{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GGTQH3CUUOVP4YOGWEMFVXITEO","short_pith_number":"pith:GGTQH3CU","schema_version":"1.0","canonical_sha256":"31a703ec54a3aafe61c6b1185add13238586f63b5b8ad572585328eb6e1f66cc","source":{"kind":"arxiv","id":"2103.09716","version":5},"attestation_state":"computed","paper":{"title":"Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Yang Zhao","submitted_at":"2021-03-17T15:18:18Z","abstract_excerpt":"Identifying the status of individual network units is critical for understanding the mechanism of convolutional neural networks (CNNs). However, it is still challenging to reliably give a general indication of unit status, especially for units in different network models. To this end, we propose a novel method for quantitatively clarifying the status of single unit in CNN using algebraic topological tools. Unit status is indicated via the calculation of a defined topological-based entropy, called feature entropy, which measures the degree of chaos of the global spatial pattern hidden in the un"},"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":"2103.09716","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-17T15:18:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aab847ae08ec9fc63ea2324a3f31ed6c16f5945ee0ca6207b59a443a67774b8e","abstract_canon_sha256":"742127cf7372df84d5c6d3214713cfca2046b798e96e41fc1ea8ac12f4c9da72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:57.680052Z","signature_b64":"O/+gw7O+xfmLAdT9xuQhD0XNp9oEPsjJbXGP960vwUKYDqmHgChVCqlWn6QuzMvBHxHMdqgkcZg8BP4uGpsQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31a703ec54a3aafe61c6b1185add13238586f63b5b8ad572585328eb6e1f66cc","last_reissued_at":"2026-07-05T04:05:57.679568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:57.679568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Yang Zhao","submitted_at":"2021-03-17T15:18:18Z","abstract_excerpt":"Identifying the status of individual network units is critical for understanding the mechanism of convolutional neural networks (CNNs). However, it is still challenging to reliably give a general indication of unit status, especially for units in different network models. To this end, we propose a novel method for quantitatively clarifying the status of single unit in CNN using algebraic topological tools. Unit status is indicated via the calculation of a defined topological-based entropy, called feature entropy, which measures the degree of chaos of the global spatial pattern hidden in the un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09716","kind":"arxiv","version":5},"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/2103.09716/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":"2103.09716","created_at":"2026-07-05T04:05:57.679642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09716v5","created_at":"2026-07-05T04:05:57.679642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09716","created_at":"2026-07-05T04:05:57.679642+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGTQH3CUUOVP","created_at":"2026-07-05T04:05:57.679642+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGTQH3CUUOVP4YOG","created_at":"2026-07-05T04:05:57.679642+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGTQH3CU","created_at":"2026-07-05T04:05:57.679642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06109","citing_title":"FMCE-Net++: Feature Map Convergence Evaluation and Training","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO","json":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO.json","graph_json":"https://pith.science/api/pith-number/GGTQH3CUUOVP4YOGWEMFVXITEO/graph.json","events_json":"https://pith.science/api/pith-number/GGTQH3CUUOVP4YOGWEMFVXITEO/events.json","paper":"https://pith.science/paper/GGTQH3CU"},"agent_actions":{"view_html":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO","download_json":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO.json","view_paper":"https://pith.science/paper/GGTQH3CU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09716&json=true","fetch_graph":"https://pith.science/api/pith-number/GGTQH3CUUOVP4YOGWEMFVXITEO/graph.json","fetch_events":"https://pith.science/api/pith-number/GGTQH3CUUOVP4YOGWEMFVXITEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO/action/storage_attestation","attest_author":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO/action/author_attestation","sign_citation":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO/action/citation_signature","submit_replication":"https://pith.science/pith/GGTQH3CUUOVP4YOGWEMFVXITEO/action/replication_record"}},"created_at":"2026-07-05T04:05:57.679642+00:00","updated_at":"2026-07-05T04:05:57.679642+00:00"}