{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:L7RPBAHDLGFOANC7AWFK7MQ7FX","short_pith_number":"pith:L7RPBAHD","schema_version":"1.0","canonical_sha256":"5fe2f080e3598ae0345f058aafb21f2dee8dfc19d76895f384d9fb20064381c0","source":{"kind":"arxiv","id":"1712.00003","version":1},"attestation_state":"computed","paper":{"title":"Modeling Information Flow Through Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmad Chaddad, Behnaz Naisiri, Christian Desrosiers, Eric Granger, Marco Pedersoli, Matthew Toews","submitted_at":"2017-11-29T23:09:58Z","abstract_excerpt":"This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e.g. convolutional neural networks (CNN). The output of convolutional filters is modeled as a random variable Y conditioned on the object class C and network filter bank F. The conditional entropy (CENT) H(Y |C,F) is shown in theory and experiments to be a highly compact and class-informative code, that can be computed from the filter outputs throughout an existing CNN and used to obtain higher classification results than the original CNN itself. Experiments demonstrate the eff"},"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":"1712.00003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-29T23:09:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"771446ad8bbd2f8cd59cd591130f79bd8425be5f1fd2f8a239c7e39e973b6b7f","abstract_canon_sha256":"df9b35f7ae73b632bfceb569a2658126e5dc1ddb1442c7ad8a65189455f86567"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:07.667902Z","signature_b64":"VdfHaZ0aC76yFZbbhYataWzOHm2blC9+xP3hWTPTgf5ZQVHna6v/+nQ3PfkK2aB75Dz/uLg2C5OmpMlY0uw7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fe2f080e3598ae0345f058aafb21f2dee8dfc19d76895f384d9fb20064381c0","last_reissued_at":"2026-05-18T00:29:07.667118Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:07.667118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Information Flow Through Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmad Chaddad, Behnaz Naisiri, Christian Desrosiers, Eric Granger, Marco Pedersoli, Matthew Toews","submitted_at":"2017-11-29T23:09:58Z","abstract_excerpt":"This paper proposes a principled information theoretic analysis of classification for deep neural network structures, e.g. convolutional neural networks (CNN). The output of convolutional filters is modeled as a random variable Y conditioned on the object class C and network filter bank F. The conditional entropy (CENT) H(Y |C,F) is shown in theory and experiments to be a highly compact and class-informative code, that can be computed from the filter outputs throughout an existing CNN and used to obtain higher classification results than the original CNN itself. Experiments demonstrate the eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00003","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":"1712.00003","created_at":"2026-05-18T00:29:07.667250+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.00003v1","created_at":"2026-05-18T00:29:07.667250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00003","created_at":"2026-05-18T00:29:07.667250+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7RPBAHDLGFO","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7RPBAHDLGFOANC7","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7RPBAHD","created_at":"2026-05-18T12:31:28.150371+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/L7RPBAHDLGFOANC7AWFK7MQ7FX","json":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX.json","graph_json":"https://pith.science/api/pith-number/L7RPBAHDLGFOANC7AWFK7MQ7FX/graph.json","events_json":"https://pith.science/api/pith-number/L7RPBAHDLGFOANC7AWFK7MQ7FX/events.json","paper":"https://pith.science/paper/L7RPBAHD"},"agent_actions":{"view_html":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX","download_json":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX.json","view_paper":"https://pith.science/paper/L7RPBAHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.00003&json=true","fetch_graph":"https://pith.science/api/pith-number/L7RPBAHDLGFOANC7AWFK7MQ7FX/graph.json","fetch_events":"https://pith.science/api/pith-number/L7RPBAHDLGFOANC7AWFK7MQ7FX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX/action/storage_attestation","attest_author":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX/action/author_attestation","sign_citation":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX/action/citation_signature","submit_replication":"https://pith.science/pith/L7RPBAHDLGFOANC7AWFK7MQ7FX/action/replication_record"}},"created_at":"2026-05-18T00:29:07.667250+00:00","updated_at":"2026-05-18T00:29:07.667250+00:00"}