{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E2PHZ6JO6MBIFYE7IPPYYZUUMF","short_pith_number":"pith:E2PHZ6JO","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"},"canonical_sha256":"269e7cf92ef30282e09f43df8c6694614a93050c944615fed79194d9ebab9e4d","source":{"kind":"arxiv","id":"2506.11093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11093","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11093v1","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11093","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"E2PHZ6JO6MBI","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"E2PHZ6JO6MBIFYE7","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"E2PHZ6JO","created_at":"2026-07-05T11:20:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E2PHZ6JO6MBIFYE7IPPYYZUUMF","target":"record","payload":{"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"},"canonical_sha256":"269e7cf92ef30282e09f43df8c6694614a93050c944615fed79194d9ebab9e4d","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"},"source_kind":"arxiv","source_id":"2506.11093","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8/wrgnalwPDkcI5RomTusFxhYfHgdSvFNCt62dbRiCrhVR8HRj5EI8C8VEHvTNJawU2LnbT0tQKCjIScEXFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:55:19.660224Z"},"content_sha256":"224bae1a20cda545ba703e0d8f9696bc2a3c20073854e6d11d08d57b36ac2849","schema_version":"1.0","event_id":"sha256:224bae1a20cda545ba703e0d8f9696bc2a3c20073854e6d11d08d57b36ac2849"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E2PHZ6JO6MBIFYE7IPPYYZUUMF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:20:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OtFiMeEiAYLUVzuol2HyAuD/wlHJTIsTZ+Yz6so9HTuga+V1QXIW86iUXYlySt3UyMymOhSNRTPqrRdn1bkdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:55:19.660795Z"},"content_sha256":"32215ee0ec627e6fa65c1acbea7910cc3a7474f45b923b25c3c36c5980e547f3","schema_version":"1.0","event_id":"sha256:32215ee0ec627e6fa65c1acbea7910cc3a7474f45b923b25c3c36c5980e547f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/bundle.json","state_url":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T16:55:19Z","links":{"resolver":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF","bundle":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/bundle.json","state":"https://pith.science/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E2PHZ6JO6MBIFYE7IPPYYZUUMF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E2PHZ6JO6MBIFYE7IPPYYZUUMF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4a517e1d0f4c6925d3cbe930957c5b97be06e05c5efdbe11b8d436d8157c67df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T21:46:41Z","title_canon_sha256":"5c814584a48473aa7ad040092cd69686e35fe08873e96876d05ee98d5bc2b091"},"schema_version":"1.0","source":{"id":"2506.11093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11093","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11093v1","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11093","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_12","alias_value":"E2PHZ6JO6MBI","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_16","alias_value":"E2PHZ6JO6MBIFYE7","created_at":"2026-07-05T11:20:59Z"},{"alias_kind":"pith_short_8","alias_value":"E2PHZ6JO","created_at":"2026-07-05T11:20:59Z"}],"graph_snapshots":[{"event_id":"sha256:32215ee0ec627e6fa65c1acbea7910cc3a7474f45b923b25c3c36c5980e547f3","target":"graph","created_at":"2026-07-05T11:20:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.11093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lanyu Xu, Shaibal Saha","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T21:46:41Z","title":"EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11093","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:224bae1a20cda545ba703e0d8f9696bc2a3c20073854e6d11d08d57b36ac2849","target":"record","created_at":"2026-07-05T11:20:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4a517e1d0f4c6925d3cbe930957c5b97be06e05c5efdbe11b8d436d8157c67df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T21:46:41Z","title_canon_sha256":"5c814584a48473aa7ad040092cd69686e35fe08873e96876d05ee98d5bc2b091"},"schema_version":"1.0","source":{"id":"2506.11093","kind":"arxiv","version":1}},"canonical_sha256":"269e7cf92ef30282e09f43df8c6694614a93050c944615fed79194d9ebab9e4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"269e7cf92ef30282e09f43df8c6694614a93050c944615fed79194d9ebab9e4d","first_computed_at":"2026-07-05T11:20:59.296920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:59.296920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cXpkcwX1QGLWAm+OXiGh7zaI9xPtXT4roosD7UMJGvanHc4Y1N9+/cb8pa9qu9WthYZzj7s3QuY8GjBn9sv5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:59.297322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:224bae1a20cda545ba703e0d8f9696bc2a3c20073854e6d11d08d57b36ac2849","sha256:32215ee0ec627e6fa65c1acbea7910cc3a7474f45b923b25c3c36c5980e547f3"],"state_sha256":"aef8204030acbbe795c23462a5fb94ae24faffe50150ffd4f91d2a5dbaefa0b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OBrkhPjTpbEHIY5HfSN2OR7isa3BHMzofv4VklEc2xJbLo6YNPLD3P1AuAz8FbN5KJkM0qf7XmNQXvLShufZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:55:19.664846Z","bundle_sha256":"f8e30a03175d50722e766a8de705726ee616bc5965e4a57f02ddd3d63ee016ad"}}