{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:A5LEEYSL4LO42QBLTFAAV355PO","short_pith_number":"pith:A5LEEYSL","schema_version":"1.0","canonical_sha256":"075642624be2ddcd402b99400aefbd7bbe4fc5255ae2dd3cfb1add1c0534555f","source":{"kind":"arxiv","id":"1604.01792","version":2},"attestation_state":"computed","paper":{"title":"Advances in Very Deep Convolutional Neural Networks for LVCSR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Tom Sercu, Vaibhava Goel","submitted_at":"2016-04-06T20:07:52Z","abstract_excerpt":"Very deep CNNs with small 3x3 kernels have recently been shown to achieve very strong performance as acoustic models in hybrid NN-HMM speech recognition systems. In this paper we investigate how to efficiently scale these models to larger datasets. Specifically, we address the design choice of pooling and padding along the time dimension which renders convolutional evaluation of sequences highly inefficient. We propose a new CNN design without timepadding and without timepooling, which is slightly suboptimal for accuracy, but has two significant advantages: it enables sequence training and dep"},"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":"1604.01792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-06T20:07:52Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"bbf9e83a1d045beb76e26078a175cf84bc7e60e2f77b096b31c26ddf890a1057","abstract_canon_sha256":"fa58774daedd2be73b0267b1893306450abb59d195766fa8e99e5e4e6defc8b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:54.585799Z","signature_b64":"XC1LGHI8oT+QzmEATSbHQu/k9ljiKPhOFOMu1zRVmbuylWZuCWvwVkresY4BMs/bjYFgDsueFPSyDtGEQwKiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"075642624be2ddcd402b99400aefbd7bbe4fc5255ae2dd3cfb1add1c0534555f","last_reissued_at":"2026-05-18T01:11:54.585450Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:54.585450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advances in Very Deep Convolutional Neural Networks for LVCSR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Tom Sercu, Vaibhava Goel","submitted_at":"2016-04-06T20:07:52Z","abstract_excerpt":"Very deep CNNs with small 3x3 kernels have recently been shown to achieve very strong performance as acoustic models in hybrid NN-HMM speech recognition systems. In this paper we investigate how to efficiently scale these models to larger datasets. Specifically, we address the design choice of pooling and padding along the time dimension which renders convolutional evaluation of sequences highly inefficient. We propose a new CNN design without timepadding and without timepooling, which is slightly suboptimal for accuracy, but has two significant advantages: it enables sequence training and dep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.01792","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":""},"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":"1604.01792","created_at":"2026-05-18T01:11:54.585516+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.01792v2","created_at":"2026-05-18T01:11:54.585516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.01792","created_at":"2026-05-18T01:11:54.585516+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5LEEYSL4LO4","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5LEEYSL4LO42QBL","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5LEEYSL","created_at":"2026-05-18T12:30:04.600751+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/A5LEEYSL4LO42QBLTFAAV355PO","json":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO.json","graph_json":"https://pith.science/api/pith-number/A5LEEYSL4LO42QBLTFAAV355PO/graph.json","events_json":"https://pith.science/api/pith-number/A5LEEYSL4LO42QBLTFAAV355PO/events.json","paper":"https://pith.science/paper/A5LEEYSL"},"agent_actions":{"view_html":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO","download_json":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO.json","view_paper":"https://pith.science/paper/A5LEEYSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.01792&json=true","fetch_graph":"https://pith.science/api/pith-number/A5LEEYSL4LO42QBLTFAAV355PO/graph.json","fetch_events":"https://pith.science/api/pith-number/A5LEEYSL4LO42QBLTFAAV355PO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO/action/storage_attestation","attest_author":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO/action/author_attestation","sign_citation":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO/action/citation_signature","submit_replication":"https://pith.science/pith/A5LEEYSL4LO42QBLTFAAV355PO/action/replication_record"}},"created_at":"2026-05-18T01:11:54.585516+00:00","updated_at":"2026-05-18T01:11:54.585516+00:00"}