{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CZ5ATU3UB4M5MA2WQQOMZB6SCJ","short_pith_number":"pith:CZ5ATU3U","canonical_record":{"source":{"id":"1802.10280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-28T06:31:45Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"6aa6f04481eafb65c0b8cf7d259ec7b199cbfd109b5984c315d4b61c671cdd55","abstract_canon_sha256":"f5e6d29d2d5dc64816c1a616d6dbc7a382593d27d05bb3ebf98acc2df49b3d09"},"schema_version":"1.0"},"canonical_sha256":"167a09d3740f19d60356841ccc87d21276fc117ffcf9181a7596ca43dc9fc178","source":{"kind":"arxiv","id":"1802.10280","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10280","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10280v2","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10280","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"CZ5ATU3UB4M5","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CZ5ATU3UB4M5MA2W","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CZ5ATU3U","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CZ5ATU3UB4M5MA2WQQOMZB6SCJ","target":"record","payload":{"canonical_record":{"source":{"id":"1802.10280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-28T06:31:45Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"6aa6f04481eafb65c0b8cf7d259ec7b199cbfd109b5984c315d4b61c671cdd55","abstract_canon_sha256":"f5e6d29d2d5dc64816c1a616d6dbc7a382593d27d05bb3ebf98acc2df49b3d09"},"schema_version":"1.0"},"canonical_sha256":"167a09d3740f19d60356841ccc87d21276fc117ffcf9181a7596ca43dc9fc178","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:27.866593Z","signature_b64":"VWWQ3Jyn4YAjtxTVsz+BXsq1tzqUcv/BDhijIRMOrRYHGYUsE6RcpHykt7TnDWEs5AT3cVxrAvJi18t9hEqYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167a09d3740f19d60356841ccc87d21276fc117ffcf9181a7596ca43dc9fc178","last_reissued_at":"2026-05-17T23:49:27.865992Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:27.865992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.10280","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DyODkPdvKYm0IZShviIOEbhV1MMo8gywfiGPau2LNxCyat0sv3EM7T0nIw/Vd1qKJIA4v3ZhWl8XBmYc1iPwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:00:55.119281Z"},"content_sha256":"ae8ba15c445314f93a9e6cef34cb1dfb6e332198812cecb75709a3729ca3d3ee","schema_version":"1.0","event_id":"sha256:ae8ba15c445314f93a9e6cef34cb1dfb6e332198812cecb75709a3729ca3d3ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CZ5ATU3UB4M5MA2WQQOMZB6SCJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.DC","authors_text":"Xuhao Chen","submitted_at":"2018-02-28T06:31:45Z","abstract_excerpt":"Deep neural networks have achieved remarkable accuracy in many artificial intelligence applications, e.g. computer vision, at the cost of a large number of parameters and high computational complexity. Weight pruning can compress DNN models by removing redundant parameters in the networks, but it brings sparsity in the weight matrix, and therefore makes the computation inefficient on GPUs. Although pruning can remove more than 80% of the weights, it actually hurts inference performance (speed) when running models on GPUs.\n  Two major problems cause this unsatisfactory performance on GPUs. Firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10280","kind":"arxiv","version":2},"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":"2026-05-17T23:49:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S0mbS/sTHHaW9sS1Yq5a9Ys+ACbSLVeSwrK/F2ADKKNulyZqrx2gk2+evYvxU9gv9qHXCdAvDBrUkViTZc3qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:00:55.119970Z"},"content_sha256":"9acf1cc59938293915e28a2991e75070870e85c1128c7dfaceb60342bf547148","schema_version":"1.0","event_id":"sha256:9acf1cc59938293915e28a2991e75070870e85c1128c7dfaceb60342bf547148"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZ5ATU3UB4M5MA2WQQOMZB6SCJ/bundle.json","state_url":"https://pith.science/pith/CZ5ATU3UB4M5MA2WQQOMZB6SCJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZ5ATU3UB4M5MA2WQQOMZB6SCJ/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":"2026-05-25T15:00:55Z","links":{"resolver":"https://pith.science/pith/CZ5ATU3UB4M5MA2WQQOMZB6SCJ","bundle":"https://pith.science/pith/CZ5ATU3UB4M5MA2WQQOMZB6SCJ/bundle.json","state":"https://pith.science/pith/CZ5ATU3UB4M5MA2WQQOMZB6SCJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZ5ATU3UB4M5MA2WQQOMZB6SCJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CZ5ATU3UB4M5MA2WQQOMZB6SCJ","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":"f5e6d29d2d5dc64816c1a616d6dbc7a382593d27d05bb3ebf98acc2df49b3d09","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-28T06:31:45Z","title_canon_sha256":"6aa6f04481eafb65c0b8cf7d259ec7b199cbfd109b5984c315d4b61c671cdd55"},"schema_version":"1.0","source":{"id":"1802.10280","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10280","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10280v2","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10280","created_at":"2026-05-17T23:49:27Z"},{"alias_kind":"pith_short_12","alias_value":"CZ5ATU3UB4M5","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CZ5ATU3UB4M5MA2W","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CZ5ATU3U","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:9acf1cc59938293915e28a2991e75070870e85c1128c7dfaceb60342bf547148","target":"graph","created_at":"2026-05-17T23:49:27Z","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":"Deep neural networks have achieved remarkable accuracy in many artificial intelligence applications, e.g. computer vision, at the cost of a large number of parameters and high computational complexity. Weight pruning can compress DNN models by removing redundant parameters in the networks, but it brings sparsity in the weight matrix, and therefore makes the computation inefficient on GPUs. Although pruning can remove more than 80% of the weights, it actually hurts inference performance (speed) when running models on GPUs.\n  Two major problems cause this unsatisfactory performance on GPUs. Firs","authors_text":"Xuhao Chen","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-28T06:31:45Z","title":"Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10280","kind":"arxiv","version":2},"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:ae8ba15c445314f93a9e6cef34cb1dfb6e332198812cecb75709a3729ca3d3ee","target":"record","created_at":"2026-05-17T23:49:27Z","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":"f5e6d29d2d5dc64816c1a616d6dbc7a382593d27d05bb3ebf98acc2df49b3d09","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-02-28T06:31:45Z","title_canon_sha256":"6aa6f04481eafb65c0b8cf7d259ec7b199cbfd109b5984c315d4b61c671cdd55"},"schema_version":"1.0","source":{"id":"1802.10280","kind":"arxiv","version":2}},"canonical_sha256":"167a09d3740f19d60356841ccc87d21276fc117ffcf9181a7596ca43dc9fc178","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"167a09d3740f19d60356841ccc87d21276fc117ffcf9181a7596ca43dc9fc178","first_computed_at":"2026-05-17T23:49:27.865992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:27.865992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VWWQ3Jyn4YAjtxTVsz+BXsq1tzqUcv/BDhijIRMOrRYHGYUsE6RcpHykt7TnDWEs5AT3cVxrAvJi18t9hEqYCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:27.866593Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.10280","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae8ba15c445314f93a9e6cef34cb1dfb6e332198812cecb75709a3729ca3d3ee","sha256:9acf1cc59938293915e28a2991e75070870e85c1128c7dfaceb60342bf547148"],"state_sha256":"d28e75c9b7ef2555d3a538a610ef02af2d60f14c7c5313dd23221135a0e29e9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N2F2jIazYxpNln/yPEEXPQ0LxJPBAdkdSUBgO5Ad+DcCUxZwiNhrWmLeukArAbycM9HYsU/zusU8GFHbipX/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:00:55.123255Z","bundle_sha256":"128234253d86d3d26110eb6f583da333edef37bee5f7030fe637f7923fac134a"}}