{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IOPGZ5M7NUC44PFLK6EFWMWWCB","short_pith_number":"pith:IOPGZ5M7","schema_version":"1.0","canonical_sha256":"439e6cf59f6d05ce3cab57885b32d6105f13493fea44f6710d0e21a7ce72fdec","source":{"kind":"arxiv","id":"1910.09745","version":1},"attestation_state":"computed","paper":{"title":"Vanishing Nodes: Another Phenomenon That Makes Training Deep Neural Networks Difficult","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tsung-Nan Lin, Wen-Yu Chang","submitted_at":"2019-10-22T03:11:26Z","abstract_excerpt":"It is well known that the problem of vanishing/exploding gradients is a challenge when training deep networks. In this paper, we describe another phenomenon, called vanishing nodes, that also increases the difficulty of training deep neural networks. As the depth of a neural network increases, the network's hidden nodes have more highly correlated behavior. This results in great similarities between these nodes. The redundancy of hidden nodes thus increases as the network becomes deeper. We call this problem vanishing nodes, and we propose the metric vanishing node indicator (VNI) for quantita"},"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":"1910.09745","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-22T03:11:26Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"3fbe499add01b5e76cedfb3ae6232d4c42cd3e74ec1826e25c28932572f8fa54","abstract_canon_sha256":"ade554cc651e5625cfbe38c00cb340953ed6711182502ccb7868ef2d9771cfcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:01.932574Z","signature_b64":"7APGLY8G+Kv86Le6T2UEz2RYPDnpvvbGTKZYzingJuiM6I/0erm2lKHwWy+CzjT10FxGBYnIXA+PBsPRFviKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"439e6cf59f6d05ce3cab57885b32d6105f13493fea44f6710d0e21a7ce72fdec","last_reissued_at":"2026-07-05T00:14:01.932134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:01.932134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vanishing Nodes: Another Phenomenon That Makes Training Deep Neural Networks Difficult","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tsung-Nan Lin, Wen-Yu Chang","submitted_at":"2019-10-22T03:11:26Z","abstract_excerpt":"It is well known that the problem of vanishing/exploding gradients is a challenge when training deep networks. In this paper, we describe another phenomenon, called vanishing nodes, that also increases the difficulty of training deep neural networks. As the depth of a neural network increases, the network's hidden nodes have more highly correlated behavior. This results in great similarities between these nodes. The redundancy of hidden nodes thus increases as the network becomes deeper. We call this problem vanishing nodes, and we propose the metric vanishing node indicator (VNI) for quantita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09745","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/1910.09745/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":"1910.09745","created_at":"2026-07-05T00:14:01.932210+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.09745v1","created_at":"2026-07-05T00:14:01.932210+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09745","created_at":"2026-07-05T00:14:01.932210+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOPGZ5M7NUC4","created_at":"2026-07-05T00:14:01.932210+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOPGZ5M7NUC44PFL","created_at":"2026-07-05T00:14:01.932210+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOPGZ5M7","created_at":"2026-07-05T00:14:01.932210+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/IOPGZ5M7NUC44PFLK6EFWMWWCB","json":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB.json","graph_json":"https://pith.science/api/pith-number/IOPGZ5M7NUC44PFLK6EFWMWWCB/graph.json","events_json":"https://pith.science/api/pith-number/IOPGZ5M7NUC44PFLK6EFWMWWCB/events.json","paper":"https://pith.science/paper/IOPGZ5M7"},"agent_actions":{"view_html":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB","download_json":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB.json","view_paper":"https://pith.science/paper/IOPGZ5M7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.09745&json=true","fetch_graph":"https://pith.science/api/pith-number/IOPGZ5M7NUC44PFLK6EFWMWWCB/graph.json","fetch_events":"https://pith.science/api/pith-number/IOPGZ5M7NUC44PFLK6EFWMWWCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB/action/storage_attestation","attest_author":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB/action/author_attestation","sign_citation":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB/action/citation_signature","submit_replication":"https://pith.science/pith/IOPGZ5M7NUC44PFLK6EFWMWWCB/action/replication_record"}},"created_at":"2026-07-05T00:14:01.932210+00:00","updated_at":"2026-07-05T00:14:01.932210+00:00"}