{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PYCKPRA5OLSUAMI72W6IU24TVJ","short_pith_number":"pith:PYCKPRA5","canonical_record":{"source":{"id":"1803.09926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T07:06:54Z","cross_cats_sorted":[],"title_canon_sha256":"0e43ed3dee8471879b16bfe440b41fe5c570b1d4ce51cb7ee154ef34e2e9f1bb","abstract_canon_sha256":"8b060b76a25c66babab4016c755e263ef4b835ff175fcd8ef0a3b5fddb0cf799"},"schema_version":"1.0"},"canonical_sha256":"7e04a7c41d72e540311fd5bc8a6b93aa40ac6b4ae69692bcbcdd5dab3c2762bf","source":{"kind":"arxiv","id":"1803.09926","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09926","created_at":"2026-05-18T00:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09926v1","created_at":"2026-05-18T00:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09926","created_at":"2026-05-18T00:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"PYCKPRA5OLSU","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PYCKPRA5OLSUAMI7","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PYCKPRA5","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PYCKPRA5OLSUAMI72W6IU24TVJ","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T07:06:54Z","cross_cats_sorted":[],"title_canon_sha256":"0e43ed3dee8471879b16bfe440b41fe5c570b1d4ce51cb7ee154ef34e2e9f1bb","abstract_canon_sha256":"8b060b76a25c66babab4016c755e263ef4b835ff175fcd8ef0a3b5fddb0cf799"},"schema_version":"1.0"},"canonical_sha256":"7e04a7c41d72e540311fd5bc8a6b93aa40ac6b4ae69692bcbcdd5dab3c2762bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:01.045435Z","signature_b64":"br8hSSRqzyDkJT4aQ4jxJxoWS5ky78dD/lSmfL7h82Q3+RZp75TBxKJBQJYhQrJzoJo8jfzDf9M+acrr8PuyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e04a7c41d72e540311fd5bc8a6b93aa40ac6b4ae69692bcbcdd5dab3c2762bf","last_reissued_at":"2026-05-18T00:20:01.044872Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:01.044872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09926","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":"2026-05-18T00:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WCOCotRshR2xbkWS9AqmrPTRDCFNnVUl2ivhGOK4TN8OQG8h1VpIuJ6ogdU66xA3cdUMgdqhsTPGZgL4sCajAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:53:53.932129Z"},"content_sha256":"c81efcad74564285cbe5e35507d5b925b96a99ae31b6ba35e3ac87d031851c96","schema_version":"1.0","event_id":"sha256:c81efcad74564285cbe5e35507d5b925b96a99ae31b6ba35e3ac87d031851c96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PYCKPRA5OLSUAMI72W6IU24TVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongsheng Li, Yiming Zhang, Yuxing Peng, Zhaoning Zhang, Zheng Qin","submitted_at":"2018-03-27T07:06:54Z","abstract_excerpt":"Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds. However, training depthwise convolution layers with GPUs is slow in current deep learning frameworks because their implementations cannot fully utilize the GPU capacity. To address this problem, in this paper we present an efficient method (called diagonalwise refactorization) for accelerating the training of depthwise convolution layers. Our key idea is to rearrange the weight vectors of a depthwise convolution into a large diagonal weight matrix so as to convert the depthw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09926","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":"2026-05-18T00:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iSi5uKXzTEAfdtnk9J6iutSIx/4JUvamULM+Xcevbp7a0uqVCr0FhOr6cAxsBY3s3fVbRJcFDsilEimGAVzJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:53:53.932493Z"},"content_sha256":"c00bc9ffc845c9895d7bc9036e9b21e8c205341d89f1626a70cf97030b0eaa41","schema_version":"1.0","event_id":"sha256:c00bc9ffc845c9895d7bc9036e9b21e8c205341d89f1626a70cf97030b0eaa41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYCKPRA5OLSUAMI72W6IU24TVJ/bundle.json","state_url":"https://pith.science/pith/PYCKPRA5OLSUAMI72W6IU24TVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYCKPRA5OLSUAMI72W6IU24TVJ/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":"2026-05-30T07:53:53Z","links":{"resolver":"https://pith.science/pith/PYCKPRA5OLSUAMI72W6IU24TVJ","bundle":"https://pith.science/pith/PYCKPRA5OLSUAMI72W6IU24TVJ/bundle.json","state":"https://pith.science/pith/PYCKPRA5OLSUAMI72W6IU24TVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYCKPRA5OLSUAMI72W6IU24TVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PYCKPRA5OLSUAMI72W6IU24TVJ","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":"8b060b76a25c66babab4016c755e263ef4b835ff175fcd8ef0a3b5fddb0cf799","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T07:06:54Z","title_canon_sha256":"0e43ed3dee8471879b16bfe440b41fe5c570b1d4ce51cb7ee154ef34e2e9f1bb"},"schema_version":"1.0","source":{"id":"1803.09926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09926","created_at":"2026-05-18T00:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09926v1","created_at":"2026-05-18T00:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09926","created_at":"2026-05-18T00:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"PYCKPRA5OLSU","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PYCKPRA5OLSUAMI7","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PYCKPRA5","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:c00bc9ffc845c9895d7bc9036e9b21e8c205341d89f1626a70cf97030b0eaa41","target":"graph","created_at":"2026-05-18T00:20:01Z","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":"Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds. However, training depthwise convolution layers with GPUs is slow in current deep learning frameworks because their implementations cannot fully utilize the GPU capacity. To address this problem, in this paper we present an efficient method (called diagonalwise refactorization) for accelerating the training of depthwise convolution layers. Our key idea is to rearrange the weight vectors of a depthwise convolution into a large diagonal weight matrix so as to convert the depthw","authors_text":"Dongsheng Li, Yiming Zhang, Yuxing Peng, Zhaoning Zhang, Zheng Qin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T07:06:54Z","title":"Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09926","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:c81efcad74564285cbe5e35507d5b925b96a99ae31b6ba35e3ac87d031851c96","target":"record","created_at":"2026-05-18T00:20:01Z","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":"8b060b76a25c66babab4016c755e263ef4b835ff175fcd8ef0a3b5fddb0cf799","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-27T07:06:54Z","title_canon_sha256":"0e43ed3dee8471879b16bfe440b41fe5c570b1d4ce51cb7ee154ef34e2e9f1bb"},"schema_version":"1.0","source":{"id":"1803.09926","kind":"arxiv","version":1}},"canonical_sha256":"7e04a7c41d72e540311fd5bc8a6b93aa40ac6b4ae69692bcbcdd5dab3c2762bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e04a7c41d72e540311fd5bc8a6b93aa40ac6b4ae69692bcbcdd5dab3c2762bf","first_computed_at":"2026-05-18T00:20:01.044872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:01.044872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"br8hSSRqzyDkJT4aQ4jxJxoWS5ky78dD/lSmfL7h82Q3+RZp75TBxKJBQJYhQrJzoJo8jfzDf9M+acrr8PuyDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:01.045435Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c81efcad74564285cbe5e35507d5b925b96a99ae31b6ba35e3ac87d031851c96","sha256:c00bc9ffc845c9895d7bc9036e9b21e8c205341d89f1626a70cf97030b0eaa41"],"state_sha256":"2729b44b66dc785f1f5333c54749c76f0c8c101a2237d35efdcba5cd267abb6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RpHwdrrn6Hc26C1A0UQSA61R6AmzAbB1FLQIT9rD3l7iUXEhTU1b9bdzR9rErHwgCxnk/7PT4HDRYc5fcYwIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:53:53.934475Z","bundle_sha256":"6de33ff12aed028f64dd9110d509707c95e67a9b22b350cfda653dc65e10c75b"}}