{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LPJKGRMI2W7HWUQQJ3RKCFXMK6","short_pith_number":"pith:LPJKGRMI","schema_version":"1.0","canonical_sha256":"5bd2a34588d5be7b52104ee2a116ec579e5b0a29e50a512aef4f6777ea010928","source":{"kind":"arxiv","id":"1801.02108","version":2},"attestation_state":"computed","paper":{"title":"SBNet: Sparse Blocks Network for Fast Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrei Pokrovsky, Bin Yang, Mengye Ren, Raquel Urtasun","submitted_at":"2018-01-07T01:03:25Z","abstract_excerpt":"Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such as object detection and semantic segmentation, we are able to obtain a low-cost computation mask, either from a priori problem knowledge, or from a low-resolution segmentation network. We show that such computation masks can be used to reduce computation in the high-resolution main network. Variants of sparse activation CNNs have previously been explored on "},"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":"1801.02108","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-01-07T01:03:25Z","cross_cats_sorted":[],"title_canon_sha256":"967e5b60e11480e5837a88bad5131cddeaf88174fbd0e6ca688505d5bac526cf","abstract_canon_sha256":"e3d12903519acaf7954e8c93174333a4cb8f58e02ce20572348265928b48ec13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:00.479946Z","signature_b64":"tBzWxBYMpjbJ91YOMDVV0rgut/mgTOyxyYK13E/NUb8Dd+5I9BqbMw8D7fXxpIFUXAnHewUa30WlP9fpUjJ3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bd2a34588d5be7b52104ee2a116ec579e5b0a29e50a512aef4f6777ea010928","last_reissued_at":"2026-05-18T00:14:00.474397Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:00.474397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SBNet: Sparse Blocks Network for Fast Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrei Pokrovsky, Bin Yang, Mengye Ren, Raquel Urtasun","submitted_at":"2018-01-07T01:03:25Z","abstract_excerpt":"Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such as object detection and semantic segmentation, we are able to obtain a low-cost computation mask, either from a priori problem knowledge, or from a low-resolution segmentation network. We show that such computation masks can be used to reduce computation in the high-resolution main network. Variants of sparse activation CNNs have previously been explored on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02108","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":"1801.02108","created_at":"2026-05-18T00:14:00.474486+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.02108v2","created_at":"2026-05-18T00:14:00.474486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02108","created_at":"2026-05-18T00:14:00.474486+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPJKGRMI2W7H","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPJKGRMI2W7HWUQQ","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPJKGRMI","created_at":"2026-05-18T12:32:37.024351+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/LPJKGRMI2W7HWUQQJ3RKCFXMK6","json":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6.json","graph_json":"https://pith.science/api/pith-number/LPJKGRMI2W7HWUQQJ3RKCFXMK6/graph.json","events_json":"https://pith.science/api/pith-number/LPJKGRMI2W7HWUQQJ3RKCFXMK6/events.json","paper":"https://pith.science/paper/LPJKGRMI"},"agent_actions":{"view_html":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6","download_json":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6.json","view_paper":"https://pith.science/paper/LPJKGRMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.02108&json=true","fetch_graph":"https://pith.science/api/pith-number/LPJKGRMI2W7HWUQQJ3RKCFXMK6/graph.json","fetch_events":"https://pith.science/api/pith-number/LPJKGRMI2W7HWUQQJ3RKCFXMK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6/action/storage_attestation","attest_author":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6/action/author_attestation","sign_citation":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6/action/citation_signature","submit_replication":"https://pith.science/pith/LPJKGRMI2W7HWUQQJ3RKCFXMK6/action/replication_record"}},"created_at":"2026-05-18T00:14:00.474486+00:00","updated_at":"2026-05-18T00:14:00.474486+00:00"}