{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AAIV4YZWNRBUXTI4PTAWRMFJQG","short_pith_number":"pith:AAIV4YZW","schema_version":"1.0","canonical_sha256":"00115e63366c434bcd1c7cc168b0a981b0118898c255fdddbc6a39ebd439dce3","source":{"kind":"arxiv","id":"1804.06679","version":4},"attestation_state":"computed","paper":{"title":"Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernhard C. Geiger, Kairen Liu, Rana Ali Amjad","submitted_at":"2018-04-18T12:29:24Z","abstract_excerpt":"In this work, we investigate the use of three information-theoretic quantities -- entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler divergence -- to understand and study the behavior of already trained fully-connected feed-forward neural networks. We analyze the connection between these information-theoretic quantities and classification performance on the test set by cumulatively ablating neurons in networks trained on MNIST, FashionMNIST, and CIFAR-10. Our results parallel those recently published by Morcos et al., indicating that "},"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":"1804.06679","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-18T12:29:24Z","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"c4c86a4013d3ac5968d31dffa4b830a1674ab8dc4b48fd4de934e462aa0bca81","abstract_canon_sha256":"630800e43a71ea9d6e23708f37ec4c76c3054829cf22c818131c08bcd5e09337"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:21.304907Z","signature_b64":"kD4XOYhn93X5DSTF1ubXR+8mImRFypwRyELpkgbgNqBr8CzSa0by+P0lO7/hza3g0JJ8XJnvXY2+5UbCuQmjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00115e63366c434bcd1c7cc168b0a981b0118898c255fdddbc6a39ebd439dce3","last_reissued_at":"2026-07-05T05:21:21.304445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:21.304445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Neural Networks and Individual Neuron Importance via Information-Ordered Cumulative Ablation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernhard C. Geiger, Kairen Liu, Rana Ali Amjad","submitted_at":"2018-04-18T12:29:24Z","abstract_excerpt":"In this work, we investigate the use of three information-theoretic quantities -- entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler divergence -- to understand and study the behavior of already trained fully-connected feed-forward neural networks. We analyze the connection between these information-theoretic quantities and classification performance on the test set by cumulatively ablating neurons in networks trained on MNIST, FashionMNIST, and CIFAR-10. Our results parallel those recently published by Morcos et al., indicating that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06679","kind":"arxiv","version":4},"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/1804.06679/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":"1804.06679","created_at":"2026-07-05T05:21:21.304508+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06679v4","created_at":"2026-07-05T05:21:21.304508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06679","created_at":"2026-07-05T05:21:21.304508+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAIV4YZWNRBU","created_at":"2026-07-05T05:21:21.304508+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAIV4YZWNRBUXTI4","created_at":"2026-07-05T05:21:21.304508+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAIV4YZW","created_at":"2026-07-05T05:21:21.304508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05242","citing_title":"SECNEURON: Reliable and Flexible Abuse Control in Local LLMs via Hybrid Neuron Encryption","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG","json":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG.json","graph_json":"https://pith.science/api/pith-number/AAIV4YZWNRBUXTI4PTAWRMFJQG/graph.json","events_json":"https://pith.science/api/pith-number/AAIV4YZWNRBUXTI4PTAWRMFJQG/events.json","paper":"https://pith.science/paper/AAIV4YZW"},"agent_actions":{"view_html":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG","download_json":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG.json","view_paper":"https://pith.science/paper/AAIV4YZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06679&json=true","fetch_graph":"https://pith.science/api/pith-number/AAIV4YZWNRBUXTI4PTAWRMFJQG/graph.json","fetch_events":"https://pith.science/api/pith-number/AAIV4YZWNRBUXTI4PTAWRMFJQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG/action/storage_attestation","attest_author":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG/action/author_attestation","sign_citation":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG/action/citation_signature","submit_replication":"https://pith.science/pith/AAIV4YZWNRBUXTI4PTAWRMFJQG/action/replication_record"}},"created_at":"2026-07-05T05:21:21.304508+00:00","updated_at":"2026-07-05T05:21:21.304508+00:00"}