{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VWKIIGFW3BMHKVMXRVN5EOM3ZE","short_pith_number":"pith:VWKIIGFW","schema_version":"1.0","canonical_sha256":"ad948418b6d8587555978d5bd2399bc9180b764b1e701d48c04433200c180a77","source":{"kind":"arxiv","id":"1901.10900","version":1},"attestation_state":"computed","paper":{"title":"On Correlation of Features Extracted by Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Babajide O. Ayinde, Jacek M. Zurada, Tamer Inanc","submitted_at":"2019-01-30T15:31:35Z","abstract_excerpt":"Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of size (both width and depth), activation function, and weight initialization on the susceptibility of deep neural network models to extract redundant features. To estimate the number of redundant features in each layer, all the features of a given layer are hierarchically clustered according to their relative cosine distances in feature space and a set thresho"},"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":"1901.10900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T15:31:35Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"302055f0bb1c44a71a4bd658b5bc925f2bf47d35f93d60f324db67a77fd8065d","abstract_canon_sha256":"231766c46e644ef7229244192129840d73f096fb88338375534f5f3f6f7c3101"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:05.764471Z","signature_b64":"efvedSfbmCHd0mENvlYdTYFddtFDI7/H3i+XQKB5OaIC8yHaRlKO6EupmUClaTP76UBz55s2rsR5/U77pWAXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad948418b6d8587555978d5bd2399bc9180b764b1e701d48c04433200c180a77","last_reissued_at":"2026-05-17T23:55:05.764071Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:05.764071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Correlation of Features Extracted by Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Babajide O. Ayinde, Jacek M. Zurada, Tamer Inanc","submitted_at":"2019-01-30T15:31:35Z","abstract_excerpt":"Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of size (both width and depth), activation function, and weight initialization on the susceptibility of deep neural network models to extract redundant features. To estimate the number of redundant features in each layer, all the features of a given layer are hierarchically clustered according to their relative cosine distances in feature space and a set thresho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10900","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":"1901.10900","created_at":"2026-05-17T23:55:05.764129+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10900v1","created_at":"2026-05-17T23:55:05.764129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10900","created_at":"2026-05-17T23:55:05.764129+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWKIIGFW3BMH","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWKIIGFW3BMHKVMX","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWKIIGFW","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/VWKIIGFW3BMHKVMXRVN5EOM3ZE","json":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE.json","graph_json":"https://pith.science/api/pith-number/VWKIIGFW3BMHKVMXRVN5EOM3ZE/graph.json","events_json":"https://pith.science/api/pith-number/VWKIIGFW3BMHKVMXRVN5EOM3ZE/events.json","paper":"https://pith.science/paper/VWKIIGFW"},"agent_actions":{"view_html":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE","download_json":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE.json","view_paper":"https://pith.science/paper/VWKIIGFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10900&json=true","fetch_graph":"https://pith.science/api/pith-number/VWKIIGFW3BMHKVMXRVN5EOM3ZE/graph.json","fetch_events":"https://pith.science/api/pith-number/VWKIIGFW3BMHKVMXRVN5EOM3ZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE/action/storage_attestation","attest_author":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE/action/author_attestation","sign_citation":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE/action/citation_signature","submit_replication":"https://pith.science/pith/VWKIIGFW3BMHKVMXRVN5EOM3ZE/action/replication_record"}},"created_at":"2026-05-17T23:55:05.764129+00:00","updated_at":"2026-05-17T23:55:05.764129+00:00"}