{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LPJA5NFPLGQMX7AKEHZCUEKHOI","short_pith_number":"pith:LPJA5NFP","schema_version":"1.0","canonical_sha256":"5bd20eb4af59a0cbfc0a21f22a11477208bf40ee13cd3c0fdc735d7ff40a7816","source":{"kind":"arxiv","id":"1708.01785","version":3},"attestation_state":"computed","paper":{"title":"Interpreting CNN Knowledge via an Explanatory Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Shi, Quanshi Zhang, Ruiming Cao, Song-Chun Zhu, Ying Nian Wu","submitted_at":"2017-08-05T15:59:13Z","abstract_excerpt":"This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv-layer of a pre-trained CNN usually represents a mixture of object parts, we propose a simple yet efficient method to automatically disentangles different part patterns from each filter, and construct an explanatory graph. In the explanatory graph, each node represents a part pattern, and each edge encodes co-activation relationships and spatial relationships between patterns. More importantly, we learn the explanatory gr"},"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":"1708.01785","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-05T15:59:13Z","cross_cats_sorted":[],"title_canon_sha256":"e04f8a59361722163fa401e091d826c3b94e6fbffd0f348b957d54880434708f","abstract_canon_sha256":"43b27861e1c2ac4d068f63fb50432bd4bd086c4f5c6540b4be4f30025ba3d8a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:51.415356Z","signature_b64":"SN/36qI25zEudKnOHFBP94A4KFySFF+cyRHLlP+mPaJ7gDLPXXyHvxWzHv70maoqKR+av2wYdJKnb0zRpJLbCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bd20eb4af59a0cbfc0a21f22a11477208bf40ee13cd3c0fdc735d7ff40a7816","last_reissued_at":"2026-05-18T00:29:51.414751Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:51.414751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpreting CNN Knowledge via an Explanatory Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Shi, Quanshi Zhang, Ruiming Cao, Song-Chun Zhu, Ying Nian Wu","submitted_at":"2017-08-05T15:59:13Z","abstract_excerpt":"This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv-layer of a pre-trained CNN usually represents a mixture of object parts, we propose a simple yet efficient method to automatically disentangles different part patterns from each filter, and construct an explanatory graph. In the explanatory graph, each node represents a part pattern, and each edge encodes co-activation relationships and spatial relationships between patterns. More importantly, we learn the explanatory gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01785","kind":"arxiv","version":3},"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":"1708.01785","created_at":"2026-05-18T00:29:51.414826+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01785v3","created_at":"2026-05-18T00:29:51.414826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01785","created_at":"2026-05-18T00:29:51.414826+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPJA5NFPLGQM","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPJA5NFPLGQMX7AK","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPJA5NFP","created_at":"2026-05-18T12:31:28.150371+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/LPJA5NFPLGQMX7AKEHZCUEKHOI","json":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI.json","graph_json":"https://pith.science/api/pith-number/LPJA5NFPLGQMX7AKEHZCUEKHOI/graph.json","events_json":"https://pith.science/api/pith-number/LPJA5NFPLGQMX7AKEHZCUEKHOI/events.json","paper":"https://pith.science/paper/LPJA5NFP"},"agent_actions":{"view_html":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI","download_json":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI.json","view_paper":"https://pith.science/paper/LPJA5NFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01785&json=true","fetch_graph":"https://pith.science/api/pith-number/LPJA5NFPLGQMX7AKEHZCUEKHOI/graph.json","fetch_events":"https://pith.science/api/pith-number/LPJA5NFPLGQMX7AKEHZCUEKHOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI/action/storage_attestation","attest_author":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI/action/author_attestation","sign_citation":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI/action/citation_signature","submit_replication":"https://pith.science/pith/LPJA5NFPLGQMX7AKEHZCUEKHOI/action/replication_record"}},"created_at":"2026-05-18T00:29:51.414826+00:00","updated_at":"2026-05-18T00:29:51.414826+00:00"}