{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KVBVYX4IMH5Q5ZZK7P3VMCC2C3","short_pith_number":"pith:KVBVYX4I","canonical_record":{"source":{"id":"1809.02697","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-09-07T22:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"2f6bb56d6ef861e4b06f0743c2d25e4c0b2ced3d8677ed07b4efc4456d16dd7f","abstract_canon_sha256":"c4f4758195ec2046bfecb3579b8b97d19d7bc1824604f355c1e0b229fe1aa006"},"schema_version":"1.0"},"canonical_sha256":"55435c5f8861fb0ee72afbf756085a16cec087a852d66f929b4fe161ccca7540","source":{"kind":"arxiv","id":"1809.02697","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02697","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02697v3","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02697","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"KVBVYX4IMH5Q","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KVBVYX4IMH5Q5ZZK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KVBVYX4I","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KVBVYX4IMH5Q5ZZK7P3VMCC2C3","target":"record","payload":{"canonical_record":{"source":{"id":"1809.02697","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-09-07T22:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"2f6bb56d6ef861e4b06f0743c2d25e4c0b2ced3d8677ed07b4efc4456d16dd7f","abstract_canon_sha256":"c4f4758195ec2046bfecb3579b8b97d19d7bc1824604f355c1e0b229fe1aa006"},"schema_version":"1.0"},"canonical_sha256":"55435c5f8861fb0ee72afbf756085a16cec087a852d66f929b4fe161ccca7540","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:22.086409Z","signature_b64":"DwYxjZQgN9m7m4FGsSRI4lcApYjDhyi/8Z965ex+fXRUwn9au959YpSRbr7yx+3xQ5nopIabjOk78ihP62TBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55435c5f8861fb0ee72afbf756085a16cec087a852d66f929b4fe161ccca7540","last_reissued_at":"2026-05-17T23:41:22.085906Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:22.085906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.02697","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":"2026-05-17T23:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nfsK3IzyVbJmtberAhSac2DC9DVdp24hGDg+ciPSlkGgswDeh9jGghjwuK15w/VBxqINtRMjsQ7Aat2ipluaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:08:27.483477Z"},"content_sha256":"2fc30235a046e4a10e088014c3dccb87369df60d8fa639795136c1e7f7064455","schema_version":"1.0","event_id":"sha256:2fc30235a046e4a10e088014c3dccb87369df60d8fa639795136c1e7f7064455"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KVBVYX4IMH5Q5ZZK7P3VMCC2C3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing CNN Model Inference on CPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Mu Li, Ruofei Yu, Vin Sharma, Yao Wang, Yida Wang, Yizhi Liu","submitted_at":"2018-09-07T22:09:23Z","abstract_excerpt":"The popularity of Convolutional Neural Network (CNN) models and the ubiquity of CPUs imply that better performance of CNN model inference on CPUs can deliver significant gain to a large number of users. To improve the performance of CNN inference on CPUs, current approaches like MXNet and Intel OpenVINO usually treat the model as a graph and use the high-performance libraries such as Intel MKL-DNN to implement the operations of the graph. While achieving reasonable performance on individual operations from the off-the-shelf libraries, this solution makes it inflexible to conduct optimizations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02697","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":"2026-05-17T23:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0stnWOFr2YAqyl5Nm3edaSJ3YSko2tFmGJ7zRtpJe9UAEoSd/zNREOTFhftcc1yLnbD0SDt8/BbIS/iCwsYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:08:27.484147Z"},"content_sha256":"b3067a62806243a6aa311a01b36660794abc6d67dfa570c9bf56e05ac42968d0","schema_version":"1.0","event_id":"sha256:b3067a62806243a6aa311a01b36660794abc6d67dfa570c9bf56e05ac42968d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KVBVYX4IMH5Q5ZZK7P3VMCC2C3/bundle.json","state_url":"https://pith.science/pith/KVBVYX4IMH5Q5ZZK7P3VMCC2C3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KVBVYX4IMH5Q5ZZK7P3VMCC2C3/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":"2026-05-25T20:08:27Z","links":{"resolver":"https://pith.science/pith/KVBVYX4IMH5Q5ZZK7P3VMCC2C3","bundle":"https://pith.science/pith/KVBVYX4IMH5Q5ZZK7P3VMCC2C3/bundle.json","state":"https://pith.science/pith/KVBVYX4IMH5Q5ZZK7P3VMCC2C3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KVBVYX4IMH5Q5ZZK7P3VMCC2C3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KVBVYX4IMH5Q5ZZK7P3VMCC2C3","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":"c4f4758195ec2046bfecb3579b8b97d19d7bc1824604f355c1e0b229fe1aa006","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-09-07T22:09:23Z","title_canon_sha256":"2f6bb56d6ef861e4b06f0743c2d25e4c0b2ced3d8677ed07b4efc4456d16dd7f"},"schema_version":"1.0","source":{"id":"1809.02697","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.02697","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1809.02697v3","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02697","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"KVBVYX4IMH5Q","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KVBVYX4IMH5Q5ZZK","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KVBVYX4I","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:b3067a62806243a6aa311a01b36660794abc6d67dfa570c9bf56e05ac42968d0","target":"graph","created_at":"2026-05-17T23:41:22Z","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":"The popularity of Convolutional Neural Network (CNN) models and the ubiquity of CPUs imply that better performance of CNN model inference on CPUs can deliver significant gain to a large number of users. To improve the performance of CNN inference on CPUs, current approaches like MXNet and Intel OpenVINO usually treat the model as a graph and use the high-performance libraries such as Intel MKL-DNN to implement the operations of the graph. While achieving reasonable performance on individual operations from the off-the-shelf libraries, this solution makes it inflexible to conduct optimizations ","authors_text":"Mu Li, Ruofei Yu, Vin Sharma, Yao Wang, Yida Wang, Yizhi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-09-07T22:09:23Z","title":"Optimizing CNN Model Inference on CPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02697","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":"sha256:2fc30235a046e4a10e088014c3dccb87369df60d8fa639795136c1e7f7064455","target":"record","created_at":"2026-05-17T23:41:22Z","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":"c4f4758195ec2046bfecb3579b8b97d19d7bc1824604f355c1e0b229fe1aa006","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-09-07T22:09:23Z","title_canon_sha256":"2f6bb56d6ef861e4b06f0743c2d25e4c0b2ced3d8677ed07b4efc4456d16dd7f"},"schema_version":"1.0","source":{"id":"1809.02697","kind":"arxiv","version":3}},"canonical_sha256":"55435c5f8861fb0ee72afbf756085a16cec087a852d66f929b4fe161ccca7540","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55435c5f8861fb0ee72afbf756085a16cec087a852d66f929b4fe161ccca7540","first_computed_at":"2026-05-17T23:41:22.085906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:22.085906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwYxjZQgN9m7m4FGsSRI4lcApYjDhyi/8Z965ex+fXRUwn9au959YpSRbr7yx+3xQ5nopIabjOk78ihP62TBBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:22.086409Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.02697","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fc30235a046e4a10e088014c3dccb87369df60d8fa639795136c1e7f7064455","sha256:b3067a62806243a6aa311a01b36660794abc6d67dfa570c9bf56e05ac42968d0"],"state_sha256":"f3d6ae6a26eca72d19b9d20320d3f3bd120adf1191ad1d936f1070fe3678aaf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0a4qP+NtysmVVT+zBfGCRW3pk2MAbYdsVvz8kG8SNh+5cbRg8DkD/Yew1xWLiK90Y+nyiK7Gq2+qtjSlI1p3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:08:27.487920Z","bundle_sha256":"29b4d0da59cc2d500d3cf5049db7c24e1f44392f2eb955139d8ac5123c28d140"}}