{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3OXRMJYN5JRMPYXYWJQUTFCA23","short_pith_number":"pith:3OXRMJYN","schema_version":"1.0","canonical_sha256":"dbaf16270dea62c7e2f8b261499440d6f8d93fc4be5a70e78e339447fd22477e","source":{"kind":"arxiv","id":"1805.08743","version":1},"attestation_state":"computed","paper":{"title":"CascadeCNN: Pushing the performance limits of quantisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Kouris, Christos-Savvas Bouganis, Stylianos I. Venieris","submitted_at":"2018-05-22T17:06:02Z","abstract_excerpt":"This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, to perform high-throughput inference by exploiting the computation time-accuracy trade-off. Without the need for retraining, a two-stage architecture tailored for any given FPGA device is generated, consisting of a low- and a high-precision unit. A confidence evaluation unit is employed between them to identify misclassified cases at run time and forward them to the high-precision unit or terminate computation. Experiments demonstrate that CascadeCNN achieves a performance boost of "},"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":"1805.08743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-22T17:06:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"04180b131f76ea8706900617a2d32a5d7fab66f2ea8a23d50f912726489af14e","abstract_canon_sha256":"72a9392aa082a08466d106257f0bb942f4432731fdf1009781770a34b04fc535"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:25.191142Z","signature_b64":"X7hgXdhLiATeIQRby/bX5v+O6WW97lnZQkd1ODNvI8mvHctBCrOwOlePMjxbFinCRPnVVuc+2FM5q5hF79cJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbaf16270dea62c7e2f8b261499440d6f8d93fc4be5a70e78e339447fd22477e","last_reissued_at":"2026-05-18T00:15:25.190426Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:25.190426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CascadeCNN: Pushing the performance limits of quantisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandros Kouris, Christos-Savvas Bouganis, Stylianos I. Venieris","submitted_at":"2018-05-22T17:06:02Z","abstract_excerpt":"This work presents CascadeCNN, an automated toolflow that pushes the quantisation limits of any given CNN model, to perform high-throughput inference by exploiting the computation time-accuracy trade-off. Without the need for retraining, a two-stage architecture tailored for any given FPGA device is generated, consisting of a low- and a high-precision unit. A confidence evaluation unit is employed between them to identify misclassified cases at run time and forward them to the high-precision unit or terminate computation. Experiments demonstrate that CascadeCNN achieves a performance boost of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08743","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":"1805.08743","created_at":"2026-05-18T00:15:25.190688+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08743v1","created_at":"2026-05-18T00:15:25.190688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08743","created_at":"2026-05-18T00:15:25.190688+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OXRMJYN5JRM","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OXRMJYN5JRMPYXY","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OXRMJYN","created_at":"2026-05-18T12:32:02.567920+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/3OXRMJYN5JRMPYXYWJQUTFCA23","json":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23.json","graph_json":"https://pith.science/api/pith-number/3OXRMJYN5JRMPYXYWJQUTFCA23/graph.json","events_json":"https://pith.science/api/pith-number/3OXRMJYN5JRMPYXYWJQUTFCA23/events.json","paper":"https://pith.science/paper/3OXRMJYN"},"agent_actions":{"view_html":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23","download_json":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23.json","view_paper":"https://pith.science/paper/3OXRMJYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08743&json=true","fetch_graph":"https://pith.science/api/pith-number/3OXRMJYN5JRMPYXYWJQUTFCA23/graph.json","fetch_events":"https://pith.science/api/pith-number/3OXRMJYN5JRMPYXYWJQUTFCA23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23/action/storage_attestation","attest_author":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23/action/author_attestation","sign_citation":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23/action/citation_signature","submit_replication":"https://pith.science/pith/3OXRMJYN5JRMPYXYWJQUTFCA23/action/replication_record"}},"created_at":"2026-05-18T00:15:25.190688+00:00","updated_at":"2026-05-18T00:15:25.190688+00:00"}