{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XH6S3GLEDGCPOEK4UPJAZLH3KC","short_pith_number":"pith:XH6S3GLE","schema_version":"1.0","canonical_sha256":"b9fd2d99641984f7115ca3d20cacfb50a0bc12da1f6300909ef6cb3e66276170","source":{"kind":"arxiv","id":"1807.11720","version":2},"attestation_state":"computed","paper":{"title":"Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dasom Seo, Il-Seok Oh, Kanghan Oh","submitted_at":"2018-07-31T09:37:39Z","abstract_excerpt":"Recently, many methods to interpret and visualize deep neural network predictions have been proposed and significant progress has been made. However, a more class-discriminative and visually pleasing explanation is required. Thus, this paper proposes a region-based approach that estimates feature importance in terms of appropriately segmented regions. By fusing the saliency maps generated from multi-scale segmentations, a more class-discriminative and visually pleasing map is obtained. We incorporate this regional multi-scale concept into a prediction difference method that is model-agnostic. "},"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":"1807.11720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-31T09:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"1d3a4c1fc225265e73c21fa5be1dbb95a3ca6efbb34cee616da756b9299ee377","abstract_canon_sha256":"31b7b8a9977c2c3dcbf9c28e33b0d5b4041ad8926c2688878b8a2d896300fb8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:26.931911Z","signature_b64":"2bV40xrymy60q8eKuubggWswdsSjyT31oY31JvHLbr9ti39pqPm8kqbwYL9QPjHhtoc6WaX5N8whXoY1/G5HBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9fd2d99641984f7115ca3d20cacfb50a0bc12da1f6300909ef6cb3e66276170","last_reissued_at":"2026-07-05T00:29:26.931538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:26.931538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regional Multi-scale Approach for Visually Pleasing Explanations of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dasom Seo, Il-Seok Oh, Kanghan Oh","submitted_at":"2018-07-31T09:37:39Z","abstract_excerpt":"Recently, many methods to interpret and visualize deep neural network predictions have been proposed and significant progress has been made. However, a more class-discriminative and visually pleasing explanation is required. Thus, this paper proposes a region-based approach that estimates feature importance in terms of appropriately segmented regions. By fusing the saliency maps generated from multi-scale segmentations, a more class-discriminative and visually pleasing map is obtained. We incorporate this regional multi-scale concept into a prediction difference method that is model-agnostic. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11720","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/1807.11720/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":"1807.11720","created_at":"2026-07-05T00:29:26.931598+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.11720v2","created_at":"2026-07-05T00:29:26.931598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11720","created_at":"2026-07-05T00:29:26.931598+00:00"},{"alias_kind":"pith_short_12","alias_value":"XH6S3GLEDGCP","created_at":"2026-07-05T00:29:26.931598+00:00"},{"alias_kind":"pith_short_16","alias_value":"XH6S3GLEDGCPOEK4","created_at":"2026-07-05T00:29:26.931598+00:00"},{"alias_kind":"pith_short_8","alias_value":"XH6S3GLE","created_at":"2026-07-05T00:29:26.931598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.02686","citing_title":"Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC","json":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC.json","graph_json":"https://pith.science/api/pith-number/XH6S3GLEDGCPOEK4UPJAZLH3KC/graph.json","events_json":"https://pith.science/api/pith-number/XH6S3GLEDGCPOEK4UPJAZLH3KC/events.json","paper":"https://pith.science/paper/XH6S3GLE"},"agent_actions":{"view_html":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC","download_json":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC.json","view_paper":"https://pith.science/paper/XH6S3GLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.11720&json=true","fetch_graph":"https://pith.science/api/pith-number/XH6S3GLEDGCPOEK4UPJAZLH3KC/graph.json","fetch_events":"https://pith.science/api/pith-number/XH6S3GLEDGCPOEK4UPJAZLH3KC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC/action/storage_attestation","attest_author":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC/action/author_attestation","sign_citation":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC/action/citation_signature","submit_replication":"https://pith.science/pith/XH6S3GLEDGCPOEK4UPJAZLH3KC/action/replication_record"}},"created_at":"2026-07-05T00:29:26.931598+00:00","updated_at":"2026-07-05T00:29:26.931598+00:00"}