{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:XHBPVP7INYDGOXKCDLYQWBAJGD","short_pith_number":"pith:XHBPVP7I","schema_version":"1.0","canonical_sha256":"b9c2fabfe86e06675d421af10b040930d8dbc7d09ed834d4c974f0d210a067e2","source":{"kind":"arxiv","id":"1604.07043","version":3},"attestation_state":"computed","paper":{"title":"Towards Better Analysis of Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Jiaxin Shi, Jun Zhu, Mengchen Liu, Shixia Liu, Zhen Li","submitted_at":"2016-04-24T15:53:22Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount of trial-and-error, as there is still no clear understanding of when and why a deep model works. In this paper, we present a visual analytics approach for better understanding, diagnosing, and refining deep CNNs. We formulate a deep CNN as a directed acyclic graph. Based on this formulation, a hybrid visualization is developed to disclose the multiple facets "},"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":"1604.07043","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-24T15:53:22Z","cross_cats_sorted":[],"title_canon_sha256":"b732fe07ea8e5f59ce5147dfb984697a775beee4457364dd31a16093fec58426","abstract_canon_sha256":"1af90474a36c624865a4db7b488c1716212ccadf744cea5f46a5563e7d87ceac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:38.079218Z","signature_b64":"ryncy/3dsZWOwPrd0g/Tsu0eRI5RNzf395J7gKztXdIEaV7RPRDNreqgQCKcpTfheqtTXs3fFET/YYiMm0O/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c2fabfe86e06675d421af10b040930d8dbc7d09ed834d4c974f0d210a067e2","last_reissued_at":"2026-05-18T01:15:38.078356Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:38.078356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Analysis of Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongxuan Li, Jiaxin Shi, Jun Zhu, Mengchen Liu, Shixia Liu, Zhen Li","submitted_at":"2016-04-24T15:53:22Z","abstract_excerpt":"Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount of trial-and-error, as there is still no clear understanding of when and why a deep model works. In this paper, we present a visual analytics approach for better understanding, diagnosing, and refining deep CNNs. We formulate a deep CNN as a directed acyclic graph. Based on this formulation, a hybrid visualization is developed to disclose the multiple facets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.07043","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":"1604.07043","created_at":"2026-05-18T01:15:38.078491+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.07043v3","created_at":"2026-05-18T01:15:38.078491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.07043","created_at":"2026-05-18T01:15:38.078491+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHBPVP7INYDG","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHBPVP7INYDGOXKC","created_at":"2026-05-18T12:30:51.357362+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHBPVP7I","created_at":"2026-05-18T12:30:51.357362+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/XHBPVP7INYDGOXKCDLYQWBAJGD","json":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD.json","graph_json":"https://pith.science/api/pith-number/XHBPVP7INYDGOXKCDLYQWBAJGD/graph.json","events_json":"https://pith.science/api/pith-number/XHBPVP7INYDGOXKCDLYQWBAJGD/events.json","paper":"https://pith.science/paper/XHBPVP7I"},"agent_actions":{"view_html":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD","download_json":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD.json","view_paper":"https://pith.science/paper/XHBPVP7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.07043&json=true","fetch_graph":"https://pith.science/api/pith-number/XHBPVP7INYDGOXKCDLYQWBAJGD/graph.json","fetch_events":"https://pith.science/api/pith-number/XHBPVP7INYDGOXKCDLYQWBAJGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD/action/storage_attestation","attest_author":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD/action/author_attestation","sign_citation":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD/action/citation_signature","submit_replication":"https://pith.science/pith/XHBPVP7INYDGOXKCDLYQWBAJGD/action/replication_record"}},"created_at":"2026-05-18T01:15:38.078491+00:00","updated_at":"2026-05-18T01:15:38.078491+00:00"}