{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:FL77XHB7WZNXAYYX4R6TX3J2ZP","short_pith_number":"pith:FL77XHB7","canonical_record":{"source":{"id":"1405.3866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-05-15T14:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"0608e55cf1ea5afe1bfd6637d686327b0bdf12ffeb87789baa39368d721b6ebf","abstract_canon_sha256":"0b2ef8198dca78be92b225942dc5cf327905cbba1d3cbf7d51b8892f576c045c"},"schema_version":"1.0"},"canonical_sha256":"2afffb9c3fb65b706317e47d3bed3acbf412c85daec30ff7376610d1f67b08b4","source":{"kind":"arxiv","id":"1405.3866","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.3866","created_at":"2026-05-18T02:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"1405.3866v1","created_at":"2026-05-18T02:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.3866","created_at":"2026-05-18T02:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"FL77XHB7WZNX","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FL77XHB7WZNXAYYX","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FL77XHB7","created_at":"2026-05-18T12:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:FL77XHB7WZNXAYYX4R6TX3J2ZP","target":"record","payload":{"canonical_record":{"source":{"id":"1405.3866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-05-15T14:41:06Z","cross_cats_sorted":[],"title_canon_sha256":"0608e55cf1ea5afe1bfd6637d686327b0bdf12ffeb87789baa39368d721b6ebf","abstract_canon_sha256":"0b2ef8198dca78be92b225942dc5cf327905cbba1d3cbf7d51b8892f576c045c"},"schema_version":"1.0"},"canonical_sha256":"2afffb9c3fb65b706317e47d3bed3acbf412c85daec30ff7376610d1f67b08b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:51:49.138079Z","signature_b64":"y9s2pj061Vzh2KwAFI+sb6lyO4Zme6y+0rLZeZ5z/8eZN38ITQ3mkR5K4Y8CyNdbx4V3+cNJ+SkYKnLDyE4yAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2afffb9c3fb65b706317e47d3bed3acbf412c85daec30ff7376610d1f67b08b4","last_reissued_at":"2026-05-18T02:51:49.137640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:51:49.137640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1405.3866","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":"2026-05-18T02:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DzNpxoN2Dct7dLvbUDoTDWc8if6ssFHazYEQbHWfc0il5VPOaukX7KPwFogcsAGGul7CAswsF0kF+g7+rlIRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:54:43.694883Z"},"content_sha256":"53ed380e74812fe4bcf451557810f0d3bf808e1e539591f6797a0238ceeb75a2","schema_version":"1.0","event_id":"sha256:53ed380e74812fe4bcf451557810f0d3bf808e1e539591f6797a0238ceeb75a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:FL77XHB7WZNXAYYX4R6TX3J2ZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Max Jaderberg","submitted_at":"2014-05-15T14:41:06Z","abstract_excerpt":"The focus of this paper is speeding up the evaluation of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume the bulk of the processing time, and so in this work we present two simple schemes for drastically speeding up these layers. This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain. Our methods are architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.3866","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":"2026-05-18T02:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GXEUW6QjsZMGbC/y60iarwU2CVISBgn10TUefJYFPO9TcE1SxMpvPa2ukPDQMKFwT9vJp7rIHEOoQZAq94E0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T14:54:43.695234Z"},"content_sha256":"bee27efae11157022111939a09d97533dce123cf399a7b3049e154bc5345af60","schema_version":"1.0","event_id":"sha256:bee27efae11157022111939a09d97533dce123cf399a7b3049e154bc5345af60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FL77XHB7WZNXAYYX4R6TX3J2ZP/bundle.json","state_url":"https://pith.science/pith/FL77XHB7WZNXAYYX4R6TX3J2ZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FL77XHB7WZNXAYYX4R6TX3J2ZP/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":"2026-05-21T14:54:43Z","links":{"resolver":"https://pith.science/pith/FL77XHB7WZNXAYYX4R6TX3J2ZP","bundle":"https://pith.science/pith/FL77XHB7WZNXAYYX4R6TX3J2ZP/bundle.json","state":"https://pith.science/pith/FL77XHB7WZNXAYYX4R6TX3J2ZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FL77XHB7WZNXAYYX4R6TX3J2ZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:FL77XHB7WZNXAYYX4R6TX3J2ZP","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":"0b2ef8198dca78be92b225942dc5cf327905cbba1d3cbf7d51b8892f576c045c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-05-15T14:41:06Z","title_canon_sha256":"0608e55cf1ea5afe1bfd6637d686327b0bdf12ffeb87789baa39368d721b6ebf"},"schema_version":"1.0","source":{"id":"1405.3866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.3866","created_at":"2026-05-18T02:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"1405.3866v1","created_at":"2026-05-18T02:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.3866","created_at":"2026-05-18T02:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"FL77XHB7WZNX","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"FL77XHB7WZNXAYYX","created_at":"2026-05-18T12:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"FL77XHB7","created_at":"2026-05-18T12:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:bee27efae11157022111939a09d97533dce123cf399a7b3049e154bc5345af60","target":"graph","created_at":"2026-05-18T02:51:49Z","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":"The focus of this paper is speeding up the evaluation of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume the bulk of the processing time, and so in this work we present two simple schemes for drastically speeding up these layers. This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain. Our methods are architecture","authors_text":"Andrea Vedaldi, Andrew Zisserman, Max Jaderberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-05-15T14:41:06Z","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.3866","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":"sha256:53ed380e74812fe4bcf451557810f0d3bf808e1e539591f6797a0238ceeb75a2","target":"record","created_at":"2026-05-18T02:51:49Z","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":"0b2ef8198dca78be92b225942dc5cf327905cbba1d3cbf7d51b8892f576c045c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-05-15T14:41:06Z","title_canon_sha256":"0608e55cf1ea5afe1bfd6637d686327b0bdf12ffeb87789baa39368d721b6ebf"},"schema_version":"1.0","source":{"id":"1405.3866","kind":"arxiv","version":1}},"canonical_sha256":"2afffb9c3fb65b706317e47d3bed3acbf412c85daec30ff7376610d1f67b08b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2afffb9c3fb65b706317e47d3bed3acbf412c85daec30ff7376610d1f67b08b4","first_computed_at":"2026-05-18T02:51:49.137640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:51:49.137640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y9s2pj061Vzh2KwAFI+sb6lyO4Zme6y+0rLZeZ5z/8eZN38ITQ3mkR5K4Y8CyNdbx4V3+cNJ+SkYKnLDyE4yAw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:51:49.138079Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.3866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53ed380e74812fe4bcf451557810f0d3bf808e1e539591f6797a0238ceeb75a2","sha256:bee27efae11157022111939a09d97533dce123cf399a7b3049e154bc5345af60"],"state_sha256":"b32b5d93851f7c1d17f70664ac561ed0f81b20a3807691034ea23fb3827144ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVHDCYcNMCPsEIVoeYefsKifUdBP5YTllNYgTp65u7OebmbHJ8eGGH1vWm/dyuKQFFhOdMMQ6+QoNCRv0IVFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T14:54:43.697407Z","bundle_sha256":"c207bf51a85428820f88eef68cd83f54df74fdf9619b72cff0364ac4d9d8da74"}}