{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KVXA6PVRV6JM6CI5XVQYXE3PEU","short_pith_number":"pith:KVXA6PVR","schema_version":"1.0","canonical_sha256":"556e0f3eb1af92cf091dbd618b936f251e01f0c611a29eb0b741593c997b2d01","source":{"kind":"arxiv","id":"1709.04060","version":2},"attestation_state":"computed","paper":{"title":"Streamlined Deployment for Quantized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Magnus Jahre, Yaman Umuroglu","submitted_at":"2017-09-12T21:14:57Z","abstract_excerpt":"Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem, promising to offer most of the DNN accuracy benefits with much lower computational cost. However, harvesting these benefits on existing mobile CPUs is a challenge since operations on highly quantized datatypes are not natively supported in most instruction set architectures (ISAs). In this work, we first describe a streamlining flow to convert all QNN inferenc"},"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":"1709.04060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-12T21:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"33fc410677208a8b5c2327f4a4e7d4d192e9d24f1119e0352788fac91c002dc6","abstract_canon_sha256":"1f2aef083292a4e42900bf4443ec105cb4d1deb38a5d9c95fe6512631c6345d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:40.947197Z","signature_b64":"NGYnN4EcuEuICywRaaxNckj82sT0jKvC0cQ0MGqCMSfORlAK6JkOTRoauMl0CZuXuYrmOxLTeGLyBsmQNUgrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"556e0f3eb1af92cf091dbd618b936f251e01f0c611a29eb0b741593c997b2d01","last_reissued_at":"2026-05-18T00:14:40.946654Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:40.946654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streamlined Deployment for Quantized Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Magnus Jahre, Yaman Umuroglu","submitted_at":"2017-09-12T21:14:57Z","abstract_excerpt":"Running Deep Neural Network (DNN) models on devices with limited computational capability is a challenge due to large compute and memory requirements. Quantized Neural Networks (QNNs) have emerged as a potential solution to this problem, promising to offer most of the DNN accuracy benefits with much lower computational cost. However, harvesting these benefits on existing mobile CPUs is a challenge since operations on highly quantized datatypes are not natively supported in most instruction set architectures (ISAs). In this work, we first describe a streamlining flow to convert all QNN inferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04060","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":"1709.04060","created_at":"2026-05-18T00:14:40.946740+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04060v2","created_at":"2026-05-18T00:14:40.946740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04060","created_at":"2026-05-18T00:14:40.946740+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVXA6PVRV6JM","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVXA6PVRV6JM6CI5","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVXA6PVR","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20810","citing_title":"FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMs","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU","json":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU.json","graph_json":"https://pith.science/api/pith-number/KVXA6PVRV6JM6CI5XVQYXE3PEU/graph.json","events_json":"https://pith.science/api/pith-number/KVXA6PVRV6JM6CI5XVQYXE3PEU/events.json","paper":"https://pith.science/paper/KVXA6PVR"},"agent_actions":{"view_html":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU","download_json":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU.json","view_paper":"https://pith.science/paper/KVXA6PVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04060&json=true","fetch_graph":"https://pith.science/api/pith-number/KVXA6PVRV6JM6CI5XVQYXE3PEU/graph.json","fetch_events":"https://pith.science/api/pith-number/KVXA6PVRV6JM6CI5XVQYXE3PEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU/action/storage_attestation","attest_author":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU/action/author_attestation","sign_citation":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU/action/citation_signature","submit_replication":"https://pith.science/pith/KVXA6PVRV6JM6CI5XVQYXE3PEU/action/replication_record"}},"created_at":"2026-05-18T00:14:40.946740+00:00","updated_at":"2026-05-18T00:14:40.946740+00:00"}