{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PBAMEC3KXFTKMUCMEMKFJUVVFX","short_pith_number":"pith:PBAMEC3K","schema_version":"1.0","canonical_sha256":"7840c20b6ab966a6504c231454d2b52dea031a475595dfd7c9fab7f142cd4873","source":{"kind":"arxiv","id":"1908.01224","version":1},"attestation_state":"computed","paper":{"title":"Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Celia Cintas, Daniel Omeiza, Komminist Weldermariam, Skyler Speakman","submitted_at":"2019-08-03T20:09:40Z","abstract_excerpt":"Gaining insight into how deep convolutional neural network models perform image classification and how to explain their outputs have been a concern to computer vision researchers and decision makers. These deep models are often referred to as black box due to low comprehension of their internal workings. As an effort to developing explainable deep learning models, several methods have been proposed such as finding gradients of class output with respect to input image (sensitivity maps), class activation map (CAM), and Gradient based Class Activation Maps (Grad-CAM). These methods under perform"},"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":"1908.01224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-03T20:09:40Z","cross_cats_sorted":[],"title_canon_sha256":"4ce0c682f984ebab11de569d4d5cffb3a281f70b5f5ae50dfa99f0849e554b12","abstract_canon_sha256":"326cea76bc9b7d5c4a98682b063364bba0f58c4c5666236f66d73b1c56a45d1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:28.226830Z","signature_b64":"LT1Be22AUx+Ws0OBkAO4DICKxTqcBrQrVR267Ln49u0TETRwFidVYjxUJD3JePze3Pj07i5Yk/ox01X2/3ISCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7840c20b6ab966a6504c231454d2b52dea031a475595dfd7c9fab7f142cd4873","last_reissued_at":"2026-07-04T23:51:28.226412Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:28.226412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Celia Cintas, Daniel Omeiza, Komminist Weldermariam, Skyler Speakman","submitted_at":"2019-08-03T20:09:40Z","abstract_excerpt":"Gaining insight into how deep convolutional neural network models perform image classification and how to explain their outputs have been a concern to computer vision researchers and decision makers. These deep models are often referred to as black box due to low comprehension of their internal workings. As an effort to developing explainable deep learning models, several methods have been proposed such as finding gradients of class output with respect to input image (sensitivity maps), class activation map (CAM), and Gradient based Class Activation Maps (Grad-CAM). These methods under perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01224","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/1908.01224/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":"1908.01224","created_at":"2026-07-04T23:51:28.226468+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01224v1","created_at":"2026-07-04T23:51:28.226468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01224","created_at":"2026-07-04T23:51:28.226468+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBAMEC3KXFTK","created_at":"2026-07-04T23:51:28.226468+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBAMEC3KXFTKMUCM","created_at":"2026-07-04T23:51:28.226468+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBAMEC3K","created_at":"2026-07-04T23:51:28.226468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18008","citing_title":"PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07451","citing_title":"TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16905","citing_title":"AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14787","citing_title":"FOCUS: Fused Observation of Channels for Unveiling Spectra","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02007","citing_title":"How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX","json":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX.json","graph_json":"https://pith.science/api/pith-number/PBAMEC3KXFTKMUCMEMKFJUVVFX/graph.json","events_json":"https://pith.science/api/pith-number/PBAMEC3KXFTKMUCMEMKFJUVVFX/events.json","paper":"https://pith.science/paper/PBAMEC3K"},"agent_actions":{"view_html":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX","download_json":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX.json","view_paper":"https://pith.science/paper/PBAMEC3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01224&json=true","fetch_graph":"https://pith.science/api/pith-number/PBAMEC3KXFTKMUCMEMKFJUVVFX/graph.json","fetch_events":"https://pith.science/api/pith-number/PBAMEC3KXFTKMUCMEMKFJUVVFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX/action/storage_attestation","attest_author":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX/action/author_attestation","sign_citation":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX/action/citation_signature","submit_replication":"https://pith.science/pith/PBAMEC3KXFTKMUCMEMKFJUVVFX/action/replication_record"}},"created_at":"2026-07-04T23:51:28.226468+00:00","updated_at":"2026-07-04T23:51:28.226468+00:00"}