{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DTX3IQ2R7EN2HJE2Z36JA5RPFS","short_pith_number":"pith:DTX3IQ2R","schema_version":"1.0","canonical_sha256":"1cefb44351f91ba3a49acefc90762f2ca6337773915ebfb8affe325a0345881e","source":{"kind":"arxiv","id":"2211.01413","version":2},"attestation_state":"computed","paper":{"title":"Harnessing the Power of Explanations for Incremental Training: A LIME-Based Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arnab Neelim Mazumder, Ashutosh Pandey, Avik Santra, Niall Lyons, Tinoosh Mohsenin","submitted_at":"2022-11-02T18:16:17Z","abstract_excerpt":"Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization, and there is scarce work that looks to use these explanations as feedback to improve model performance. In this work, model explanations are fed back to the feed-forward training to help the model generalize better. To this extent, a custom weighted loss where the weights are generated by considering the Euclidean distances between true LIME (Local Interpret"},"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":"2211.01413","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-02T18:16:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"395ce48c12c8831695ea19ec27273e07d9985e95a606faa82c0b570c501bc274","abstract_canon_sha256":"792d58170f6f630de5e5629a0a3fd4ced884bd5da9e93c6eb69fb0da74e1dd9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:02.695434Z","signature_b64":"FMNNSKLBjURtqbRsuWVDBtlaL7eX74zBm7IL2zR6l5v2y5GCqvsoZTNB+R5PCeQPizIQJUkKkGNcCKGL1VWHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cefb44351f91ba3a49acefc90762f2ca6337773915ebfb8affe325a0345881e","last_reissued_at":"2026-07-05T06:30:02.694963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:02.694963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing the Power of Explanations for Incremental Training: A LIME-Based Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arnab Neelim Mazumder, Ashutosh Pandey, Avik Santra, Niall Lyons, Tinoosh Mohsenin","submitted_at":"2022-11-02T18:16:17Z","abstract_excerpt":"Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization, and there is scarce work that looks to use these explanations as feedback to improve model performance. In this work, model explanations are fed back to the feed-forward training to help the model generalize better. To this extent, a custom weighted loss where the weights are generated by considering the Euclidean distances between true LIME (Local Interpret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01413","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/2211.01413/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":"2211.01413","created_at":"2026-07-05T06:30:02.695019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01413v2","created_at":"2026-07-05T06:30:02.695019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01413","created_at":"2026-07-05T06:30:02.695019+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTX3IQ2R7EN2","created_at":"2026-07-05T06:30:02.695019+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTX3IQ2R7EN2HJE2","created_at":"2026-07-05T06:30:02.695019+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTX3IQ2R","created_at":"2026-07-05T06:30:02.695019+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/DTX3IQ2R7EN2HJE2Z36JA5RPFS","json":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS.json","graph_json":"https://pith.science/api/pith-number/DTX3IQ2R7EN2HJE2Z36JA5RPFS/graph.json","events_json":"https://pith.science/api/pith-number/DTX3IQ2R7EN2HJE2Z36JA5RPFS/events.json","paper":"https://pith.science/paper/DTX3IQ2R"},"agent_actions":{"view_html":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS","download_json":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS.json","view_paper":"https://pith.science/paper/DTX3IQ2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01413&json=true","fetch_graph":"https://pith.science/api/pith-number/DTX3IQ2R7EN2HJE2Z36JA5RPFS/graph.json","fetch_events":"https://pith.science/api/pith-number/DTX3IQ2R7EN2HJE2Z36JA5RPFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS/action/storage_attestation","attest_author":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS/action/author_attestation","sign_citation":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS/action/citation_signature","submit_replication":"https://pith.science/pith/DTX3IQ2R7EN2HJE2Z36JA5RPFS/action/replication_record"}},"created_at":"2026-07-05T06:30:02.695019+00:00","updated_at":"2026-07-05T06:30:02.695019+00:00"}