{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MXN2O4HMLKL3BGJYFCBHJCJRLN","short_pith_number":"pith:MXN2O4HM","schema_version":"1.0","canonical_sha256":"65dba770ec5a97b0993828827489315b430654e09b439d493a75ae631990d900","source":{"kind":"arxiv","id":"1811.01753","version":2},"attestation_state":"computed","paper":{"title":"How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Achim Schilling, Claus Metzner, Holger Schulze, Jonas Rietsch, Patrick Krauss, Richard Gerum","submitted_at":"2018-11-05T14:46:12Z","abstract_excerpt":"Deep neural networks typically outperform more traditional machine learning models in their ability to classify complex data, and yet is not clear how the individual hidden layers of a deep network contribute to the overall classification performance. We thus introduce a Generalized Discrimination Value (GDV) that measures, in a non-invasive manner, how well different data classes separate in each given network layer. The GDV can be used for the automatic tuning of hyper-parameters, such as the width profile and the total depth of a network. Moreover, the layer-dependent GDV(L) provides new in"},"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":"1811.01753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T14:46:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"77d6bfcc4dd636bf9f876bda31ae56e941c5bd30c259473e1ade61922ac9a2a0","abstract_canon_sha256":"b15b97f491bd319544de989b9dd484c69dd1b6167ec9be46e5d5f6d4a9fce234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:07.993109Z","signature_b64":"KQo0RdVJgENEhSzbkd7JCUhIFRl0Zr85XWKpGDqsQFdqf2+/+l8XVmQzOQNBC8Af3fumz+8CV8UWojti99l3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65dba770ec5a97b0993828827489315b430654e09b439d493a75ae631990d900","last_reissued_at":"2026-07-05T05:02:07.992699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:07.992699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Achim Schilling, Claus Metzner, Holger Schulze, Jonas Rietsch, Patrick Krauss, Richard Gerum","submitted_at":"2018-11-05T14:46:12Z","abstract_excerpt":"Deep neural networks typically outperform more traditional machine learning models in their ability to classify complex data, and yet is not clear how the individual hidden layers of a deep network contribute to the overall classification performance. We thus introduce a Generalized Discrimination Value (GDV) that measures, in a non-invasive manner, how well different data classes separate in each given network layer. The GDV can be used for the automatic tuning of hyper-parameters, such as the width profile and the total depth of a network. Moreover, the layer-dependent GDV(L) provides new in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01753","kind":"arxiv","version":2},"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/1811.01753/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":"1811.01753","created_at":"2026-07-05T05:02:07.992754+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01753v2","created_at":"2026-07-05T05:02:07.992754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01753","created_at":"2026-07-05T05:02:07.992754+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXN2O4HMLKL3","created_at":"2026-07-05T05:02:07.992754+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXN2O4HMLKL3BGJY","created_at":"2026-07-05T05:02:07.992754+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXN2O4HM","created_at":"2026-07-05T05:02:07.992754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17736","citing_title":"Ten Years of the Stochastic Resonance Model of Tinnitus: From Phantom Perception to Adaptive Sensory Optimization","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN","json":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN.json","graph_json":"https://pith.science/api/pith-number/MXN2O4HMLKL3BGJYFCBHJCJRLN/graph.json","events_json":"https://pith.science/api/pith-number/MXN2O4HMLKL3BGJYFCBHJCJRLN/events.json","paper":"https://pith.science/paper/MXN2O4HM"},"agent_actions":{"view_html":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN","download_json":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN.json","view_paper":"https://pith.science/paper/MXN2O4HM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01753&json=true","fetch_graph":"https://pith.science/api/pith-number/MXN2O4HMLKL3BGJYFCBHJCJRLN/graph.json","fetch_events":"https://pith.science/api/pith-number/MXN2O4HMLKL3BGJYFCBHJCJRLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN/action/storage_attestation","attest_author":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN/action/author_attestation","sign_citation":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN/action/citation_signature","submit_replication":"https://pith.science/pith/MXN2O4HMLKL3BGJYFCBHJCJRLN/action/replication_record"}},"created_at":"2026-07-05T05:02:07.992754+00:00","updated_at":"2026-07-05T05:02:07.992754+00:00"}