{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YN5XMAGANLTRW7O7YK3KPJECAF","short_pith_number":"pith:YN5XMAGA","schema_version":"1.0","canonical_sha256":"c37b7600c06ae71b7ddfc2b6a7a4820173fccb480b54c7f7bd047eeb9d2ff40f","source":{"kind":"arxiv","id":"2006.14255","version":3},"attestation_state":"computed","paper":{"title":"SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haofan Wang, Joy Michael, Rakshit Naidu, Soumya Snigdha Kundu","submitted_at":"2020-06-25T08:51:54Z","abstract_excerpt":"Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications in high-risk environments. To explain these black-box architectures there have been many methods applied so the internal decisions can be analyzed and understood. In this paper, built on the top of Score-CAM, we introduce an enhanced visual explanation in terms of visual sharpness called SS-CAM, which produces centralized localization of object features within an image through a smooth operation. We evaluate our met"},"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":"2006.14255","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-06-25T08:51:54Z","cross_cats_sorted":[],"title_canon_sha256":"0ed0b86c6fc270de4c3a9e6ff6848bcf10741f8d259b8fc397bffe4408d37063","abstract_canon_sha256":"ead803e28f4a5bf2d03e832b495acb5a71900d98da88e59ebfa3e51bbe390daa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:07.988023Z","signature_b64":"+9vu1+O0VEbhUVCJsbz3/+wy9ZygoD5o7U3k3tY6XOlOQ72uMIkg+94ciJ3L+oN3mkA06XqXfODhAvaa/7TECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c37b7600c06ae71b7ddfc2b6a7a4820173fccb480b54c7f7bd047eeb9d2ff40f","last_reissued_at":"2026-07-05T01:51:07.987530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:07.987530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haofan Wang, Joy Michael, Rakshit Naidu, Soumya Snigdha Kundu","submitted_at":"2020-06-25T08:51:54Z","abstract_excerpt":"Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications in high-risk environments. To explain these black-box architectures there have been many methods applied so the internal decisions can be analyzed and understood. In this paper, built on the top of Score-CAM, we introduce an enhanced visual explanation in terms of visual sharpness called SS-CAM, which produces centralized localization of object features within an image through a smooth operation. We evaluate our met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14255","kind":"arxiv","version":3},"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/2006.14255/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":"2006.14255","created_at":"2026-07-05T01:51:07.987590+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14255v3","created_at":"2026-07-05T01:51:07.987590+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14255","created_at":"2026-07-05T01:51:07.987590+00:00"},{"alias_kind":"pith_short_12","alias_value":"YN5XMAGANLTR","created_at":"2026-07-05T01:51:07.987590+00:00"},{"alias_kind":"pith_short_16","alias_value":"YN5XMAGANLTRW7O7","created_at":"2026-07-05T01:51:07.987590+00:00"},{"alias_kind":"pith_short_8","alias_value":"YN5XMAGA","created_at":"2026-07-05T01:51:07.987590+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.18816","citing_title":"Grad-ECLIP: Gradient-based Visual and Textual Explanations for CLIP","ref_index":37,"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":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF","json":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF.json","graph_json":"https://pith.science/api/pith-number/YN5XMAGANLTRW7O7YK3KPJECAF/graph.json","events_json":"https://pith.science/api/pith-number/YN5XMAGANLTRW7O7YK3KPJECAF/events.json","paper":"https://pith.science/paper/YN5XMAGA"},"agent_actions":{"view_html":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF","download_json":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF.json","view_paper":"https://pith.science/paper/YN5XMAGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14255&json=true","fetch_graph":"https://pith.science/api/pith-number/YN5XMAGANLTRW7O7YK3KPJECAF/graph.json","fetch_events":"https://pith.science/api/pith-number/YN5XMAGANLTRW7O7YK3KPJECAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF/action/storage_attestation","attest_author":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF/action/author_attestation","sign_citation":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF/action/citation_signature","submit_replication":"https://pith.science/pith/YN5XMAGANLTRW7O7YK3KPJECAF/action/replication_record"}},"created_at":"2026-07-05T01:51:07.987590+00:00","updated_at":"2026-07-05T01:51:07.987590+00:00"}