{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:G47DM2E7KSZ4XLNYA4UDVURBCR","short_pith_number":"pith:G47DM2E7","schema_version":"1.0","canonical_sha256":"373e36689f54b3cbadb807283ad221145766f261ed919a16e0a790dd99b879d8","source":{"kind":"arxiv","id":"1312.6098","version":5},"attestation_state":"computed","paper":{"title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Guido Montufar, Razvan Pascanu, Yoshua Bengio","submitted_at":"2013-12-20T20:22:31Z","abstract_excerpt":"This paper explores the complexity of deep feedforward networks with linear pre-synaptic couplings and rectified linear activations. This is a contribution to the growing body of work contrasting the representational power of deep and shallow network architectures. In particular, we offer a framework for comparing deep and shallow models that belong to the family of piecewise linear functions based on computational geometry. We look at a deep rectifier multi-layer perceptron (MLP) with linear outputs units and compare it with a single layer version of the model. In the asymptotic regime, when "},"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":"1312.6098","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-12-20T20:22:31Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"3cb17ee59156b17c72b79cd7bfaef02a4f7148f203d737faa406eb9a41b8897e","abstract_canon_sha256":"4ada344723ea177281bb1f0f5f7828e5e8445924ceba8fcdb28bc74dcc11973b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:59:05.799098Z","signature_b64":"NPvxjp6LAsvkRxYA1YtFGK0+vclFFnsgtSWzgtUNCkDDJ4OQHEDkBGnL5jX539IPz+C2u2cwxHjtCdoyxD8oDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"373e36689f54b3cbadb807283ad221145766f261ed919a16e0a790dd99b879d8","last_reissued_at":"2026-05-18T02:59:05.798595Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:59:05.798595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the number of response regions of deep feed forward networks with piece-wise linear activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Guido Montufar, Razvan Pascanu, Yoshua Bengio","submitted_at":"2013-12-20T20:22:31Z","abstract_excerpt":"This paper explores the complexity of deep feedforward networks with linear pre-synaptic couplings and rectified linear activations. This is a contribution to the growing body of work contrasting the representational power of deep and shallow network architectures. In particular, we offer a framework for comparing deep and shallow models that belong to the family of piecewise linear functions based on computational geometry. We look at a deep rectifier multi-layer perceptron (MLP) with linear outputs units and compare it with a single layer version of the model. In the asymptotic regime, when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.6098","kind":"arxiv","version":5},"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":"1312.6098","created_at":"2026-05-18T02:59:05.798669+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.6098v5","created_at":"2026-05-18T02:59:05.798669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.6098","created_at":"2026-05-18T02:59:05.798669+00:00"},{"alias_kind":"pith_short_12","alias_value":"G47DM2E7KSZ4","created_at":"2026-05-18T12:27:45.050594+00:00"},{"alias_kind":"pith_short_16","alias_value":"G47DM2E7KSZ4XLNY","created_at":"2026-05-18T12:27:45.050594+00:00"},{"alias_kind":"pith_short_8","alias_value":"G47DM2E7","created_at":"2026-05-18T12:27:45.050594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.20534","citing_title":"Axiomatizing Neural Networks via Pursuit of Subspaces","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2507.16079","citing_title":"A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2602.03204","citing_title":"Sparsity is Combinatorial Depth: Quantifying MoE Expressivity via Tropical Geometry","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03992","citing_title":"HyParLyVe: Hyperplane Partitioning for Neural Lyapunov Verification","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24393","citing_title":"Complexity of Linear Regions in Self-supervised Deep ReLU Networks","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07378","citing_title":"Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR","json":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR.json","graph_json":"https://pith.science/api/pith-number/G47DM2E7KSZ4XLNYA4UDVURBCR/graph.json","events_json":"https://pith.science/api/pith-number/G47DM2E7KSZ4XLNYA4UDVURBCR/events.json","paper":"https://pith.science/paper/G47DM2E7"},"agent_actions":{"view_html":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR","download_json":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR.json","view_paper":"https://pith.science/paper/G47DM2E7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.6098&json=true","fetch_graph":"https://pith.science/api/pith-number/G47DM2E7KSZ4XLNYA4UDVURBCR/graph.json","fetch_events":"https://pith.science/api/pith-number/G47DM2E7KSZ4XLNYA4UDVURBCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR/action/storage_attestation","attest_author":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR/action/author_attestation","sign_citation":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR/action/citation_signature","submit_replication":"https://pith.science/pith/G47DM2E7KSZ4XLNYA4UDVURBCR/action/replication_record"}},"created_at":"2026-05-18T02:59:05.798669+00:00","updated_at":"2026-05-18T02:59:05.798669+00:00"}