{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TT4M2MZCKFTM3445NKVEP4EFZS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2c07508ddaa3f7b42aae81d0aa676d15c0b8a2eb8a8c9ba87f666822179b3c60","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:05:04Z","title_canon_sha256":"1cabdcaa2a76d83c1c2041234ec3097f05183c11d5e2ededa2e8588911e3c01d"},"schema_version":"1.0","source":{"id":"1908.04351","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.04351","created_at":"2026-07-05T00:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"1908.04351v3","created_at":"2026-07-05T00:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.04351","created_at":"2026-07-05T00:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"TT4M2MZCKFTM","created_at":"2026-07-05T00:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"TT4M2MZCKFTM3445","created_at":"2026-07-05T00:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"TT4M2MZC","created_at":"2026-07-05T00:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:b17f613b258cb4983574180635fc6405bfb9789d0672ce3b8debd140037a9623","target":"graph","created_at":"2026-07-05T00:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.04351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relev","authors_text":"Brian Kenji Iwana, Ryohei Kuroki, Seiichi Uchida","cross_cats":["cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:05:04Z","title":"Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.04351","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ce6bc0605244dc39964d211c6090a0616b21f50912a4af52a64f2a133aa8c28","target":"record","created_at":"2026-07-05T00:17:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2c07508ddaa3f7b42aae81d0aa676d15c0b8a2eb8a8c9ba87f666822179b3c60","cross_cats_sorted":["cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-06T13:05:04Z","title_canon_sha256":"1cabdcaa2a76d83c1c2041234ec3097f05183c11d5e2ededa2e8588911e3c01d"},"schema_version":"1.0","source":{"id":"1908.04351","kind":"arxiv","version":3}},"canonical_sha256":"9cf8cd33225166cdf39d6aaa47f085cca3b0648bf5194e98b6af3d3f6e5b92f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cf8cd33225166cdf39d6aaa47f085cca3b0648bf5194e98b6af3d3f6e5b92f4","first_computed_at":"2026-07-05T00:17:54.544343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:17:54.544343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"geUE4t03IYDGp77Wo8jeGMJk5QuuMAXFfnHw+zSgCm5YvLQxo/pHgp/V6zblwKu47n0j++GfUxZ6oJv8B6CyDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:17:54.544824Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.04351","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ce6bc0605244dc39964d211c6090a0616b21f50912a4af52a64f2a133aa8c28","sha256:b17f613b258cb4983574180635fc6405bfb9789d0672ce3b8debd140037a9623"],"state_sha256":"8225aaf7b32af29cbd08a67ad58abd9547d93a318e5dec9bfd6734312ca441d7"}