{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4NA5T6GGKALV2DT4R3SWASMSZY","short_pith_number":"pith:4NA5T6GG","schema_version":"1.0","canonical_sha256":"e341d9f8c650175d0e7c8ee5604992ce3ce1f86bd2ac884c3519435333490873","source":{"kind":"arxiv","id":"1909.11396","version":1},"attestation_state":"computed","paper":{"title":"Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jose Principe, Kristoffer Wickstr{\\o}m, Michael Kampffmeyer, Robert Jenssen, Shujian Yu, Sigurd L{\\o}kse","submitted_at":"2019-09-25T10:42:39Z","abstract_excerpt":"Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently as a tool to gain insight into, among others, their generalization ability. However, it is by no means obvious how to estimate mutual information (MI) between each hidden layer and the input/desired output, to construct the IP. For instance, hidden layers with many neurons require MI estimators with robustness towards the high dimensionality associated with such layers. MI estimators should also be able to naturally handle convolutional layers, while at the same time being computati"},"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":"1909.11396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T10:42:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"125521f9708fd63b426780cafd0e59954dc193902a3e723f382178d0dfee0d6d","abstract_canon_sha256":"1c5a3be430c0133d88f8c20c11c5c76b3083b9252ebabf5e73640af3861bea87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:18.182713Z","signature_b64":"sA2mtfkGTTMvbUPNQfVWxUzSohEg/lPZkdap6PEJE1VUxcniQs3uSc7dgItyzoPIFFS91lk0jWb2h+SKoQdpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e341d9f8c650175d0e7c8ee5604992ce3ce1f86bd2ac884c3519435333490873","last_reissued_at":"2026-07-05T00:07:18.182290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:18.182290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jose Principe, Kristoffer Wickstr{\\o}m, Michael Kampffmeyer, Robert Jenssen, Shujian Yu, Sigurd L{\\o}kse","submitted_at":"2019-09-25T10:42:39Z","abstract_excerpt":"Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently as a tool to gain insight into, among others, their generalization ability. However, it is by no means obvious how to estimate mutual information (MI) between each hidden layer and the input/desired output, to construct the IP. For instance, hidden layers with many neurons require MI estimators with robustness towards the high dimensionality associated with such layers. MI estimators should also be able to naturally handle convolutional layers, while at the same time being computati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11396","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/1909.11396/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":"1909.11396","created_at":"2026-07-05T00:07:18.182354+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11396v1","created_at":"2026-07-05T00:07:18.182354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11396","created_at":"2026-07-05T00:07:18.182354+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NA5T6GGKALV","created_at":"2026-07-05T00:07:18.182354+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NA5T6GGKALV2DT4","created_at":"2026-07-05T00:07:18.182354+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NA5T6GG","created_at":"2026-07-05T00:07:18.182354+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/4NA5T6GGKALV2DT4R3SWASMSZY","json":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY.json","graph_json":"https://pith.science/api/pith-number/4NA5T6GGKALV2DT4R3SWASMSZY/graph.json","events_json":"https://pith.science/api/pith-number/4NA5T6GGKALV2DT4R3SWASMSZY/events.json","paper":"https://pith.science/paper/4NA5T6GG"},"agent_actions":{"view_html":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY","download_json":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY.json","view_paper":"https://pith.science/paper/4NA5T6GG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11396&json=true","fetch_graph":"https://pith.science/api/pith-number/4NA5T6GGKALV2DT4R3SWASMSZY/graph.json","fetch_events":"https://pith.science/api/pith-number/4NA5T6GGKALV2DT4R3SWASMSZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY/action/storage_attestation","attest_author":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY/action/author_attestation","sign_citation":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY/action/citation_signature","submit_replication":"https://pith.science/pith/4NA5T6GGKALV2DT4R3SWASMSZY/action/replication_record"}},"created_at":"2026-07-05T00:07:18.182354+00:00","updated_at":"2026-07-05T00:07:18.182354+00:00"}