{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RG73DMVYZC7U3GY7ZAZ5BNSPK6","short_pith_number":"pith:RG73DMVY","schema_version":"1.0","canonical_sha256":"89bfb1b2b8c8bf4d9b1fc833d0b64f579a77d7c8f154c7a14d94e1d44aa2aecb","source":{"kind":"arxiv","id":"2501.15374","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jugal Kalita, Melkamu Abay Mersha, Mesay Gemeda Yigezu","submitted_at":"2025-01-26T03:08:34Z","abstract_excerpt":"The black-box nature of large language models (LLMs) necessitates the development of eXplainable AI (XAI) techniques for transparency and trustworthiness. However, evaluating these techniques remains a challenge. This study presents a general evaluation framework using four key metrics: Human-reasoning Agreement (HA), Robustness, Consistency, and Contrastivity. We assess the effectiveness of six explainability techniques from five different XAI categories model simplification (LIME), perturbation-based methods (SHAP), gradient-based approaches (InputXGradient, Grad-CAM), Layer-wise Relevance P"},"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":"2501.15374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-26T03:08:34Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"9ab36b5de14e390e9c6a59096c7475b7150dec9ded96a0e346ca33c640dfd968","abstract_canon_sha256":"35eedc8693748c41ab77f78a01a287953781fdc81036fa19c758cf62c63e3000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:30.499298Z","signature_b64":"f/A9ZQHUNjPT04Dc/KjcB5BO4L8a7flbabveX+CXI9ucl5ABlQxDrCG1eJ4eaueA7r+vwaiqvDZsnKXjFKaxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89bfb1b2b8c8bf4d9b1fc833d0b64f579a77d7c8f154c7a14d94e1d44aa2aecb","last_reissued_at":"2026-07-05T10:30:30.498723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:30.498723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jugal Kalita, Melkamu Abay Mersha, Mesay Gemeda Yigezu","submitted_at":"2025-01-26T03:08:34Z","abstract_excerpt":"The black-box nature of large language models (LLMs) necessitates the development of eXplainable AI (XAI) techniques for transparency and trustworthiness. However, evaluating these techniques remains a challenge. This study presents a general evaluation framework using four key metrics: Human-reasoning Agreement (HA), Robustness, Consistency, and Contrastivity. We assess the effectiveness of six explainability techniques from five different XAI categories model simplification (LIME), perturbation-based methods (SHAP), gradient-based approaches (InputXGradient, Grad-CAM), Layer-wise Relevance P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15374","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/2501.15374/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":"2501.15374","created_at":"2026-07-05T10:30:30.498792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15374v1","created_at":"2026-07-05T10:30:30.498792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15374","created_at":"2026-07-05T10:30:30.498792+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG73DMVYZC7U","created_at":"2026-07-05T10:30:30.498792+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG73DMVYZC7U3GY7","created_at":"2026-07-05T10:30:30.498792+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG73DMVY","created_at":"2026-07-05T10:30:30.498792+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/RG73DMVYZC7U3GY7ZAZ5BNSPK6","json":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6.json","graph_json":"https://pith.science/api/pith-number/RG73DMVYZC7U3GY7ZAZ5BNSPK6/graph.json","events_json":"https://pith.science/api/pith-number/RG73DMVYZC7U3GY7ZAZ5BNSPK6/events.json","paper":"https://pith.science/paper/RG73DMVY"},"agent_actions":{"view_html":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6","download_json":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6.json","view_paper":"https://pith.science/paper/RG73DMVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15374&json=true","fetch_graph":"https://pith.science/api/pith-number/RG73DMVYZC7U3GY7ZAZ5BNSPK6/graph.json","fetch_events":"https://pith.science/api/pith-number/RG73DMVYZC7U3GY7ZAZ5BNSPK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6/action/storage_attestation","attest_author":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6/action/author_attestation","sign_citation":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6/action/citation_signature","submit_replication":"https://pith.science/pith/RG73DMVYZC7U3GY7ZAZ5BNSPK6/action/replication_record"}},"created_at":"2026-07-05T10:30:30.498792+00:00","updated_at":"2026-07-05T10:30:30.498792+00:00"}