{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:CVZJHNNUVQOLQOBCKN23B4I6JV","short_pith_number":"pith:CVZJHNNU","canonical_record":{"source":{"id":"1512.06473","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-21T02:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"cb79c18e5d5e7a51f399c00a94b1023dddb9985284b895fbf914b4fcd60bebe6","abstract_canon_sha256":"d891582582de171b88c9bc25b1f859317bbd83a95c4575c4773dee88c46ad0aa"},"schema_version":"1.0"},"canonical_sha256":"157293b5b4ac1cb838225375b0f11e4d749ee9dc207d3a1e83e81873cc438481","source":{"kind":"arxiv","id":"1512.06473","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.06473","created_at":"2026-05-18T01:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"1512.06473v3","created_at":"2026-05-18T01:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.06473","created_at":"2026-05-18T01:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"CVZJHNNUVQOL","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CVZJHNNUVQOLQOBC","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CVZJHNNU","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:CVZJHNNUVQOLQOBCKN23B4I6JV","target":"record","payload":{"canonical_record":{"source":{"id":"1512.06473","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-21T02:26:46Z","cross_cats_sorted":[],"title_canon_sha256":"cb79c18e5d5e7a51f399c00a94b1023dddb9985284b895fbf914b4fcd60bebe6","abstract_canon_sha256":"d891582582de171b88c9bc25b1f859317bbd83a95c4575c4773dee88c46ad0aa"},"schema_version":"1.0"},"canonical_sha256":"157293b5b4ac1cb838225375b0f11e4d749ee9dc207d3a1e83e81873cc438481","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:52.622281Z","signature_b64":"Y/ZSfxL5QtJYX0FPdv6Fbgf432q9rQXK94i+uugNm1kh7EYClceUau1G8MogEx/Kd6onqo9NEK//c4NfxMQjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"157293b5b4ac1cb838225375b0f11e4d749ee9dc207d3a1e83e81873cc438481","last_reissued_at":"2026-05-18T01:14:52.621801Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:52.621801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.06473","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:14:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Y1CGKnSLCPNcmz+s2n6tEwIyKhnU9lp41rCr29503ueJzzNy/ucaaWd/ntQGkP4EtDRNU1nCTrPlx0GS0MnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:07:51.060576Z"},"content_sha256":"3f01ca16f70567b0971713f860a6f57669466b7e8d357eee549845f55b0c7c91","schema_version":"1.0","event_id":"sha256:3f01ca16f70567b0971713f860a6f57669466b7e8d357eee549845f55b0c7c91"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:CVZJHNNUVQOLQOBCKN23B4I6JV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantized Convolutional Neural Networks for Mobile Devices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Leng, Jian Cheng, Jiaxiang Wu, Qinghao Hu, Yuhang Wang","submitted_at":"2015-12-21T02:26:46Z","abstract_excerpt":"Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high computation complexity, which prohibits their further extensions. In this paper, we propose an efficient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Both filter kernels in convolutional layers and weighting matrices in fully-connected layers are quantized, aiming at minimizing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.06473","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:14:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qDg0Wti7JBMYFS3ldz8slGXYl8dsUhaUblCxmRP9s38AHlL9LFno8EqsfW//vg/iwdM827FzoEwhRKlkjxiJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:07:51.061283Z"},"content_sha256":"4bc90bad572155277fa856c30d16309602fe0e2abfe9e6335172aea2ab897814","schema_version":"1.0","event_id":"sha256:4bc90bad572155277fa856c30d16309602fe0e2abfe9e6335172aea2ab897814"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CVZJHNNUVQOLQOBCKN23B4I6JV/bundle.json","state_url":"https://pith.science/pith/CVZJHNNUVQOLQOBCKN23B4I6JV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CVZJHNNUVQOLQOBCKN23B4I6JV/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":"2026-06-09T08:07:51Z","links":{"resolver":"https://pith.science/pith/CVZJHNNUVQOLQOBCKN23B4I6JV","bundle":"https://pith.science/pith/CVZJHNNUVQOLQOBCKN23B4I6JV/bundle.json","state":"https://pith.science/pith/CVZJHNNUVQOLQOBCKN23B4I6JV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CVZJHNNUVQOLQOBCKN23B4I6JV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CVZJHNNUVQOLQOBCKN23B4I6JV","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":"d891582582de171b88c9bc25b1f859317bbd83a95c4575c4773dee88c46ad0aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-21T02:26:46Z","title_canon_sha256":"cb79c18e5d5e7a51f399c00a94b1023dddb9985284b895fbf914b4fcd60bebe6"},"schema_version":"1.0","source":{"id":"1512.06473","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.06473","created_at":"2026-05-18T01:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"1512.06473v3","created_at":"2026-05-18T01:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.06473","created_at":"2026-05-18T01:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"CVZJHNNUVQOL","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CVZJHNNUVQOLQOBC","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CVZJHNNU","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:4bc90bad572155277fa856c30d16309602fe0e2abfe9e6335172aea2ab897814","target":"graph","created_at":"2026-05-18T01:14:52Z","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"},"paper":{"abstract_excerpt":"Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high computation complexity, which prohibits their further extensions. In this paper, we propose an efficient framework, namely Quantized CNN, to simultaneously speed-up the computation and reduce the storage and memory overhead of CNN models. Both filter kernels in convolutional layers and weighting matrices in fully-connected layers are quantized, aiming at minimizing","authors_text":"Cong Leng, Jian Cheng, Jiaxiang Wu, Qinghao Hu, Yuhang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-21T02:26:46Z","title":"Quantized Convolutional Neural Networks for Mobile Devices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.06473","kind":"arxiv","version":3},"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":"sha256:3f01ca16f70567b0971713f860a6f57669466b7e8d357eee549845f55b0c7c91","target":"record","created_at":"2026-05-18T01:14:52Z","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":"d891582582de171b88c9bc25b1f859317bbd83a95c4575c4773dee88c46ad0aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-21T02:26:46Z","title_canon_sha256":"cb79c18e5d5e7a51f399c00a94b1023dddb9985284b895fbf914b4fcd60bebe6"},"schema_version":"1.0","source":{"id":"1512.06473","kind":"arxiv","version":3}},"canonical_sha256":"157293b5b4ac1cb838225375b0f11e4d749ee9dc207d3a1e83e81873cc438481","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"157293b5b4ac1cb838225375b0f11e4d749ee9dc207d3a1e83e81873cc438481","first_computed_at":"2026-05-18T01:14:52.621801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:52.621801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y/ZSfxL5QtJYX0FPdv6Fbgf432q9rQXK94i+uugNm1kh7EYClceUau1G8MogEx/Kd6onqo9NEK//c4NfxMQjBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:52.622281Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.06473","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f01ca16f70567b0971713f860a6f57669466b7e8d357eee549845f55b0c7c91","sha256:4bc90bad572155277fa856c30d16309602fe0e2abfe9e6335172aea2ab897814"],"state_sha256":"5d038cb5c2a637396169003cdcea067a15c65f4c7590ee4a18b619aea78e4c2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uy+2NgQxwlW38rGyzvqNdg+cfvPqNVoegABjRF8Xp0jqxF8TZuuIARp6FqsrauKJG5ZaBtkfuYH+Fuj37AVhAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T08:07:51.064592Z","bundle_sha256":"220d2a87c4a59f20b157ed1268c05a7095d3fa33237f5b79100f182f90b5b92b"}}