{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KOQFE6COEU75U7XS3PUONWTTN3","short_pith_number":"pith:KOQFE6CO","schema_version":"1.0","canonical_sha256":"53a052784e253fda7ef2dbe8e6da736ec0aba626cb889c179619aecee705c8bd","source":{"kind":"arxiv","id":"1806.05337","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical interpretations for neural network predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bin Yu, Chandan Singh, W. James Murdoch","submitted_at":"2018-06-14T02:41:03Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved impressive predictive performance due to their ability to learn complex, non-linear relationships between variables. However, the inability to effectively visualize these relationships has led to DNNs being characterized as black boxes and consequently limited their applications. To ameliorate this problem, we introduce the use of hierarchical interpretations to explain DNN predictions through our proposed method, agglomerative contextual decomposition (ACD). Given a prediction from a trained DNN, ACD produces a hierarchical clustering of the input fea"},"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":"1806.05337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-14T02:41:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"66942914ced2ebf03a6677b8ded57eddca99c56b19a126f2a6d149793dc398d9","abstract_canon_sha256":"c64b421660f984d3f970a44e0a313df3f74084f61f0ee81453c98f64cc9e3d15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:15.107873Z","signature_b64":"XxbPglNSAIlmDHvskBy3A0GPerzPwDGQRYYd3/6nhla5RafxqKfJfZ4gg7mYYHo7676UwVsX1QObTic4bsfDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53a052784e253fda7ef2dbe8e6da736ec0aba626cb889c179619aecee705c8bd","last_reissued_at":"2026-05-17T23:56:15.107232Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:15.107232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical interpretations for neural network predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bin Yu, Chandan Singh, W. James Murdoch","submitted_at":"2018-06-14T02:41:03Z","abstract_excerpt":"Deep neural networks (DNNs) have achieved impressive predictive performance due to their ability to learn complex, non-linear relationships between variables. However, the inability to effectively visualize these relationships has led to DNNs being characterized as black boxes and consequently limited their applications. To ameliorate this problem, we introduce the use of hierarchical interpretations to explain DNN predictions through our proposed method, agglomerative contextual decomposition (ACD). Given a prediction from a trained DNN, ACD produces a hierarchical clustering of the input fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05337","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":""},"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":"1806.05337","created_at":"2026-05-17T23:56:15.107338+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05337v2","created_at":"2026-05-17T23:56:15.107338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05337","created_at":"2026-05-17T23:56:15.107338+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOQFE6COEU75","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOQFE6COEU75U7XS","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOQFE6CO","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22045","citing_title":"H-Sets: Hessian-Guided Discovery of Set-Level Feature Interactions in Image Classifiers","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3","json":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3.json","graph_json":"https://pith.science/api/pith-number/KOQFE6COEU75U7XS3PUONWTTN3/graph.json","events_json":"https://pith.science/api/pith-number/KOQFE6COEU75U7XS3PUONWTTN3/events.json","paper":"https://pith.science/paper/KOQFE6CO"},"agent_actions":{"view_html":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3","download_json":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3.json","view_paper":"https://pith.science/paper/KOQFE6CO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05337&json=true","fetch_graph":"https://pith.science/api/pith-number/KOQFE6COEU75U7XS3PUONWTTN3/graph.json","fetch_events":"https://pith.science/api/pith-number/KOQFE6COEU75U7XS3PUONWTTN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3/action/storage_attestation","attest_author":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3/action/author_attestation","sign_citation":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3/action/citation_signature","submit_replication":"https://pith.science/pith/KOQFE6COEU75U7XS3PUONWTTN3/action/replication_record"}},"created_at":"2026-05-17T23:56:15.107338+00:00","updated_at":"2026-05-17T23:56:15.107338+00:00"}