{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:6WWQJEBB2WY4MITTO37JPTAXXQ","short_pith_number":"pith:6WWQJEBB","canonical_record":{"source":{"id":"1901.08624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T19:45:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ceddcf42e50134f2a83ab038c167c45e09d9de257a246f7242db014e6aae1472","abstract_canon_sha256":"ab82871b0abecf521c8b472d699fc38da7e064cc2a2199e7478b87106fa9c556"},"schema_version":"1.0"},"canonical_sha256":"f5ad049021d5b1c6227376fe97cc17bc1f38ac5802d01d897b41e88fd18962aa","source":{"kind":"arxiv","id":"1901.08624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08624","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08624v1","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08624","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"6WWQJEBB2WY4","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6WWQJEBB2WY4MITT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6WWQJEBB","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:6WWQJEBB2WY4MITTO37JPTAXXQ","target":"record","payload":{"canonical_record":{"source":{"id":"1901.08624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T19:45:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ceddcf42e50134f2a83ab038c167c45e09d9de257a246f7242db014e6aae1472","abstract_canon_sha256":"ab82871b0abecf521c8b472d699fc38da7e064cc2a2199e7478b87106fa9c556"},"schema_version":"1.0"},"canonical_sha256":"f5ad049021d5b1c6227376fe97cc17bc1f38ac5802d01d897b41e88fd18962aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:33.568838Z","signature_b64":"/alh6vSFbsljnwUqkdrJPHKsF+hOaXJGWIt2ieTnPIEjVRRC71slNzmVOm6EEUQ06+4ioMqMCwLZ3JuiqhSCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5ad049021d5b1c6227376fe97cc17bc1f38ac5802d01d897b41e88fd18962aa","last_reissued_at":"2026-05-17T23:55:33.568424Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:33.568424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.08624","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":"2026-05-17T23:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+uamC/Dl90cjEy6lunS2nyYUUEX/pJc6yq1w4JCtY5JaZ/ACa32vsK5JK9aCxKU/CblnLjPkbkHGgtFUzaWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:31:00.918564Z"},"content_sha256":"a42ac7b394c2ba5dd90edcf08b9195736257dc571f2b5d0ccef6da4c03bc2e5b","schema_version":"1.0","event_id":"sha256:a42ac7b394c2ba5dd90edcf08b9195736257dc571f2b5d0ccef6da4c03bc2e5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:6WWQJEBB2WY4MITTO37JPTAXXQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jack Xin, Jiancheng Lyu, Shuai Zhang, Yingyong Qi","submitted_at":"2019-01-24T19:45:53Z","abstract_excerpt":"ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its basic operations include group, channel-wise convolution and channel shuffling. However, channel shuffling is manually designed empirically. Mathematically, shuffling is a multiplication by a permutation matrix. In this paper, we propose to automate channel shuffling by learning permutation matrices in network training. We introduce an exact Lipschitz continuous non-convex penalty so that it can be incorporated in the stochastic gradient descent to approximate permutation at high precision. Exact permu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08624","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":"2026-05-17T23:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CvJ/u1MnrGaHAlfsA3sdBwzfzhohHMuyh3V9/ddBpAduO97rBUxuNPIDIaXZWmbouDxVb221AbWLay4Ywa8ZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:31:00.918914Z"},"content_sha256":"5dc0382042bdcb31079feee62dda58825ca9ba796c322e8ea401147f89b92675","schema_version":"1.0","event_id":"sha256:5dc0382042bdcb31079feee62dda58825ca9ba796c322e8ea401147f89b92675"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WWQJEBB2WY4MITTO37JPTAXXQ/bundle.json","state_url":"https://pith.science/pith/6WWQJEBB2WY4MITTO37JPTAXXQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WWQJEBB2WY4MITTO37JPTAXXQ/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":"2026-05-28T10:31:00Z","links":{"resolver":"https://pith.science/pith/6WWQJEBB2WY4MITTO37JPTAXXQ","bundle":"https://pith.science/pith/6WWQJEBB2WY4MITTO37JPTAXXQ/bundle.json","state":"https://pith.science/pith/6WWQJEBB2WY4MITTO37JPTAXXQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WWQJEBB2WY4MITTO37JPTAXXQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6WWQJEBB2WY4MITTO37JPTAXXQ","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":"ab82871b0abecf521c8b472d699fc38da7e064cc2a2199e7478b87106fa9c556","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T19:45:53Z","title_canon_sha256":"ceddcf42e50134f2a83ab038c167c45e09d9de257a246f7242db014e6aae1472"},"schema_version":"1.0","source":{"id":"1901.08624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.08624","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1901.08624v1","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08624","created_at":"2026-05-17T23:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"6WWQJEBB2WY4","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"6WWQJEBB2WY4MITT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"6WWQJEBB","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:5dc0382042bdcb31079feee62dda58825ca9ba796c322e8ea401147f89b92675","target":"graph","created_at":"2026-05-17T23:55:33Z","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":"ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its basic operations include group, channel-wise convolution and channel shuffling. However, channel shuffling is manually designed empirically. Mathematically, shuffling is a multiplication by a permutation matrix. In this paper, we propose to automate channel shuffling by learning permutation matrices in network training. We introduce an exact Lipschitz continuous non-convex penalty so that it can be incorporated in the stochastic gradient descent to approximate permutation at high precision. Exact permu","authors_text":"Jack Xin, Jiancheng Lyu, Shuai Zhang, Yingyong Qi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T19:45:53Z","title":"AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08624","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:a42ac7b394c2ba5dd90edcf08b9195736257dc571f2b5d0ccef6da4c03bc2e5b","target":"record","created_at":"2026-05-17T23:55:33Z","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":"ab82871b0abecf521c8b472d699fc38da7e064cc2a2199e7478b87106fa9c556","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T19:45:53Z","title_canon_sha256":"ceddcf42e50134f2a83ab038c167c45e09d9de257a246f7242db014e6aae1472"},"schema_version":"1.0","source":{"id":"1901.08624","kind":"arxiv","version":1}},"canonical_sha256":"f5ad049021d5b1c6227376fe97cc17bc1f38ac5802d01d897b41e88fd18962aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5ad049021d5b1c6227376fe97cc17bc1f38ac5802d01d897b41e88fd18962aa","first_computed_at":"2026-05-17T23:55:33.568424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:33.568424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/alh6vSFbsljnwUqkdrJPHKsF+hOaXJGWIt2ieTnPIEjVRRC71slNzmVOm6EEUQ06+4ioMqMCwLZ3JuiqhSCAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:33.568838Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.08624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a42ac7b394c2ba5dd90edcf08b9195736257dc571f2b5d0ccef6da4c03bc2e5b","sha256:5dc0382042bdcb31079feee62dda58825ca9ba796c322e8ea401147f89b92675"],"state_sha256":"30f6d600e4f73417d05167e93ec4f1c04d7d1584348bab3c6240b7611919901e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+JCX/rdVf0VechNz4vwX0LgRtz7rrWGXTmrQu3IhksFaTzxT9W9oTOvyzBo6ArzmJefr48FXh0CM8c045ikPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T10:31:00.921031Z","bundle_sha256":"4fce1fe3981a40266439160b9ce903190e815e00bd59cb789ec31f983a5eedb3"}}