{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3AVFKDUDRVNTKINIEPVDPO4SDW","short_pith_number":"pith:3AVFKDUD","schema_version":"1.0","canonical_sha256":"d82a550e838d5b3521a823ea37bb921db890b663aa97a96a99e84f294b924b56","source":{"kind":"arxiv","id":"2412.18036","version":2},"attestation_state":"computed","paper":{"title":"Explainability in Neural Networks for Natural Language Processing Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jugal Kalita, Melkamu Mersha, Mingiziem Bitewa, Tsion Abay","submitted_at":"2024-12-23T23:09:56Z","abstract_excerpt":"Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation techniques like Local Interpretable Model-Agnostic Explanations (LIME) have emerged as essential tools for providing insights into the behavior of these complex systems. This study leverages LIME to interpret a multi-layer perceptron (MLP) neural network trained on a text classification task. By analyzing the contribution of individual features to model predictions"},"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":"2412.18036","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T23:09:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a26b36df9aaa2763ed795cddb163d1824101c76b17c732b9093e76ff5f9d7a95","abstract_canon_sha256":"43690c0df8fd33ebf3343ab56138eb40960913924fb0364645be9508271c94f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:44.377596Z","signature_b64":"yhNFLUrojQOMRzFFnzL+BdrgRr8tAToAxwSeb83pAs3SqvbpAPSHychCF+bB3PIVx16NQA47nPuwwEIWa/pyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d82a550e838d5b3521a823ea37bb921db890b663aa97a96a99e84f294b924b56","last_reissued_at":"2026-07-05T09:58:44.377105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:44.377105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainability in Neural Networks for Natural Language Processing Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jugal Kalita, Melkamu Mersha, Mingiziem Bitewa, Tsion Abay","submitted_at":"2024-12-23T23:09:56Z","abstract_excerpt":"Neural networks are widely regarded as black-box models, creating significant challenges in understanding their inner workings, especially in natural language processing (NLP) applications. To address this opacity, model explanation techniques like Local Interpretable Model-Agnostic Explanations (LIME) have emerged as essential tools for providing insights into the behavior of these complex systems. This study leverages LIME to interpret a multi-layer perceptron (MLP) neural network trained on a text classification task. By analyzing the contribution of individual features to model predictions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18036","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/2412.18036/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":"2412.18036","created_at":"2026-07-05T09:58:44.377163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18036v2","created_at":"2026-07-05T09:58:44.377163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18036","created_at":"2026-07-05T09:58:44.377163+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AVFKDUDRVNT","created_at":"2026-07-05T09:58:44.377163+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AVFKDUDRVNTKINI","created_at":"2026-07-05T09:58:44.377163+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AVFKDUD","created_at":"2026-07-05T09:58:44.377163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.16608","citing_title":"Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW","json":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW.json","graph_json":"https://pith.science/api/pith-number/3AVFKDUDRVNTKINIEPVDPO4SDW/graph.json","events_json":"https://pith.science/api/pith-number/3AVFKDUDRVNTKINIEPVDPO4SDW/events.json","paper":"https://pith.science/paper/3AVFKDUD"},"agent_actions":{"view_html":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW","download_json":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW.json","view_paper":"https://pith.science/paper/3AVFKDUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18036&json=true","fetch_graph":"https://pith.science/api/pith-number/3AVFKDUDRVNTKINIEPVDPO4SDW/graph.json","fetch_events":"https://pith.science/api/pith-number/3AVFKDUDRVNTKINIEPVDPO4SDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW/action/storage_attestation","attest_author":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW/action/author_attestation","sign_citation":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW/action/citation_signature","submit_replication":"https://pith.science/pith/3AVFKDUDRVNTKINIEPVDPO4SDW/action/replication_record"}},"created_at":"2026-07-05T09:58:44.377163+00:00","updated_at":"2026-07-05T09:58:44.377163+00:00"}