{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3R365WLNGNI7R7SEO2ULUFSU2M","short_pith_number":"pith:3R365WLN","schema_version":"1.0","canonical_sha256":"dc77eed96d3351f8fe4476a8ba1654d31267e5721c12f6d575cc8cf354f37817","source":{"kind":"arxiv","id":"2010.03023","version":1},"attestation_state":"computed","paper":{"title":"IS-CAM: Integrated Score-CAM for axiomatic-based explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankita Ghosh, Rakshit Naidu, Shamanth R Nayak K, Soumya Snigdha Kundu, Yash Maurya","submitted_at":"2020-10-06T21:03:03Z","abstract_excerpt":"Convolutional Neural Networks have been known as black-box models as humans cannot interpret their inner functionalities. With an attempt to make CNNs more interpretable and trustworthy, we propose IS-CAM (Integrated Score-CAM), where we introduce the integration operation within the Score-CAM pipeline to achieve visually sharper attribution maps quantitatively. Our method is evaluated on 2000 randomly selected images from the ILSVRC 2012 Validation dataset, which proves the versatility of IS-CAM to account for different models and methods."},"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":"2010.03023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-10-06T21:03:03Z","cross_cats_sorted":[],"title_canon_sha256":"e05c64d4d4a181ae4b579f5ea511e6ea1ddee8f18f10e44e32f1a0612b9936d9","abstract_canon_sha256":"e97c4cabc061e291f3d3a3a25e27eb6335a4b413558c1ebd59b5fb2090bc0195"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:58.718670Z","signature_b64":"NTORf8wj8xjeon9WhsLzAxLJRSwHi5wT1vh6Fg2A7C9gI5bY0B6j14AmhsYqRsd7TBRvtV1RtwF0Cjq6oi9bCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc77eed96d3351f8fe4476a8ba1654d31267e5721c12f6d575cc8cf354f37817","last_reissued_at":"2026-07-05T01:40:58.718198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:58.718198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IS-CAM: Integrated Score-CAM for axiomatic-based explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankita Ghosh, Rakshit Naidu, Shamanth R Nayak K, Soumya Snigdha Kundu, Yash Maurya","submitted_at":"2020-10-06T21:03:03Z","abstract_excerpt":"Convolutional Neural Networks have been known as black-box models as humans cannot interpret their inner functionalities. With an attempt to make CNNs more interpretable and trustworthy, we propose IS-CAM (Integrated Score-CAM), where we introduce the integration operation within the Score-CAM pipeline to achieve visually sharper attribution maps quantitatively. Our method is evaluated on 2000 randomly selected images from the ILSVRC 2012 Validation dataset, which proves the versatility of IS-CAM to account for different models and methods."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03023","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/2010.03023/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":"2010.03023","created_at":"2026-07-05T01:40:58.718257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03023v1","created_at":"2026-07-05T01:40:58.718257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03023","created_at":"2026-07-05T01:40:58.718257+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R365WLNGNI7","created_at":"2026-07-05T01:40:58.718257+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R365WLNGNI7R7SE","created_at":"2026-07-05T01:40:58.718257+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R365WLN","created_at":"2026-07-05T01:40:58.718257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02007","citing_title":"How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M","json":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M.json","graph_json":"https://pith.science/api/pith-number/3R365WLNGNI7R7SEO2ULUFSU2M/graph.json","events_json":"https://pith.science/api/pith-number/3R365WLNGNI7R7SEO2ULUFSU2M/events.json","paper":"https://pith.science/paper/3R365WLN"},"agent_actions":{"view_html":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M","download_json":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M.json","view_paper":"https://pith.science/paper/3R365WLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03023&json=true","fetch_graph":"https://pith.science/api/pith-number/3R365WLNGNI7R7SEO2ULUFSU2M/graph.json","fetch_events":"https://pith.science/api/pith-number/3R365WLNGNI7R7SEO2ULUFSU2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M/action/storage_attestation","attest_author":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M/action/author_attestation","sign_citation":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M/action/citation_signature","submit_replication":"https://pith.science/pith/3R365WLNGNI7R7SEO2ULUFSU2M/action/replication_record"}},"created_at":"2026-07-05T01:40:58.718257+00:00","updated_at":"2026-07-05T01:40:58.718257+00:00"}