{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y6B47KDPHCEFVNLXTO376MSRFM","short_pith_number":"pith:Y6B47KDP","schema_version":"1.0","canonical_sha256":"c783cfa86f38885ab5779bb7ff32512b2dc2275e65bf962e74272314588b531c","source":{"kind":"arxiv","id":"2508.18154","version":1},"attestation_state":"computed","paper":{"title":"Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bhupender Kaushal, Kiran Raja, Revoti P. Bora, Sudhish N George, Syamantak Sarkar","submitted_at":"2025-08-25T15:59:06Z","abstract_excerpt":"Class Activation Maps (CAMs) are one of the important methods for visualizing regions used by deep learning models. Yet their robustness to different noise remains underexplored. In this work, we evaluate and report the resilience of various CAM methods for different noise perturbations across multiple architectures and datasets. By analyzing the influence of different noise types on CAM explanations, we assess the susceptibility to noise and the extent to which dataset characteristics may impact explanation stability. The findings highlight considerable variability in noise sensitivity for va"},"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":"2508.18154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-25T15:59:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4670e1fdcb6775cc05b668e68381f1fda1b64d23d26385d4d08ca5f97b2d070a","abstract_canon_sha256":"640d6db1df6f94bff23a0d862fb9b869332293ff90e851681a465dea451910a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:54.615850Z","signature_b64":"OF6dgWaPD8ylk8/VASrZ8SRPWj3spB5j53OFcH912WoPDBBiTr4gdfvATzvBrc+BB2Dq6LDas5aTi82QmgrjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c783cfa86f38885ab5779bb7ff32512b2dc2275e65bf962e74272314588b531c","last_reissued_at":"2026-07-05T11:58:54.615383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:54.615383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Noise Robustness of Class Activation Maps: A Framework for Reliable Model Interpretability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bhupender Kaushal, Kiran Raja, Revoti P. Bora, Sudhish N George, Syamantak Sarkar","submitted_at":"2025-08-25T15:59:06Z","abstract_excerpt":"Class Activation Maps (CAMs) are one of the important methods for visualizing regions used by deep learning models. Yet their robustness to different noise remains underexplored. In this work, we evaluate and report the resilience of various CAM methods for different noise perturbations across multiple architectures and datasets. By analyzing the influence of different noise types on CAM explanations, we assess the susceptibility to noise and the extent to which dataset characteristics may impact explanation stability. The findings highlight considerable variability in noise sensitivity for va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18154","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/2508.18154/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":"2508.18154","created_at":"2026-07-05T11:58:54.615440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18154v1","created_at":"2026-07-05T11:58:54.615440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18154","created_at":"2026-07-05T11:58:54.615440+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6B47KDPHCEF","created_at":"2026-07-05T11:58:54.615440+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6B47KDPHCEFVNLX","created_at":"2026-07-05T11:58:54.615440+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6B47KDP","created_at":"2026-07-05T11:58:54.615440+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/Y6B47KDPHCEFVNLXTO376MSRFM","json":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM.json","graph_json":"https://pith.science/api/pith-number/Y6B47KDPHCEFVNLXTO376MSRFM/graph.json","events_json":"https://pith.science/api/pith-number/Y6B47KDPHCEFVNLXTO376MSRFM/events.json","paper":"https://pith.science/paper/Y6B47KDP"},"agent_actions":{"view_html":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM","download_json":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM.json","view_paper":"https://pith.science/paper/Y6B47KDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18154&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6B47KDPHCEFVNLXTO376MSRFM/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6B47KDPHCEFVNLXTO376MSRFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM/action/storage_attestation","attest_author":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM/action/author_attestation","sign_citation":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM/action/citation_signature","submit_replication":"https://pith.science/pith/Y6B47KDPHCEFVNLXTO376MSRFM/action/replication_record"}},"created_at":"2026-07-05T11:58:54.615440+00:00","updated_at":"2026-07-05T11:58:54.615440+00:00"}