and samples that deviate from the true data manifold. Consequently, the surrogate model m"},"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":"2508.13672","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-19T09:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"538e0c5782b1a1071d620f5dd780edbd5007a15ad95484cbec3205dbe4dc3f77","abstract_canon_sha256":"47f5a80f4e0bbfeb783f22a4b89ff18b423ba380e81f00c4eb12157841adb51f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:02.137853Z","signature_b64":"LHY7xQpheIc9mPZR4KG0+FjgdHllC7fG7LDZGCrfey8poIbD/OiyB9i2j3RmSzHc/MDBEQ1duECQf8XCKZBkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07d73ef547f52d887c47d15901bb9567fd0ec88c5457faae2cefac8162f4b9b9","last_reissued_at":"2026-07-05T11:57:02.137513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:02.137513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanjin Wang, Hamid Laga, Kok Wai Wong, Marco Fisichella, Rehan Raza","submitted_at":"2025-08-19T09:18:20Z","abstract_excerpt":"Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior locally using interpretable surrogate models. However, LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues, especially in scenarios with limited training data. In such cases, data scarcity can result in the generation of unrealistic variations and samples that deviate from the true data manifold. Consequently, the surrogate model m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13672","kind":"arxiv","version":2},"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/2508.13672/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":"2508.13672","created_at":"2026-07-05T11:57:02.137567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13672v2","created_at":"2026-07-05T11:57:02.137567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13672","created_at":"2026-07-05T11:57:02.137567+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7LT55KH6UWY","created_at":"2026-07-05T11:57:02.137567+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7LT55KH6UWYQ7CH","created_at":"2026-07-05T11:57:02.137567+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7LT55KH","created_at":"2026-07-05T11:57:02.137567+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/A7LT55KH6UWYQ7CH2FMQDO4VM7","json":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7.json","graph_json":"https://pith.science/api/pith-number/A7LT55KH6UWYQ7CH2FMQDO4VM7/graph.json","events_json":"https://pith.science/api/pith-number/A7LT55KH6UWYQ7CH2FMQDO4VM7/events.json","paper":"https://pith.science/paper/A7LT55KH"},"agent_actions":{"view_html":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7","download_json":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7.json","view_paper":"https://pith.science/paper/A7LT55KH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13672&json=true","fetch_graph":"https://pith.science/api/pith-number/A7LT55KH6UWYQ7CH2FMQDO4VM7/graph.json","fetch_events":"https://pith.science/api/pith-number/A7LT55KH6UWYQ7CH2FMQDO4VM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7/action/storage_attestation","attest_author":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7/action/author_attestation","sign_citation":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7/action/citation_signature","submit_replication":"https://pith.science/pith/A7LT55KH6UWYQ7CH2FMQDO4VM7/action/replication_record"}},"created_at":"2026-07-05T11:57:02.137567+00:00","updated_at":"2026-07-05T11:57:02.137567+00:00"}