{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E2PHZ6JO6MBIFYE7IPPYYZUUMF","short_pith_number":"pith:E2PHZ6JO","schema_version":"1.0","canonical_sha256":"269e7cf92ef30282e09f43df8c6694614a93050c944615fed79194d9ebab9e4d","source":{"kind":"arxiv","id":"2506.11093","version":1},"attestation_state":"computed","paper":{"title":"EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lanyu Xu, Shaibal Saha","submitted_at":"2025-06-05T21:46:41Z","abstract_excerpt":"Hybrid models that combine convolutional and transformer blocks offer strong performance in computer vision (CV) tasks but are resource-intensive for edge deployment. Although post-training quantization (PTQ) can help reduce resource demand, its application to hybrid models remains limited. We propose EfficientQuant, a novel structure-aware PTQ approach that applies uniform quantization to convolutional blocks and $log_2$ quantization to transformer blocks. EfficientQuant achieves $2.5 \\times - 8.7 \\times$ latency reduction with minimal accuracy loss on the ImageNet-1K dataset. It further demo"},"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":"2506.11093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T21:46:41Z","cross_cats_sorted":[],"title_canon_sha256":"5c814584a48473aa7ad040092cd69686e35fe08873e96876d05ee98d5bc2b091","abstract_canon_sha256":"4a517e1d0f4c6925d3cbe930957c5b97be06e05c5efdbe11b8d436d8157c67df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:59.297322Z","signature_b64":"cXpkcwX1QGLWAm+OXiGh7zaI9xPtXT4roosD7UMJGvanHc4Y1N9+/cb8pa9qu9WthYZzj7s3QuY8GjBn9sv5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"269e7cf92ef30282e09f43df8c6694614a93050c944615fed79194d9ebab9e4d","last_reissued_at":"2026-07-05T11:20:59.296920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:59.296920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lanyu Xu, Shaibal Saha","submitted_at":"2025-06-05T21:46:41Z","abstract_excerpt":"Hybrid models that combine convolutional and transformer blocks offer strong performance in computer vision (CV) tasks but are resource-intensive for edge deployment. Although post-training quantization (PTQ) can help reduce resource demand, its application to hybrid models remains limited. We propose EfficientQuant, a novel structure-aware PTQ approach that applies uniform quantization to convolutional blocks and $log_2$ quantization to transformer blocks. EfficientQuant achieves $2.5 \\times - 8.7 \\times$ latency reduction with minimal accuracy loss on the ImageNet-1K dataset. It further demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11093","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.11093/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2506.11093","created_at":"2026-07-05T11:20:59.296972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11093v1","created_at":"2026-07-05T11:20:59.296972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11093","created_at":"2026-07-05T11:20:59.296972+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2PHZ6JO6MBI","created_at":"2026-07-05T11:20:59.296972+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2PHZ6JO6MBIFYE7","created_at":"2026-07-05T11:20:59.296972+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2PHZ6JO","created_at":"2026-07-05T11:20:59.296972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.22872","citing_title":"Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF","json":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF.json","graph_json":"https://pith.science/api/pith-number/E2PHZ6JO6MBIFYE7IPPYYZUUMF/graph.json","events_json":"https://pith.science/api/pith-number/E2PHZ6JO6MBIFYE7IPPYYZUUMF/events.json","paper":"https://pith.science/paper/E2PHZ6JO"},"agent_actions":{"view_html":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF","download_json":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF.json","view_paper":"https://pith.science/paper/E2PHZ6JO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11093&json=true","fetch_graph":"https://pith.science/api/pith-number/E2PHZ6JO6MBIFYE7IPPYYZUUMF/graph.json","fetch_events":"https://pith.science/api/pith-number/E2PHZ6JO6MBIFYE7IPPYYZUUMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/action/storage_attestation","attest_author":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/action/author_attestation","sign_citation":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/action/citation_signature","submit_replication":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/action/replication_record"}},"created_at":"2026-07-05T11:20:59.296972+00:00","updated_at":"2026-07-05T11:20:59.296972+00:00"}