{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PD4CDHCWOZ2DLJX4SVOCIIF5NI","short_pith_number":"pith:PD4CDHCW","canonical_record":{"source":{"id":"1810.08899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-21T05:09:45Z","cross_cats_sorted":["cs.DC","cs.PF","stat.ML"],"title_canon_sha256":"5819b7a806824902020b7f92a63cc9b7f433f187053f6b22a168aa9b6a9f8f8b","abstract_canon_sha256":"5b3ebbf47d13f8ca723e4b26f801770ca24110a611ae30b9a796e6815c739960"},"schema_version":"1.0"},"canonical_sha256":"78f8219c56767435a6fc955c2420bd6a2119dcaf27e0b45facceed6eca636820","source":{"kind":"arxiv","id":"1810.08899","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08899","created_at":"2026-05-18T00:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08899v1","created_at":"2026-05-18T00:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08899","created_at":"2026-05-18T00:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"PD4CDHCWOZ2D","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PD4CDHCWOZ2DLJX4","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PD4CDHCW","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PD4CDHCWOZ2DLJX4SVOCIIF5NI","target":"record","payload":{"canonical_record":{"source":{"id":"1810.08899","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-21T05:09:45Z","cross_cats_sorted":["cs.DC","cs.PF","stat.ML"],"title_canon_sha256":"5819b7a806824902020b7f92a63cc9b7f433f187053f6b22a168aa9b6a9f8f8b","abstract_canon_sha256":"5b3ebbf47d13f8ca723e4b26f801770ca24110a611ae30b9a796e6815c739960"},"schema_version":"1.0"},"canonical_sha256":"78f8219c56767435a6fc955c2420bd6a2119dcaf27e0b45facceed6eca636820","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:41.520886Z","signature_b64":"5Lf20ea0BBoosCKcgfgPYTFtmYbPOoDkhbywkqBbEo1aMH5YoG7xsrHyU5auhEe8Xxmlc+hT15pKVDVzvTSXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78f8219c56767435a6fc955c2420bd6a2119dcaf27e0b45facceed6eca636820","last_reissued_at":"2026-05-18T00:02:41.520464Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:41.520464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.08899","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":"2026-05-18T00:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XF+R/Z9QZUmJviDZ8p2PNYCqNflQUaVcRd8C3AeKy9wPHm+1G8amntqALsXPMdU5lrPIqIHhEFRcE7ordK27DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:43:41.040960Z"},"content_sha256":"6d8b8359939a92e4d2a5fcca7d21b5563efb564190cc6b391af21218c4d3ac90","schema_version":"1.0","event_id":"sha256:6d8b8359939a92e4d2a5fcca7d21b5563efb564190cc6b391af21218c4d3ac90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PD4CDHCWOZ2DLJX4SVOCIIF5NI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.PF","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hai Wang, Jialong Yu, Jianbin Fang, Jie Ren, Jie Zheng, Ling Gao, Qing Qin, Yansong Feng, Zheng Wang","submitted_at":"2018-10-21T05:09:45Z","abstract_excerpt":"The recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained computing devices. Model compression techniques can address the computation issue of deep inference on embedded devices. This technique is highly attractive, as it does not rely on specialized hardware, or computation-offloading that is often infeasible due to privacy concerns or high latency. However, it remains unclear how model compression techniques perform across a wide range of DNNs. To design efficient embedd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08899","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":"2026-05-18T00:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GH8kfu6O5XyWRDCzVHvLdR2Y3QJndDQpAby2zolNZ8M/6KGKC904N5gALDROdS9czTqdVXg/2LtxM5u9AZVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:43:41.041313Z"},"content_sha256":"5415161db620172a2a47266609917763bb5a3fe7b416383d3b672aa6b1c60c84","schema_version":"1.0","event_id":"sha256:5415161db620172a2a47266609917763bb5a3fe7b416383d3b672aa6b1c60c84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PD4CDHCWOZ2DLJX4SVOCIIF5NI/bundle.json","state_url":"https://pith.science/pith/PD4CDHCWOZ2DLJX4SVOCIIF5NI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PD4CDHCWOZ2DLJX4SVOCIIF5NI/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":"2026-05-27T13:43:41Z","links":{"resolver":"https://pith.science/pith/PD4CDHCWOZ2DLJX4SVOCIIF5NI","bundle":"https://pith.science/pith/PD4CDHCWOZ2DLJX4SVOCIIF5NI/bundle.json","state":"https://pith.science/pith/PD4CDHCWOZ2DLJX4SVOCIIF5NI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PD4CDHCWOZ2DLJX4SVOCIIF5NI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PD4CDHCWOZ2DLJX4SVOCIIF5NI","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":"5b3ebbf47d13f8ca723e4b26f801770ca24110a611ae30b9a796e6815c739960","cross_cats_sorted":["cs.DC","cs.PF","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-21T05:09:45Z","title_canon_sha256":"5819b7a806824902020b7f92a63cc9b7f433f187053f6b22a168aa9b6a9f8f8b"},"schema_version":"1.0","source":{"id":"1810.08899","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08899","created_at":"2026-05-18T00:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08899v1","created_at":"2026-05-18T00:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08899","created_at":"2026-05-18T00:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"PD4CDHCWOZ2D","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PD4CDHCWOZ2DLJX4","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PD4CDHCW","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:5415161db620172a2a47266609917763bb5a3fe7b416383d3b672aa6b1c60c84","target":"graph","created_at":"2026-05-18T00:02:41Z","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 recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained computing devices. Model compression techniques can address the computation issue of deep inference on embedded devices. This technique is highly attractive, as it does not rely on specialized hardware, or computation-offloading that is often infeasible due to privacy concerns or high latency. However, it remains unclear how model compression techniques perform across a wide range of DNNs. To design efficient embedd","authors_text":"Hai Wang, Jialong Yu, Jianbin Fang, Jie Ren, Jie Zheng, Ling Gao, Qing Qin, Yansong Feng, Zheng Wang","cross_cats":["cs.DC","cs.PF","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-21T05:09:45Z","title":"To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08899","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":"sha256:6d8b8359939a92e4d2a5fcca7d21b5563efb564190cc6b391af21218c4d3ac90","target":"record","created_at":"2026-05-18T00:02:41Z","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":"5b3ebbf47d13f8ca723e4b26f801770ca24110a611ae30b9a796e6815c739960","cross_cats_sorted":["cs.DC","cs.PF","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-21T05:09:45Z","title_canon_sha256":"5819b7a806824902020b7f92a63cc9b7f433f187053f6b22a168aa9b6a9f8f8b"},"schema_version":"1.0","source":{"id":"1810.08899","kind":"arxiv","version":1}},"canonical_sha256":"78f8219c56767435a6fc955c2420bd6a2119dcaf27e0b45facceed6eca636820","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78f8219c56767435a6fc955c2420bd6a2119dcaf27e0b45facceed6eca636820","first_computed_at":"2026-05-18T00:02:41.520464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:41.520464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Lf20ea0BBoosCKcgfgPYTFtmYbPOoDkhbywkqBbEo1aMH5YoG7xsrHyU5auhEe8Xxmlc+hT15pKVDVzvTSXAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:41.520886Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.08899","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d8b8359939a92e4d2a5fcca7d21b5563efb564190cc6b391af21218c4d3ac90","sha256:5415161db620172a2a47266609917763bb5a3fe7b416383d3b672aa6b1c60c84"],"state_sha256":"61f5fbdb6c6803ded345a9d9bf408fc346acb66604d6c0cf16c919667932774c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1q3gC7eylmsXjnE5L0YzaFG6liLQ10BAUryPx1JIA1tVKt+lnhFtWF8kgMlV2H/aqodW+n7gmPSj/FNwbbx6Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:43:41.043588Z","bundle_sha256":"111cb0ffab22264697768da13ff939ff7e318d67e8be0a1815e7dcd0d8faae8b"}}