{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:XWS4LESLCCBHAIE3T4ZZKYAIA2","short_pith_number":"pith:XWS4LESL","canonical_record":{"source":{"id":"1610.09639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-30T11:57:20Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"a458ab655f4ad2a89648473a3ade34fd9578cede4579c210897efe07fdd5a338","abstract_canon_sha256":"c8407ddbdde9a0c01ab5c33714ecab45d6b5291f3dfac0a3eefee5a71550faab"},"schema_version":"1.0"},"canonical_sha256":"bda5c5924b108270209b9f3395600806aa4224c13b0f771200e5fcf1abcab847","source":{"kind":"arxiv","id":"1610.09639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09639","created_at":"2026-05-18T01:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09639v1","created_at":"2026-05-18T01:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09639","created_at":"2026-05-18T01:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"XWS4LESLCCBH","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XWS4LESLCCBHAIE3","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XWS4LESL","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:XWS4LESLCCBHAIE3T4ZZKYAIA2","target":"record","payload":{"canonical_record":{"source":{"id":"1610.09639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-30T11:57:20Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"a458ab655f4ad2a89648473a3ade34fd9578cede4579c210897efe07fdd5a338","abstract_canon_sha256":"c8407ddbdde9a0c01ab5c33714ecab45d6b5291f3dfac0a3eefee5a71550faab"},"schema_version":"1.0"},"canonical_sha256":"bda5c5924b108270209b9f3395600806aa4224c13b0f771200e5fcf1abcab847","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:51.413287Z","signature_b64":"xkBMPbaYJoSPNviiBBgn1Dxio1gq9oVSl76kRPAQxQK4R8IfPiP1iwicRsrYxKrskRZoV7HN3Ht4Nhh6PQeQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bda5c5924b108270209b9f3395600806aa4224c13b0f771200e5fcf1abcab847","last_reissued_at":"2026-05-18T01:00:51.412645Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:51.412645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.09639","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":"2026-05-18T01:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMYH/lRXUfWqmYfntkJCeWtjn8TdbLEDoaROJeKdQ376KDncgHGu/czhrNV0EKwQz0Hn7VFkN776r8ZDeu/LAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T06:50:54.336863Z"},"content_sha256":"47452abea3f45f4fe465ada7fd9d2c37e4a7c56538c66f70cb7b8181c397310c","schema_version":"1.0","event_id":"sha256:47452abea3f45f4fe465ada7fd9d2c37e4a7c56538c66f70cb7b8181c397310c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:XWS4LESLCCBHAIE3T4ZZKYAIA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compact Deep Convolutional Neural Networks With Coarse Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Sajid Anwar, Wonyong Sung","submitted_at":"2016-10-30T11:57:20Z","abstract_excerpt":"The learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature map and kernel level pruning for reducing the computational complexity of a deep convolutional neural network. Pruning feature maps reduces the width of a layer and hence does not need any sparse representation. Further, kernel pruning converts the dense connectivity pattern into a sparse one. Due to coarse nature, these pruning granularities can be exploit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09639","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":"2026-05-18T01:00:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W19OGqpdMLOC4RONboJs3G7OWVsD//yBLnAqf+YCNd4LX79tiyxvE60SoVN8rqj0PjrnPJ526OF6vTivBuEKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T06:50:54.337199Z"},"content_sha256":"9b57c5e7b0e18734cdddbef219299d98d0eca97a3d7c80a8c5b05763002c06fc","schema_version":"1.0","event_id":"sha256:9b57c5e7b0e18734cdddbef219299d98d0eca97a3d7c80a8c5b05763002c06fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWS4LESLCCBHAIE3T4ZZKYAIA2/bundle.json","state_url":"https://pith.science/pith/XWS4LESLCCBHAIE3T4ZZKYAIA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWS4LESLCCBHAIE3T4ZZKYAIA2/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":"2026-06-25T06:50:54Z","links":{"resolver":"https://pith.science/pith/XWS4LESLCCBHAIE3T4ZZKYAIA2","bundle":"https://pith.science/pith/XWS4LESLCCBHAIE3T4ZZKYAIA2/bundle.json","state":"https://pith.science/pith/XWS4LESLCCBHAIE3T4ZZKYAIA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWS4LESLCCBHAIE3T4ZZKYAIA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XWS4LESLCCBHAIE3T4ZZKYAIA2","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":"c8407ddbdde9a0c01ab5c33714ecab45d6b5291f3dfac0a3eefee5a71550faab","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-30T11:57:20Z","title_canon_sha256":"a458ab655f4ad2a89648473a3ade34fd9578cede4579c210897efe07fdd5a338"},"schema_version":"1.0","source":{"id":"1610.09639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09639","created_at":"2026-05-18T01:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09639v1","created_at":"2026-05-18T01:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09639","created_at":"2026-05-18T01:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"XWS4LESLCCBH","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XWS4LESLCCBHAIE3","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XWS4LESL","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:9b57c5e7b0e18734cdddbef219299d98d0eca97a3d7c80a8c5b05763002c06fc","target":"graph","created_at":"2026-05-18T01:00:51Z","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 learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature map and kernel level pruning for reducing the computational complexity of a deep convolutional neural network. Pruning feature maps reduces the width of a layer and hence does not need any sparse representation. Further, kernel pruning converts the dense connectivity pattern into a sparse one. Due to coarse nature, these pruning granularities can be exploit","authors_text":"Sajid Anwar, Wonyong Sung","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-30T11:57:20Z","title":"Compact Deep Convolutional Neural Networks With Coarse Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09639","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":"sha256:47452abea3f45f4fe465ada7fd9d2c37e4a7c56538c66f70cb7b8181c397310c","target":"record","created_at":"2026-05-18T01:00:51Z","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":"c8407ddbdde9a0c01ab5c33714ecab45d6b5291f3dfac0a3eefee5a71550faab","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-30T11:57:20Z","title_canon_sha256":"a458ab655f4ad2a89648473a3ade34fd9578cede4579c210897efe07fdd5a338"},"schema_version":"1.0","source":{"id":"1610.09639","kind":"arxiv","version":1}},"canonical_sha256":"bda5c5924b108270209b9f3395600806aa4224c13b0f771200e5fcf1abcab847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bda5c5924b108270209b9f3395600806aa4224c13b0f771200e5fcf1abcab847","first_computed_at":"2026-05-18T01:00:51.412645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:51.412645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xkBMPbaYJoSPNviiBBgn1Dxio1gq9oVSl76kRPAQxQK4R8IfPiP1iwicRsrYxKrskRZoV7HN3Ht4Nhh6PQeQAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:51.413287Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.09639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47452abea3f45f4fe465ada7fd9d2c37e4a7c56538c66f70cb7b8181c397310c","sha256:9b57c5e7b0e18734cdddbef219299d98d0eca97a3d7c80a8c5b05763002c06fc"],"state_sha256":"9097bcb8202bae1c1cc0bc662b41e5a99f5820a8483ccf822768feacdc94a107"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/TdzXttyadfB0qAlV88EE4pvMJVuWlOEFRGnjMDsnemuS5OCelYXGGw0Hdo8wmcIcbBTM67EA5t8t6kcAX4tCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T06:50:54.339132Z","bundle_sha256":"3342e9f72927a02b635eea852d4a6153d25323b01e76faf65e9cbddf0e6c1ffa"}}