{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ","short_pith_number":"pith:LQ6DQ6XQ","canonical_record":{"source":{"id":"1608.04337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-15T17:35:56Z","cross_cats_sorted":[],"title_canon_sha256":"fa044e0fe2a119f1b3e18f7e8d3a3862bccb493018dc29fa19c8e824b9ca26b8","abstract_canon_sha256":"a5ffeb1cedc2a3f04855c91f6e236e4cd78d892660f15d9c184169ac0e4eeed4"},"schema_version":"1.0"},"canonical_sha256":"5c3c387af02ac10d66b45db493e6f82e7b98d9e6f40c33214a2c41802f2b1edf","source":{"kind":"arxiv","id":"1608.04337","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04337","created_at":"2026-05-18T00:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04337v2","created_at":"2026-05-18T00:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04337","created_at":"2026-05-18T00:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"LQ6DQ6XQFLAQ","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LQ6DQ6XQFLAQ2ZVU","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LQ6DQ6XQ","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ","target":"record","payload":{"canonical_record":{"source":{"id":"1608.04337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-15T17:35:56Z","cross_cats_sorted":[],"title_canon_sha256":"fa044e0fe2a119f1b3e18f7e8d3a3862bccb493018dc29fa19c8e824b9ca26b8","abstract_canon_sha256":"a5ffeb1cedc2a3f04855c91f6e236e4cd78d892660f15d9c184169ac0e4eeed4"},"schema_version":"1.0"},"canonical_sha256":"5c3c387af02ac10d66b45db493e6f82e7b98d9e6f40c33214a2c41802f2b1edf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:15.126683Z","signature_b64":"kAHVvJaoAcLvTlTG6d688nnClr382gg0tvEDodkha3YHwX/XeKF91VOSNwzHeaIGwTu6JOYrpxqyjEBGuMKFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3c387af02ac10d66b45db493e6f82e7b98d9e6f40c33214a2c41802f2b1edf","last_reissued_at":"2026-05-18T00:52:15.126140Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:15.126140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.04337","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pRZj/g6mJKJcb9BNBy8WGLuHd3aoNU8T+giOQlc4ufhF3eP6sKzvkACtgnjCa1C7fWp3QohkED25aak8VCcyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:19:02.314795Z"},"content_sha256":"7f5af934ac290ec706ee6e8007932dac9c74baf41de0846f182e976c583ac697","schema_version":"1.0","event_id":"sha256:7f5af934ac290ec706ee6e8007932dac9c74baf41de0846f182e976c583ac697"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial \"Bottleneck\" Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Liu, Hassan Foroosh, Min Wang","submitted_at":"2016-08-15T17:35:56Z","abstract_excerpt":"Deep convolutional neural networks achieve remarkable visual recognition performance, at the cost of high computational complexity. In this paper, we have a new design of efficient convolutional layers based on three schemes. The 3D convolution operation in a convolutional layer can be considered as performing spatial convolution in each channel and linear projection across channels simultaneously. By unravelling them and arranging the spatial convolution sequentially, the proposed layer is composed of a single intra-channel convolution, of which the computation is negligible, and a linear cha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04337","kind":"arxiv","version":2},"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":"2026-05-18T00:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rDp3Uu35OgOU9GLKLmJw3muSbJZUE79mfW7HpyBG7O7XsgSmyVHZZQ1CzHSobJrqwiePRZE+5CT7zvfM5aXFDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T12:19:02.315559Z"},"content_sha256":"b56cddd564c72e93067c77085367a9f05e1aab74cf1f65dc96a79ad655ceb8be","schema_version":"1.0","event_id":"sha256:b56cddd564c72e93067c77085367a9f05e1aab74cf1f65dc96a79ad655ceb8be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ/bundle.json","state_url":"https://pith.science/pith/LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ/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":"2026-06-10T12:19:02Z","links":{"resolver":"https://pith.science/pith/LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ","bundle":"https://pith.science/pith/LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ/bundle.json","state":"https://pith.science/pith/LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:LQ6DQ6XQFLAQ2ZVULW2JHZXYFZ","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":"a5ffeb1cedc2a3f04855c91f6e236e4cd78d892660f15d9c184169ac0e4eeed4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-15T17:35:56Z","title_canon_sha256":"fa044e0fe2a119f1b3e18f7e8d3a3862bccb493018dc29fa19c8e824b9ca26b8"},"schema_version":"1.0","source":{"id":"1608.04337","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04337","created_at":"2026-05-18T00:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04337v2","created_at":"2026-05-18T00:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04337","created_at":"2026-05-18T00:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"LQ6DQ6XQFLAQ","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LQ6DQ6XQFLAQ2ZVU","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LQ6DQ6XQ","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:b56cddd564c72e93067c77085367a9f05e1aab74cf1f65dc96a79ad655ceb8be","target":"graph","created_at":"2026-05-18T00:52:15Z","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":"Deep convolutional neural networks achieve remarkable visual recognition performance, at the cost of high computational complexity. In this paper, we have a new design of efficient convolutional layers based on three schemes. The 3D convolution operation in a convolutional layer can be considered as performing spatial convolution in each channel and linear projection across channels simultaneously. By unravelling them and arranging the spatial convolution sequentially, the proposed layer is composed of a single intra-channel convolution, of which the computation is negligible, and a linear cha","authors_text":"Baoyuan Liu, Hassan Foroosh, Min Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-15T17:35:56Z","title":"Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial \"Bottleneck\" Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04337","kind":"arxiv","version":2},"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":"sha256:7f5af934ac290ec706ee6e8007932dac9c74baf41de0846f182e976c583ac697","target":"record","created_at":"2026-05-18T00:52:15Z","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":"a5ffeb1cedc2a3f04855c91f6e236e4cd78d892660f15d9c184169ac0e4eeed4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-15T17:35:56Z","title_canon_sha256":"fa044e0fe2a119f1b3e18f7e8d3a3862bccb493018dc29fa19c8e824b9ca26b8"},"schema_version":"1.0","source":{"id":"1608.04337","kind":"arxiv","version":2}},"canonical_sha256":"5c3c387af02ac10d66b45db493e6f82e7b98d9e6f40c33214a2c41802f2b1edf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c3c387af02ac10d66b45db493e6f82e7b98d9e6f40c33214a2c41802f2b1edf","first_computed_at":"2026-05-18T00:52:15.126140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:15.126140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kAHVvJaoAcLvTlTG6d688nnClr382gg0tvEDodkha3YHwX/XeKF91VOSNwzHeaIGwTu6JOYrpxqyjEBGuMKFCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:15.126683Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.04337","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f5af934ac290ec706ee6e8007932dac9c74baf41de0846f182e976c583ac697","sha256:b56cddd564c72e93067c77085367a9f05e1aab74cf1f65dc96a79ad655ceb8be"],"state_sha256":"59a92c13ba0cb80f304434e1bef2dc4771e0cd0b59b83ee9274bbc8701613038"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sl4B30xblwCxBueCWFnVtuc16hx+haF69rsOczXBa3FFzvJFvfjhMTB5fXxMjSz25NhgAmL0wv3aYBYu0zt9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T12:19:02.319467Z","bundle_sha256":"a59d96a59eaf63ede5d2110bea14833f4bcd4fcecfd573141636667d6fce1550"}}