{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WGVVDAOBNYXGJZ64XD3HHYOTN7","short_pith_number":"pith:WGVVDAOB","schema_version":"1.0","canonical_sha256":"b1ab5181c16e2e64e7dcb8f673e1d36fd463587d6e6440ea97b84a69e7def495","source":{"kind":"arxiv","id":"1901.07538","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Quanshi Zhang, Ying Nian Wu, Yu Yang","submitted_at":"2019-01-21T16:03:31Z","abstract_excerpt":"This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explainer performs like an auto-encoder, which decomposes the feature maps into object-part features. The object-part features are learned to reconstruct CNN features without much loss of information. We can consider the disentangled representations of object parts a paraphrase of CNN fe"},"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":"1901.07538","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-21T16:03:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4b47f297734fd8cb7471f53976fd24a793685dd9472eb23227008715e2ef973e","abstract_canon_sha256":"6414e2e1f61220512b098a86a94b793ef9742701d8d05c94e557d2b533080636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:42.140217Z","signature_b64":"02SQ6OO7C8+ZvQ7TjNuBrhrCXOKvlGYGRRrWGTLyfSqjZVN06+xpLOatHmeO7UsoZ0fdgICk9UjErz9x436+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1ab5181c16e2e64e7dcb8f673e1d36fd463587d6e6440ea97b84a69e7def495","last_reissued_at":"2026-05-17T23:55:42.139746Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:42.139746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Quanshi Zhang, Ying Nian Wu, Yu Yang","submitted_at":"2019-01-21T16:03:31Z","abstract_excerpt":"This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., the explainer uses interpretable visual concepts to explain features in middle conv-layers of a CNN. Given feature maps of a conv-layer of the CNN, the explainer performs like an auto-encoder, which decomposes the feature maps into object-part features. The object-part features are learned to reconstruct CNN features without much loss of information. We can consider the disentangled representations of object parts a paraphrase of CNN fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07538","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":""},"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":"1901.07538","created_at":"2026-05-17T23:55:42.139822+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.07538v1","created_at":"2026-05-17T23:55:42.139822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07538","created_at":"2026-05-17T23:55:42.139822+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGVVDAOBNYXG","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGVVDAOBNYXGJZ64","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGVVDAOB","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7","json":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7.json","graph_json":"https://pith.science/api/pith-number/WGVVDAOBNYXGJZ64XD3HHYOTN7/graph.json","events_json":"https://pith.science/api/pith-number/WGVVDAOBNYXGJZ64XD3HHYOTN7/events.json","paper":"https://pith.science/paper/WGVVDAOB"},"agent_actions":{"view_html":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7","download_json":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7.json","view_paper":"https://pith.science/paper/WGVVDAOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.07538&json=true","fetch_graph":"https://pith.science/api/pith-number/WGVVDAOBNYXGJZ64XD3HHYOTN7/graph.json","fetch_events":"https://pith.science/api/pith-number/WGVVDAOBNYXGJZ64XD3HHYOTN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7/action/storage_attestation","attest_author":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7/action/author_attestation","sign_citation":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7/action/citation_signature","submit_replication":"https://pith.science/pith/WGVVDAOBNYXGJZ64XD3HHYOTN7/action/replication_record"}},"created_at":"2026-05-17T23:55:42.139822+00:00","updated_at":"2026-05-17T23:55:42.139822+00:00"}