{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WCIKWOMA6DUZJEIVCARUZI3G2X","short_pith_number":"pith:WCIKWOMA","canonical_record":{"source":{"id":"1805.08691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-04T07:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"f5b45341705ac223ee7b8792721feba0ebefce289d6fcf3a36ac544857a63f82","abstract_canon_sha256":"5d19e707787cd42e1df770f94da2b438b1e6372ea31df430a15044be26ca8792"},"schema_version":"1.0"},"canonical_sha256":"b090ab3980f0e994911510234ca366d5dd1c74f721a49f4b8ac5dbb6698d36b9","source":{"kind":"arxiv","id":"1805.08691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08691","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08691v1","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08691","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"WCIKWOMA6DUZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WCIKWOMA6DUZJEIV","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WCIKWOMA","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WCIKWOMA6DUZJEIVCARUZI3G2X","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-04T07:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"f5b45341705ac223ee7b8792721feba0ebefce289d6fcf3a36ac544857a63f82","abstract_canon_sha256":"5d19e707787cd42e1df770f94da2b438b1e6372ea31df430a15044be26ca8792"},"schema_version":"1.0"},"canonical_sha256":"b090ab3980f0e994911510234ca366d5dd1c74f721a49f4b8ac5dbb6698d36b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:25.363683Z","signature_b64":"+p+TOK4KyhRb79v5UJHDBT/mL/JFwXFMkX7uKxG6Q/IdqL7ecD8UAaLm4XOmc/3R2hnSlQl7pqUFf8HhC/dICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b090ab3980f0e994911510234ca366d5dd1c74f721a49f4b8ac5dbb6698d36b9","last_reissued_at":"2026-05-18T00:15:25.362620Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:25.362620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08691","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":"2026-05-18T00:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJNElwBhKSXpBN08RCsSUg9pR1FmsCbfzTrJhIoWtrEDRx72sqPxZvaMAk+ftpyNwjyqJB+40NzMcWXcfCiECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:40:13.615885Z"},"content_sha256":"465967d111feed1b822a25441f82a56fd3b3c0873d1a2ca4106479ebf33a8a4b","schema_version":"1.0","event_id":"sha256:465967d111feed1b822a25441f82a56fd3b3c0873d1a2ca4106479ebf33a8a4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WCIKWOMA6DUZJEIVCARUZI3G2X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eden Segal, Evarist Fomenko, Ge Jin, Guoming Zhang, Haihao Shen, Jiong Gong, Niharika Maheshwari, Shane Li, XiaoLi Liu","submitted_at":"2018-05-04T07:58:33Z","abstract_excerpt":"High throughput and low latency inference of deep neural networks are critical for the deployment of deep learning applications. This paper presents the efficient inference techniques of IntelCaffe, the first Intel optimized deep learning framework that supports efficient 8-bit low precision inference and model optimization techniques of convolutional neural networks on Intel Xeon Scalable Processors. The 8-bit optimized model is automatically generated with a calibration process from FP32 model without the need of fine-tuning or retraining. We show that the inference throughput and latency wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08691","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXxzCp1pWZjaQfSQROoN2Sh/+kKP/eU/iPXLcmwK3nYvGwmtJ0PNLsCSFtncpMB7bHnTlCuqocUGArFFp/EhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:40:13.616264Z"},"content_sha256":"231e2009fba1d10060f45b91bf3b02e48d0a8846b29f0d1b8f99d280eb4ca8ac","schema_version":"1.0","event_id":"sha256:231e2009fba1d10060f45b91bf3b02e48d0a8846b29f0d1b8f99d280eb4ca8ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCIKWOMA6DUZJEIVCARUZI3G2X/bundle.json","state_url":"https://pith.science/pith/WCIKWOMA6DUZJEIVCARUZI3G2X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCIKWOMA6DUZJEIVCARUZI3G2X/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":"2026-05-30T13:40:13Z","links":{"resolver":"https://pith.science/pith/WCIKWOMA6DUZJEIVCARUZI3G2X","bundle":"https://pith.science/pith/WCIKWOMA6DUZJEIVCARUZI3G2X/bundle.json","state":"https://pith.science/pith/WCIKWOMA6DUZJEIVCARUZI3G2X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCIKWOMA6DUZJEIVCARUZI3G2X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WCIKWOMA6DUZJEIVCARUZI3G2X","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":"5d19e707787cd42e1df770f94da2b438b1e6372ea31df430a15044be26ca8792","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-04T07:58:33Z","title_canon_sha256":"f5b45341705ac223ee7b8792721feba0ebefce289d6fcf3a36ac544857a63f82"},"schema_version":"1.0","source":{"id":"1805.08691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08691","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08691v1","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08691","created_at":"2026-05-18T00:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"WCIKWOMA6DUZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WCIKWOMA6DUZJEIV","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WCIKWOMA","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:231e2009fba1d10060f45b91bf3b02e48d0a8846b29f0d1b8f99d280eb4ca8ac","target":"graph","created_at":"2026-05-18T00:15:25Z","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":"High throughput and low latency inference of deep neural networks are critical for the deployment of deep learning applications. This paper presents the efficient inference techniques of IntelCaffe, the first Intel optimized deep learning framework that supports efficient 8-bit low precision inference and model optimization techniques of convolutional neural networks on Intel Xeon Scalable Processors. The 8-bit optimized model is automatically generated with a calibration process from FP32 model without the need of fine-tuning or retraining. We show that the inference throughput and latency wi","authors_text":"Eden Segal, Evarist Fomenko, Ge Jin, Guoming Zhang, Haihao Shen, Jiong Gong, Niharika Maheshwari, Shane Li, XiaoLi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-04T07:58:33Z","title":"Highly Efficient 8-bit Low Precision Inference of Convolutional Neural Networks with IntelCaffe"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08691","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":"sha256:465967d111feed1b822a25441f82a56fd3b3c0873d1a2ca4106479ebf33a8a4b","target":"record","created_at":"2026-05-18T00:15:25Z","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":"5d19e707787cd42e1df770f94da2b438b1e6372ea31df430a15044be26ca8792","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-04T07:58:33Z","title_canon_sha256":"f5b45341705ac223ee7b8792721feba0ebefce289d6fcf3a36ac544857a63f82"},"schema_version":"1.0","source":{"id":"1805.08691","kind":"arxiv","version":1}},"canonical_sha256":"b090ab3980f0e994911510234ca366d5dd1c74f721a49f4b8ac5dbb6698d36b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b090ab3980f0e994911510234ca366d5dd1c74f721a49f4b8ac5dbb6698d36b9","first_computed_at":"2026-05-18T00:15:25.362620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:25.362620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+p+TOK4KyhRb79v5UJHDBT/mL/JFwXFMkX7uKxG6Q/IdqL7ecD8UAaLm4XOmc/3R2hnSlQl7pqUFf8HhC/dICQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:25.363683Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:465967d111feed1b822a25441f82a56fd3b3c0873d1a2ca4106479ebf33a8a4b","sha256:231e2009fba1d10060f45b91bf3b02e48d0a8846b29f0d1b8f99d280eb4ca8ac"],"state_sha256":"0931fcc12049c3df567fd5e0708cfd5a7b765882cb5a22bd86c0ac99d0033628"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wD55+8ZFah/wRW05erQxYfyRfqQwsXNKSnEhyUQv2UzCOh+3A5pS6s+fpmmEaSVoYFjwqWPN4rA+/vImm1sQDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:40:13.618389Z","bundle_sha256":"d4d99b2a3152a30145ded66cda2962d9cfeb130966a6e17f2608c78aad958601"}}