{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5QUJT63LZYRPT44TTAWVPPLALL","short_pith_number":"pith:5QUJT63L","schema_version":"1.0","canonical_sha256":"ec2899fb6bce22f9f393982d57bd605af7d51af105307cc020e226b5f398f4af","source":{"kind":"arxiv","id":"1903.04120","version":2},"attestation_state":"computed","paper":{"title":"HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Piyush Rai, Pravendra Singh, Vinay Kumar Verma, Vinay P. Namboodiri","submitted_at":"2019-03-11T04:20:38Z","abstract_excerpt":"We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we present extensive experimental results on the standard convolutional neural network (CNN) architectures such as VGG \\cite{vgg2014very} and ResNet \\cite{resnet}. We find that after replacing the standard con"},"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":"1903.04120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-11T04:20:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2772f8ab06a81f559e2cb3a974d9097b3a4db572ac24ce461763a0529ef4bc4b","abstract_canon_sha256":"7146865a0641a88b9edb53f9a82bade6ce383ff43f493fa73b8192d33698d820"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:33.133924Z","signature_b64":"DPTyhqxEFs1w/VpOgTPqzut4vHZ6UCWBQg4nNRIfiWjKBO/SY6DdODksNj3RQj0X8EkXULoq+9NN0wHNjfJCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2899fb6bce22f9f393982d57bd605af7d51af105307cc020e226b5f398f4af","last_reissued_at":"2026-05-17T23:50:33.133426Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:33.133426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Piyush Rai, Pravendra Singh, Vinay Kumar Verma, Vinay P. Namboodiri","submitted_at":"2019-03-11T04:20:38Z","abstract_excerpt":"We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we present extensive experimental results on the standard convolutional neural network (CNN) architectures such as VGG \\cite{vgg2014very} and ResNet \\cite{resnet}. We find that after replacing the standard con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04120","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":"1903.04120","created_at":"2026-05-17T23:50:33.133505+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.04120v2","created_at":"2026-05-17T23:50:33.133505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04120","created_at":"2026-05-17T23:50:33.133505+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QUJT63LZYRP","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QUJT63LZYRPT44T","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QUJT63L","created_at":"2026-05-18T12:33:10.108867+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/5QUJT63LZYRPT44TTAWVPPLALL","json":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL.json","graph_json":"https://pith.science/api/pith-number/5QUJT63LZYRPT44TTAWVPPLALL/graph.json","events_json":"https://pith.science/api/pith-number/5QUJT63LZYRPT44TTAWVPPLALL/events.json","paper":"https://pith.science/paper/5QUJT63L"},"agent_actions":{"view_html":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL","download_json":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL.json","view_paper":"https://pith.science/paper/5QUJT63L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.04120&json=true","fetch_graph":"https://pith.science/api/pith-number/5QUJT63LZYRPT44TTAWVPPLALL/graph.json","fetch_events":"https://pith.science/api/pith-number/5QUJT63LZYRPT44TTAWVPPLALL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL/action/storage_attestation","attest_author":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL/action/author_attestation","sign_citation":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL/action/citation_signature","submit_replication":"https://pith.science/pith/5QUJT63LZYRPT44TTAWVPPLALL/action/replication_record"}},"created_at":"2026-05-17T23:50:33.133505+00:00","updated_at":"2026-05-17T23:50:33.133505+00:00"}