{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MQYR6SOXOXFM6QM4FCEQR46QRV","short_pith_number":"pith:MQYR6SOX","schema_version":"1.0","canonical_sha256":"64311f49d775cacf419c288908f3d08d55433aa314d4f68157308da16a2660b6","source":{"kind":"arxiv","id":"2106.14190","version":1},"attestation_state":"computed","paper":{"title":"Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Nidhi Gowdra, Roopak Sinha, Stephen MacDonell, Wei Qi Yan","submitted_at":"2021-06-27T10:34:39Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) such as ResNet-50, DenseNet-40 and ResNeXt-56 are severely over-parameterized, necessitating a consequent increase in the computational resources required for model training which scales exponentially for increments in model depth. In this paper, we propose an Entropy-Based Convolutional Layer Estimation (EBCLE) heuristic which is robust and simple, yet effective in resolving the problem of over-parameterization with regards to network depth of CNN model. The EBCLE heuristic employs a priori knowledge of the entropic data distribution of input datasets to d"},"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":"2106.14190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-27T10:34:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d553ca1b337d98a49423e13c77b5cb2825b69819dea3e5eb56c82627f06e7692","abstract_canon_sha256":"bcb4812dd1378f92eef903fa8b8b459351f0b3b2068b0c82a37c5c2d60ac2f8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:48.295971Z","signature_b64":"tGbS1bik17hi8o4eM9ErIbLAG/NweDWkuALLXmbmJre920uNXPSs0OFCfkOSCiBLR7KIY+hAvrYnmnJLbdEOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64311f49d775cacf419c288908f3d08d55433aa314d4f68157308da16a2660b6","last_reissued_at":"2026-07-05T02:52:48.295584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:48.295584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Nidhi Gowdra, Roopak Sinha, Stephen MacDonell, Wei Qi Yan","submitted_at":"2021-06-27T10:34:39Z","abstract_excerpt":"Convolutional Neural Networks (CNNs) such as ResNet-50, DenseNet-40 and ResNeXt-56 are severely over-parameterized, necessitating a consequent increase in the computational resources required for model training which scales exponentially for increments in model depth. In this paper, we propose an Entropy-Based Convolutional Layer Estimation (EBCLE) heuristic which is robust and simple, yet effective in resolving the problem of over-parameterization with regards to network depth of CNN model. The EBCLE heuristic employs a priori knowledge of the entropic data distribution of input datasets to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.14190","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.14190/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2106.14190","created_at":"2026-07-05T02:52:48.295648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.14190v1","created_at":"2026-07-05T02:52:48.295648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.14190","created_at":"2026-07-05T02:52:48.295648+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQYR6SOXOXFM","created_at":"2026-07-05T02:52:48.295648+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQYR6SOXOXFM6QM4","created_at":"2026-07-05T02:52:48.295648+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQYR6SOX","created_at":"2026-07-05T02:52:48.295648+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/MQYR6SOXOXFM6QM4FCEQR46QRV","json":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV.json","graph_json":"https://pith.science/api/pith-number/MQYR6SOXOXFM6QM4FCEQR46QRV/graph.json","events_json":"https://pith.science/api/pith-number/MQYR6SOXOXFM6QM4FCEQR46QRV/events.json","paper":"https://pith.science/paper/MQYR6SOX"},"agent_actions":{"view_html":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV","download_json":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV.json","view_paper":"https://pith.science/paper/MQYR6SOX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.14190&json=true","fetch_graph":"https://pith.science/api/pith-number/MQYR6SOXOXFM6QM4FCEQR46QRV/graph.json","fetch_events":"https://pith.science/api/pith-number/MQYR6SOXOXFM6QM4FCEQR46QRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV/action/storage_attestation","attest_author":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV/action/author_attestation","sign_citation":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV/action/citation_signature","submit_replication":"https://pith.science/pith/MQYR6SOXOXFM6QM4FCEQR46QRV/action/replication_record"}},"created_at":"2026-07-05T02:52:48.295648+00:00","updated_at":"2026-07-05T02:52:48.295648+00:00"}