{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:2TD26MENMSEUR5MZSLCYHBSQTH","short_pith_number":"pith:2TD26MEN","schema_version":"1.0","canonical_sha256":"d4c7af308d648948f59992c583865099e91cac19ca25c1b789e41eb22961ae19","source":{"kind":"arxiv","id":"1312.6184","version":7},"attestation_state":"computed","paper":{"title":"Do Deep Nets Really Need to be Deep?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Lei Jimmy Ba, Rich Caruana","submitted_at":"2013-12-21T00:47:43Z","abstract_excerpt":"Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this extended abstract, we show that shallow feed-forward networks can learn the complex functions previously learned by deep nets and achieve accuracies previously only achievable with deep models. Moreover, in some cases the shallow neural nets can learn these deep functions using a total number of parameters similar to the original deep model. We evaluate our method on the TIMIT phoneme recognition task and are able to train shallow fully-connected nets that perform simila"},"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":"1312.6184","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-12-21T00:47:43Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"8d17468712a5f188ff31b62ac9aaf69970b02d583b8212af1b9fb7bfe8c50730","abstract_canon_sha256":"309f00403530b0d9ce034c545b5e32fbaa46457d065872f422d73e5d3b9986d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:40:18.573703Z","signature_b64":"9LRujNAwfNkUrLxPStwFpziED6u0g4jBL6BJGwTYxWLHHH8SQxweSIqQvm97Vsa1sJrCOkRPuYTOCWlQ3RaUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4c7af308d648948f59992c583865099e91cac19ca25c1b789e41eb22961ae19","last_reissued_at":"2026-05-18T02:40:18.573025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:40:18.573025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Deep Nets Really Need to be Deep?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Lei Jimmy Ba, Rich Caruana","submitted_at":"2013-12-21T00:47:43Z","abstract_excerpt":"Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this extended abstract, we show that shallow feed-forward networks can learn the complex functions previously learned by deep nets and achieve accuracies previously only achievable with deep models. Moreover, in some cases the shallow neural nets can learn these deep functions using a total number of parameters similar to the original deep model. We evaluate our method on the TIMIT phoneme recognition task and are able to train shallow fully-connected nets that perform simila"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.6184","kind":"arxiv","version":7},"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":"1312.6184","created_at":"2026-05-18T02:40:18.573132+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.6184v7","created_at":"2026-05-18T02:40:18.573132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.6184","created_at":"2026-05-18T02:40:18.573132+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TD26MENMSEU","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TD26MENMSEUR5MZ","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TD26MEN","created_at":"2026-05-18T12:27:32.513160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2112.11447","citing_title":"Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13143","citing_title":"On the Generalization of Knowledge Distillation: An Information-Theoretic View","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH","json":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH.json","graph_json":"https://pith.science/api/pith-number/2TD26MENMSEUR5MZSLCYHBSQTH/graph.json","events_json":"https://pith.science/api/pith-number/2TD26MENMSEUR5MZSLCYHBSQTH/events.json","paper":"https://pith.science/paper/2TD26MEN"},"agent_actions":{"view_html":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH","download_json":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH.json","view_paper":"https://pith.science/paper/2TD26MEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.6184&json=true","fetch_graph":"https://pith.science/api/pith-number/2TD26MENMSEUR5MZSLCYHBSQTH/graph.json","fetch_events":"https://pith.science/api/pith-number/2TD26MENMSEUR5MZSLCYHBSQTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH/action/storage_attestation","attest_author":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH/action/author_attestation","sign_citation":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH/action/citation_signature","submit_replication":"https://pith.science/pith/2TD26MENMSEUR5MZSLCYHBSQTH/action/replication_record"}},"created_at":"2026-05-18T02:40:18.573132+00:00","updated_at":"2026-05-18T02:40:18.573132+00:00"}