{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:5RX76CQTYO454GCTPX2PY3JCGQ","short_pith_number":"pith:5RX76CQT","canonical_record":{"source":{"id":"1606.05688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-06-17T22:16:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6034dbc4f6580a8a4838198ddd6ed586b8f8dc7e998e4b70bb47b2b55c2175e7","abstract_canon_sha256":"b05951fbd5c9ec65c9a9e544056a2d71830a0481e8f730647137c3f4eaf6de3c"},"schema_version":"1.0"},"canonical_sha256":"ec6fff0a13c3b9de18537df4fc6d223419d7563206cb7fae01c1f2ced29a57a4","source":{"kind":"arxiv","id":"1606.05688","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05688","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05688v1","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05688","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"5RX76CQTYO45","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5RX76CQTYO454GCT","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5RX76CQT","created_at":"2026-05-18T12:30:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:5RX76CQTYO454GCTPX2PY3JCGQ","target":"record","payload":{"canonical_record":{"source":{"id":"1606.05688","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-06-17T22:16:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6034dbc4f6580a8a4838198ddd6ed586b8f8dc7e998e4b70bb47b2b55c2175e7","abstract_canon_sha256":"b05951fbd5c9ec65c9a9e544056a2d71830a0481e8f730647137c3f4eaf6de3c"},"schema_version":"1.0"},"canonical_sha256":"ec6fff0a13c3b9de18537df4fc6d223419d7563206cb7fae01c1f2ced29a57a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:16.288646Z","signature_b64":"Uaqnf3WCpd//LMZLNwVu+4eQhzDSKVmuaDvWG0IWYZsXswS53SnEMdh08w+Y8Ceo5u82O96ZVFENwmXpuQ+JAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec6fff0a13c3b9de18537df4fc6d223419d7563206cb7fae01c1f2ced29a57a4","last_reissued_at":"2026-05-18T01:12:16.288313Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:16.288313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.05688","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":"2026-05-18T01:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vc7C/EsgVa0hqIqtxd2bTyuyUJrZXpLB9oi6edBuTj/P3onlkY/PkPkTjlL1M89G79kreUpkSyWhtm9Xd5PYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:46:18.824451Z"},"content_sha256":"85d5f4a5219db2104f68a9e976ae20477588635aab51bdf7f7d68401c34e44a9","schema_version":"1.0","event_id":"sha256:85d5f4a5219db2104f68a9e976ae20477588635aab51bdf7f7d68401c34e44a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:5RX76CQTYO454GCTPX2PY3JCGQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Aleksandar Zlateski, H. Sebastian Seung, Kisuk Lee","submitted_at":"2016-06-17T22:16:39Z","abstract_excerpt":"Sliding window convolutional networks (ConvNets) have become a popular approach to computer vision problems such as image segmentation, and object detection and localization. Here we consider the problem of inference, the application of a previously trained ConvNet, with emphasis on 3D images. Our goal is to maximize throughput, defined as average number of output voxels computed per unit time. Other things being equal, processing a larger image tends to increase throughput, because fractionally less computation is wasted on the borders of the image. It follows that an apparently slower algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05688","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":"2026-05-18T01:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z4ExsWFUGDPsvOfyggi9BDqfy4KkazUTvZoszYAv8NgaEMmGI8ICVP0cZCsiyxyxrBYo3ZYwlq6hmCySIwLLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T09:46:18.824839Z"},"content_sha256":"93f75fe8a5ee358d511587412a7c4b62d52f1cfa22f80fb5eea9c8b14cb46ff0","schema_version":"1.0","event_id":"sha256:93f75fe8a5ee358d511587412a7c4b62d52f1cfa22f80fb5eea9c8b14cb46ff0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RX76CQTYO454GCTPX2PY3JCGQ/bundle.json","state_url":"https://pith.science/pith/5RX76CQTYO454GCTPX2PY3JCGQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RX76CQTYO454GCTPX2PY3JCGQ/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":"2026-06-07T09:46:18Z","links":{"resolver":"https://pith.science/pith/5RX76CQTYO454GCTPX2PY3JCGQ","bundle":"https://pith.science/pith/5RX76CQTYO454GCTPX2PY3JCGQ/bundle.json","state":"https://pith.science/pith/5RX76CQTYO454GCTPX2PY3JCGQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RX76CQTYO454GCTPX2PY3JCGQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:5RX76CQTYO454GCTPX2PY3JCGQ","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":"b05951fbd5c9ec65c9a9e544056a2d71830a0481e8f730647137c3f4eaf6de3c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-06-17T22:16:39Z","title_canon_sha256":"6034dbc4f6580a8a4838198ddd6ed586b8f8dc7e998e4b70bb47b2b55c2175e7"},"schema_version":"1.0","source":{"id":"1606.05688","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.05688","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"1606.05688v1","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.05688","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"5RX76CQTYO45","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_16","alias_value":"5RX76CQTYO454GCT","created_at":"2026-05-18T12:30:01Z"},{"alias_kind":"pith_short_8","alias_value":"5RX76CQT","created_at":"2026-05-18T12:30:01Z"}],"graph_snapshots":[{"event_id":"sha256:93f75fe8a5ee358d511587412a7c4b62d52f1cfa22f80fb5eea9c8b14cb46ff0","target":"graph","created_at":"2026-05-18T01:12:16Z","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":"Sliding window convolutional networks (ConvNets) have become a popular approach to computer vision problems such as image segmentation, and object detection and localization. Here we consider the problem of inference, the application of a previously trained ConvNet, with emphasis on 3D images. Our goal is to maximize throughput, defined as average number of output voxels computed per unit time. Other things being equal, processing a larger image tends to increase throughput, because fractionally less computation is wasted on the borders of the image. It follows that an apparently slower algori","authors_text":"Aleksandar Zlateski, H. Sebastian Seung, Kisuk Lee","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-06-17T22:16:39Z","title":"ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.05688","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":"sha256:85d5f4a5219db2104f68a9e976ae20477588635aab51bdf7f7d68401c34e44a9","target":"record","created_at":"2026-05-18T01:12:16Z","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":"b05951fbd5c9ec65c9a9e544056a2d71830a0481e8f730647137c3f4eaf6de3c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2016-06-17T22:16:39Z","title_canon_sha256":"6034dbc4f6580a8a4838198ddd6ed586b8f8dc7e998e4b70bb47b2b55c2175e7"},"schema_version":"1.0","source":{"id":"1606.05688","kind":"arxiv","version":1}},"canonical_sha256":"ec6fff0a13c3b9de18537df4fc6d223419d7563206cb7fae01c1f2ced29a57a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec6fff0a13c3b9de18537df4fc6d223419d7563206cb7fae01c1f2ced29a57a4","first_computed_at":"2026-05-18T01:12:16.288313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:16.288313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uaqnf3WCpd//LMZLNwVu+4eQhzDSKVmuaDvWG0IWYZsXswS53SnEMdh08w+Y8Ceo5u82O96ZVFENwmXpuQ+JAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:16.288646Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.05688","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85d5f4a5219db2104f68a9e976ae20477588635aab51bdf7f7d68401c34e44a9","sha256:93f75fe8a5ee358d511587412a7c4b62d52f1cfa22f80fb5eea9c8b14cb46ff0"],"state_sha256":"0abd16fa51b62260573ee4842431a352c897bfd70f89bfd91486175cdd60646c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tTQTbNrRI0B2H5HoZTGJEdDpgRwNv0pnlSuEm/qUeDfYUCSYT/iHYYXKhxj8w96/QFJCEqEj1xX6IjS8QtUTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T09:46:18.827942Z","bundle_sha256":"7b8d99bbd5461ad6b222f4ff1e97a3c0eed7a9cdef64346f7b81198b499c1da4"}}