{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XEPFBQDWNYZ2ZULXMMFMHRJJJI","short_pith_number":"pith:XEPFBQDW","canonical_record":{"source":{"id":"1906.03951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T11:11:01Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"45a1f31d7d59a2dd76b3428af71471bf88e25a7ab9a90dcd6b42621e73f2939c","abstract_canon_sha256":"f69ef0645621ab3354bf4a26a8b3f72bcbd87429bbb5776728ec459fd165f4df"},"schema_version":"1.0"},"canonical_sha256":"b91e50c0766e33acd177630ac3c5294a298c0504c9be034190855359cd29fdbd","source":{"kind":"arxiv","id":"1906.03951","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03951","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03951v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03951","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"XEPFBQDWNYZ2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XEPFBQDWNYZ2ZULX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XEPFBQDW","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XEPFBQDWNYZ2ZULXMMFMHRJJJI","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T11:11:01Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"45a1f31d7d59a2dd76b3428af71471bf88e25a7ab9a90dcd6b42621e73f2939c","abstract_canon_sha256":"f69ef0645621ab3354bf4a26a8b3f72bcbd87429bbb5776728ec459fd165f4df"},"schema_version":"1.0"},"canonical_sha256":"b91e50c0766e33acd177630ac3c5294a298c0504c9be034190855359cd29fdbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:44.423723Z","signature_b64":"ojP+VhlOI1I+pXRu6NpjqKhI+J0EFbOp+cAy75k4JVVhfojr5xiZWKOcgFx41u7gD3LnJUONLn7cVzHfp2NkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b91e50c0766e33acd177630ac3c5294a298c0504c9be034190855359cd29fdbd","last_reissued_at":"2026-05-17T23:43:44.423136Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:44.423136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03951","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":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qIPEggoJrnZMPRp0rUV8dGG9ui2gq7vHWKmQqFHW/DVHl4BfT0oHbicbaFbI8XgUg0rmK8VLUL/TJB1Bvu38CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:43:54.807177Z"},"content_sha256":"119c34fb416ce02a74fb99819156de4e899a772eb202d6c03bc158cfca45b165","schema_version":"1.0","event_id":"sha256:119c34fb416ce02a74fb99819156de4e899a772eb202d6c03bc158cfca45b165"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XEPFBQDWNYZ2ZULXMMFMHRJJJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenglong Bao, Jiebo Song, Jingwei Chen, Kaisheng Ma, Linfeng Zhang, Zhanhong Tan","submitted_at":"2019-05-27T11:11:01Z","abstract_excerpt":"Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the deployment of deep neural networks on resource-limited edge devices. To address this problem, we propose the so-called SCAN framework for networks training and inference, which is orthogonal and complementary to existing acceleration and compression methods. The proposed SCAN firstly divides neural networks into multiple sections according to their depth and cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03951","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":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1P+wdD90ONpIJu6XQ8yYjQfp2SScML1aWZMnWYcqQeY9KSQBEHb3xKhZGm+2vicHmhRpR9aySXpIelxNbZsFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:43:54.807537Z"},"content_sha256":"6ba3128214e2e3a5afa49e31255e44814ac7fc11c972663c0b90fd931fbca261","schema_version":"1.0","event_id":"sha256:6ba3128214e2e3a5afa49e31255e44814ac7fc11c972663c0b90fd931fbca261"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XEPFBQDWNYZ2ZULXMMFMHRJJJI/bundle.json","state_url":"https://pith.science/pith/XEPFBQDWNYZ2ZULXMMFMHRJJJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XEPFBQDWNYZ2ZULXMMFMHRJJJI/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":"2026-06-01T07:43:54Z","links":{"resolver":"https://pith.science/pith/XEPFBQDWNYZ2ZULXMMFMHRJJJI","bundle":"https://pith.science/pith/XEPFBQDWNYZ2ZULXMMFMHRJJJI/bundle.json","state":"https://pith.science/pith/XEPFBQDWNYZ2ZULXMMFMHRJJJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XEPFBQDWNYZ2ZULXMMFMHRJJJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XEPFBQDWNYZ2ZULXMMFMHRJJJI","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":"f69ef0645621ab3354bf4a26a8b3f72bcbd87429bbb5776728ec459fd165f4df","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T11:11:01Z","title_canon_sha256":"45a1f31d7d59a2dd76b3428af71471bf88e25a7ab9a90dcd6b42621e73f2939c"},"schema_version":"1.0","source":{"id":"1906.03951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03951","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03951v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03951","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"XEPFBQDWNYZ2","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XEPFBQDWNYZ2ZULX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XEPFBQDW","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:6ba3128214e2e3a5afa49e31255e44814ac7fc11c972663c0b90fd931fbca261","target":"graph","created_at":"2026-05-17T23:43:44Z","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":"Remarkable achievements have been attained by deep neural networks in various applications. However, the increasing depth and width of such models also lead to explosive growth in both storage and computation, which has restricted the deployment of deep neural networks on resource-limited edge devices. To address this problem, we propose the so-called SCAN framework for networks training and inference, which is orthogonal and complementary to existing acceleration and compression methods. The proposed SCAN firstly divides neural networks into multiple sections according to their depth and cons","authors_text":"Chenglong Bao, Jiebo Song, Jingwei Chen, Kaisheng Ma, Linfeng Zhang, Zhanhong Tan","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T11:11:01Z","title":"SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03951","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":"sha256:119c34fb416ce02a74fb99819156de4e899a772eb202d6c03bc158cfca45b165","target":"record","created_at":"2026-05-17T23:43:44Z","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":"f69ef0645621ab3354bf4a26a8b3f72bcbd87429bbb5776728ec459fd165f4df","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T11:11:01Z","title_canon_sha256":"45a1f31d7d59a2dd76b3428af71471bf88e25a7ab9a90dcd6b42621e73f2939c"},"schema_version":"1.0","source":{"id":"1906.03951","kind":"arxiv","version":1}},"canonical_sha256":"b91e50c0766e33acd177630ac3c5294a298c0504c9be034190855359cd29fdbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b91e50c0766e33acd177630ac3c5294a298c0504c9be034190855359cd29fdbd","first_computed_at":"2026-05-17T23:43:44.423136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:44.423136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ojP+VhlOI1I+pXRu6NpjqKhI+J0EFbOp+cAy75k4JVVhfojr5xiZWKOcgFx41u7gD3LnJUONLn7cVzHfp2NkDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:44.423723Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:119c34fb416ce02a74fb99819156de4e899a772eb202d6c03bc158cfca45b165","sha256:6ba3128214e2e3a5afa49e31255e44814ac7fc11c972663c0b90fd931fbca261"],"state_sha256":"b28edd2f6dad1608b600833a0b13d0f98321702785795093efe373c804568068"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RjprcDdQnD75+vcggdc3ImyOvh+IPenFrmtuR89l7VJZwhw+E4PBZzPYvV8CltMajhADlUrXdzq0lWUBmsViBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:43:54.809440Z","bundle_sha256":"164c982e9c74c277a87fc3161558397700ea2b07cb0fe2404ed10289c7a6692b"}}