{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:D2MR2JR4QNTAVUXTE4O5F6TYEA","short_pith_number":"pith:D2MR2JR4","schema_version":"1.0","canonical_sha256":"1e991d263c83660ad2f3271dd2fa78201b028c449909c632b0f28928e1aae1e2","source":{"kind":"arxiv","id":"1611.03131","version":3},"attestation_state":"computed","paper":{"title":"Diverse Neural Network Learns True Target Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Xie, Le Song, Yingyu Liang","submitted_at":"2016-11-09T23:19:21Z","abstract_excerpt":"Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that provide theoretical guarantees on why they are so effective. Lying in the center of the problem is the difficulty of analyzing the non-convex loss function with potentially numerous local minima and saddle points. Can neural networks corresponding to the stationary points of the loss function learn the true target function? If yes, what are the key factors cont"},"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":"1611.03131","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-09T23:19:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c460c0c7eb49d5bccdbe77a3ba3f7242f34176ac2c33bfe78e1f3264a9513f29","abstract_canon_sha256":"0e97bebfbb2ae5881cab269e4575f97ba15e242a2e61d5da147ecbd9a3109836"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:37.788071Z","signature_b64":"63RyPF9IAZ5fGfCObQGxKM/eAGGtrRcdVUE32sZV5DbhbqTyjhVssJETAAfS14786OSQiH9stweJQAENjWm5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e991d263c83660ad2f3271dd2fa78201b028c449909c632b0f28928e1aae1e2","last_reissued_at":"2026-05-18T00:49:37.787361Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:37.787361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse Neural Network Learns True Target Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Xie, Le Song, Yingyu Liang","submitted_at":"2016-11-09T23:19:21Z","abstract_excerpt":"Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that provide theoretical guarantees on why they are so effective. Lying in the center of the problem is the difficulty of analyzing the non-convex loss function with potentially numerous local minima and saddle points. Can neural networks corresponding to the stationary points of the loss function learn the true target function? If yes, what are the key factors cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03131","kind":"arxiv","version":3},"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":"1611.03131","created_at":"2026-05-18T00:49:37.787476+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.03131v3","created_at":"2026-05-18T00:49:37.787476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03131","created_at":"2026-05-18T00:49:37.787476+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2MR2JR4QNTA","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2MR2JR4QNTAVUXT","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2MR2JR4","created_at":"2026-05-18T12:30:09.641336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08654","citing_title":"ID3 Learns Juntas for Smoothed Product Distributions","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA","json":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA.json","graph_json":"https://pith.science/api/pith-number/D2MR2JR4QNTAVUXTE4O5F6TYEA/graph.json","events_json":"https://pith.science/api/pith-number/D2MR2JR4QNTAVUXTE4O5F6TYEA/events.json","paper":"https://pith.science/paper/D2MR2JR4"},"agent_actions":{"view_html":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA","download_json":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA.json","view_paper":"https://pith.science/paper/D2MR2JR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.03131&json=true","fetch_graph":"https://pith.science/api/pith-number/D2MR2JR4QNTAVUXTE4O5F6TYEA/graph.json","fetch_events":"https://pith.science/api/pith-number/D2MR2JR4QNTAVUXTE4O5F6TYEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA/action/storage_attestation","attest_author":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA/action/author_attestation","sign_citation":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA/action/citation_signature","submit_replication":"https://pith.science/pith/D2MR2JR4QNTAVUXTE4O5F6TYEA/action/replication_record"}},"created_at":"2026-05-18T00:49:37.787476+00:00","updated_at":"2026-05-18T00:49:37.787476+00:00"}