{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H6DU5C7HSEETAV3EXFI73PYVF6","short_pith_number":"pith:H6DU5C7H","schema_version":"1.0","canonical_sha256":"3f874e8be79109305764b951fdbf152fa8f4dc486fc109d608e122edba4a7566","source":{"kind":"arxiv","id":"1807.05053","version":1},"attestation_state":"computed","paper":{"title":"CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Kouris, Christos-Savvas Bouganis, Stylianos I. Venieris","submitted_at":"2018-07-13T13:21:18Z","abstract_excerpt":"This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, aiming to perform high-throughput inference. A two-stage architecture tailored for any given CNN-FPGA pair is generated, consisting of a low- and high-precision unit in a cascade. A confidence evaluation unit is employed to identify misclassified cases from the excessively low-precision unit and forward them to the high-precision unit for re-processing. Experiments demonstrate that the proposed toolflow can achieve a performance boost up to 55% for VGG-16 and 48% for AlexNet over th"},"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":"1807.05053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-13T13:21:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e2895041cb9160f0c59840622527e86a2349fe3ce48be41e0c59ca06f579deb1","abstract_canon_sha256":"6265317c611066754b1737c8a102c87c22d401843f77e96b052bf2551e106d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:49.143202Z","signature_b64":"Xruy/x4C4HgwqRQONJTuYO2yoU2WE8snrdymaciqyocvAHnlIj1asGYkdksHutDzHYhTOk+FHjrDN/lsm9UjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f874e8be79109305764b951fdbf152fa8f4dc486fc109d608e122edba4a7566","last_reissued_at":"2026-05-18T00:10:49.142728Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:49.142728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Kouris, Christos-Savvas Bouganis, Stylianos I. Venieris","submitted_at":"2018-07-13T13:21:18Z","abstract_excerpt":"This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, aiming to perform high-throughput inference. A two-stage architecture tailored for any given CNN-FPGA pair is generated, consisting of a low- and high-precision unit in a cascade. A confidence evaluation unit is employed to identify misclassified cases from the excessively low-precision unit and forward them to the high-precision unit for re-processing. Experiments demonstrate that the proposed toolflow can achieve a performance boost up to 55% for VGG-16 and 48% for AlexNet over th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05053","kind":"arxiv","version":1},"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":"1807.05053","created_at":"2026-05-18T00:10:49.142797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05053v1","created_at":"2026-05-18T00:10:49.142797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05053","created_at":"2026-05-18T00:10:49.142797+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6DU5C7HSEET","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6DU5C7HSEETAV3E","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6DU5C7H","created_at":"2026-05-18T12:32:28.185984+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/H6DU5C7HSEETAV3EXFI73PYVF6","json":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6.json","graph_json":"https://pith.science/api/pith-number/H6DU5C7HSEETAV3EXFI73PYVF6/graph.json","events_json":"https://pith.science/api/pith-number/H6DU5C7HSEETAV3EXFI73PYVF6/events.json","paper":"https://pith.science/paper/H6DU5C7H"},"agent_actions":{"view_html":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6","download_json":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6.json","view_paper":"https://pith.science/paper/H6DU5C7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05053&json=true","fetch_graph":"https://pith.science/api/pith-number/H6DU5C7HSEETAV3EXFI73PYVF6/graph.json","fetch_events":"https://pith.science/api/pith-number/H6DU5C7HSEETAV3EXFI73PYVF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6/action/storage_attestation","attest_author":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6/action/author_attestation","sign_citation":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6/action/citation_signature","submit_replication":"https://pith.science/pith/H6DU5C7HSEETAV3EXFI73PYVF6/action/replication_record"}},"created_at":"2026-05-18T00:10:49.142797+00:00","updated_at":"2026-05-18T00:10:49.142797+00:00"}