{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:42HGPQPE7VXHUV72N5NVMP5IQ6","short_pith_number":"pith:42HGPQPE","canonical_record":{"source":{"id":"1802.07653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T16:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"a592a1ef93daa1691b87023f041329bbc15c052a73104e2e8c31d7669f6cde81","abstract_canon_sha256":"6e9bc6ecd1d8bf5371f5c5db972b5bc13a6108742e9aea8560068db450bc3a47"},"schema_version":"1.0"},"canonical_sha256":"e68e67c1e4fd6e7a57fa6f5b563fa8879961e2175b4d463dc8d90cf59b47b9c3","source":{"kind":"arxiv","id":"1802.07653","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07653","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07653v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07653","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"42HGPQPE7VXH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"42HGPQPE7VXHUV72","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"42HGPQPE","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:42HGPQPE7VXHUV72N5NVMP5IQ6","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T16:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"a592a1ef93daa1691b87023f041329bbc15c052a73104e2e8c31d7669f6cde81","abstract_canon_sha256":"6e9bc6ecd1d8bf5371f5c5db972b5bc13a6108742e9aea8560068db450bc3a47"},"schema_version":"1.0"},"canonical_sha256":"e68e67c1e4fd6e7a57fa6f5b563fa8879961e2175b4d463dc8d90cf59b47b9c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.698244Z","signature_b64":"4lDDg229NaeNPG2GzmuYRr34vba3dMdFpPKUFZQ9/IT5qlSkD0br8Q266HZllg9w0U2ksudB8FucqSaqag85Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e68e67c1e4fd6e7a57fa6f5b563fa8879961e2175b4d463dc8d90cf59b47b9c3","last_reissued_at":"2026-05-18T00:22:49.697843Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.697843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07653","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQVLwJmYpafTztNb8wEMfH9Dq8j9yHqgWurEgV4DLXuZGs03YjNqnP24Yv7XVmCRIX/KxI7yQ0hHY/2R3DwvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:49:10.191306Z"},"content_sha256":"05f411e494a900730ba8efa06476dbbaed4e62c8f697d888bb740864d2d100ff","schema_version":"1.0","event_id":"sha256:05f411e494a900730ba8efa06476dbbaed4e62c8f697d888bb740864d2d100ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:42HGPQPE7VXHUV72N5NVMP5IQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Efficient ConvNets using Redundant Feature Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Babajide O. Ayinde, Jacek M. Zurada","submitted_at":"2018-02-21T16:31:28Z","abstract_excerpt":"This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce a lot of redundant features that are either shifted version of one another or are very similar and show little or no variations; thus resulting in filtering redundancy. We propose to prune these redundant features along with their connecting feature maps according to their differentiation and based on their relative cosine distances in the feature space, thu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07653","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":"2026-05-18T00:22:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmbcX4fAvbKPWWuukfSX59bO++FEPqJaUAJq8AURah/haoZpENPIvt7kE6zrLNTq1yrVKjw0TiV5oVvXOtd9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:49:10.191659Z"},"content_sha256":"34728d69acc0a9c9edcdf3d58b7bafa0a3280d015930082ce683a5a706543257","schema_version":"1.0","event_id":"sha256:34728d69acc0a9c9edcdf3d58b7bafa0a3280d015930082ce683a5a706543257"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/42HGPQPE7VXHUV72N5NVMP5IQ6/bundle.json","state_url":"https://pith.science/pith/42HGPQPE7VXHUV72N5NVMP5IQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/42HGPQPE7VXHUV72N5NVMP5IQ6/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":"2026-06-26T16:49:10Z","links":{"resolver":"https://pith.science/pith/42HGPQPE7VXHUV72N5NVMP5IQ6","bundle":"https://pith.science/pith/42HGPQPE7VXHUV72N5NVMP5IQ6/bundle.json","state":"https://pith.science/pith/42HGPQPE7VXHUV72N5NVMP5IQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/42HGPQPE7VXHUV72N5NVMP5IQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:42HGPQPE7VXHUV72N5NVMP5IQ6","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":"6e9bc6ecd1d8bf5371f5c5db972b5bc13a6108742e9aea8560068db450bc3a47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T16:31:28Z","title_canon_sha256":"a592a1ef93daa1691b87023f041329bbc15c052a73104e2e8c31d7669f6cde81"},"schema_version":"1.0","source":{"id":"1802.07653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07653","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07653v1","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07653","created_at":"2026-05-18T00:22:49Z"},{"alias_kind":"pith_short_12","alias_value":"42HGPQPE7VXH","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"42HGPQPE7VXHUV72","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"42HGPQPE","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:34728d69acc0a9c9edcdf3d58b7bafa0a3280d015930082ce683a5a706543257","target":"graph","created_at":"2026-05-18T00:22:49Z","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":"This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce a lot of redundant features that are either shifted version of one another or are very similar and show little or no variations; thus resulting in filtering redundancy. We propose to prune these redundant features along with their connecting feature maps according to their differentiation and based on their relative cosine distances in the feature space, thu","authors_text":"Babajide O. Ayinde, Jacek M. Zurada","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T16:31:28Z","title":"Building Efficient ConvNets using Redundant Feature Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07653","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":"sha256:05f411e494a900730ba8efa06476dbbaed4e62c8f697d888bb740864d2d100ff","target":"record","created_at":"2026-05-18T00:22:49Z","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":"6e9bc6ecd1d8bf5371f5c5db972b5bc13a6108742e9aea8560068db450bc3a47","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-21T16:31:28Z","title_canon_sha256":"a592a1ef93daa1691b87023f041329bbc15c052a73104e2e8c31d7669f6cde81"},"schema_version":"1.0","source":{"id":"1802.07653","kind":"arxiv","version":1}},"canonical_sha256":"e68e67c1e4fd6e7a57fa6f5b563fa8879961e2175b4d463dc8d90cf59b47b9c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e68e67c1e4fd6e7a57fa6f5b563fa8879961e2175b4d463dc8d90cf59b47b9c3","first_computed_at":"2026-05-18T00:22:49.697843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:49.697843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4lDDg229NaeNPG2GzmuYRr34vba3dMdFpPKUFZQ9/IT5qlSkD0br8Q266HZllg9w0U2ksudB8FucqSaqag85Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:49.698244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05f411e494a900730ba8efa06476dbbaed4e62c8f697d888bb740864d2d100ff","sha256:34728d69acc0a9c9edcdf3d58b7bafa0a3280d015930082ce683a5a706543257"],"state_sha256":"15e4ddf718cece7f219cc74aad0556371197c67eea8d239add18c02a3af7046d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ct6X3vrvfeQiv4QmhUQHffceOBoM9uI5jpGBLcomJX0LWRiE7xpiiucHm57sLi5PB5Ct0opqGP0DwrkjeGxLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T16:49:10.193492Z","bundle_sha256":"f736018e0e05206654206259568c22ca0c56f9fb7f290a46b74892f6938d7bab"}}