{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:O7AR2HQSWS6VWKPGZ33RX6HWYN","short_pith_number":"pith:O7AR2HQS","canonical_record":{"source":{"id":"1905.11664","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-28T08:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"f8435570136d2c32abbb1711377f766fc2134eff01cd6de3bb715e6bf613aa48","abstract_canon_sha256":"dbe0b25a4e34f3d51b61bff64851d7bb23de4d3cc36f4982e68e6534b00eebe4"},"schema_version":"1.0"},"canonical_sha256":"77c11d1e12b4bd5b29e6cef71bf8f6c3672396f725450d0051efb2be06a757ea","source":{"kind":"arxiv","id":"1905.11664","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11664","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11664v5","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11664","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"O7AR2HQSWS6V","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"O7AR2HQSWS6VWKPG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"O7AR2HQS","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:O7AR2HQSWS6VWKPGZ33RX6HWYN","target":"record","payload":{"canonical_record":{"source":{"id":"1905.11664","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-28T08:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"f8435570136d2c32abbb1711377f766fc2134eff01cd6de3bb715e6bf613aa48","abstract_canon_sha256":"dbe0b25a4e34f3d51b61bff64851d7bb23de4d3cc36f4982e68e6534b00eebe4"},"schema_version":"1.0"},"canonical_sha256":"77c11d1e12b4bd5b29e6cef71bf8f6c3672396f725450d0051efb2be06a757ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:52.962256Z","signature_b64":"p6zmZWM3j4NJKiYeLz5njZDIs8su/SB5JVbMd/JBC8aKSIthx+Pbug5M7E5O/J/bs+wofiXqZDoHgu5wLgx5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77c11d1e12b4bd5b29e6cef71bf8f6c3672396f725450d0051efb2be06a757ea","last_reissued_at":"2026-05-17T23:41:52.961666Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:52.961666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.11664","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IomZmvy/9W0zEoXHEC9duWHZEf4pg0TxjrxHXlsSN9pakM5prJWS6mcks17JE5FGvgbuKg9h3Qs73H46hoqLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:51:04.332144Z"},"content_sha256":"3d07ee6c8f6f325d9a84c46c0f8cbb8dafca2b3c4c04afba30ac47a4de1553b0","schema_version":"1.0","event_id":"sha256:3d07ee6c8f6f325d9a84c46c0f8cbb8dafca2b3c4c04afba30ac47a4de1553b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:O7AR2HQSWS6VWKPGZ33RX6HWYN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Ge, Haifeng Sun, Jiashi Li, Jingyu Wang, Qi Qi, Yujian Li, Zhangzhang Yue","submitted_at":"2019-05-28T08:09:04Z","abstract_excerpt":"Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage. However, these methods apply structured sparsity regularization on each layer separately where the correlations between consecutive layers are omitted. In this paper, we first combine one out-channel in current layer and the corresponding in-channel in next layer as a regularization group, namely out-in-channel. Our proposed Out-In-Ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11664","kind":"arxiv","version":5},"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":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/xW3LD1pq9djm01DKFcnMcVJQFgQTHQkspCm63zif41G3YLHbgLbn9q74InvGo2E4kMyPkwEjlqAQYy5S9SnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:51:04.332801Z"},"content_sha256":"59ea8a1da674bd5c0c78460ef14ede0e36309c191d28bfd418d0107e0bb7f3e3","schema_version":"1.0","event_id":"sha256:59ea8a1da674bd5c0c78460ef14ede0e36309c191d28bfd418d0107e0bb7f3e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7AR2HQSWS6VWKPGZ33RX6HWYN/bundle.json","state_url":"https://pith.science/pith/O7AR2HQSWS6VWKPGZ33RX6HWYN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7AR2HQSWS6VWKPGZ33RX6HWYN/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":"2026-05-30T16:51:04Z","links":{"resolver":"https://pith.science/pith/O7AR2HQSWS6VWKPGZ33RX6HWYN","bundle":"https://pith.science/pith/O7AR2HQSWS6VWKPGZ33RX6HWYN/bundle.json","state":"https://pith.science/pith/O7AR2HQSWS6VWKPGZ33RX6HWYN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7AR2HQSWS6VWKPGZ33RX6HWYN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:O7AR2HQSWS6VWKPGZ33RX6HWYN","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":"dbe0b25a4e34f3d51b61bff64851d7bb23de4d3cc36f4982e68e6534b00eebe4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-28T08:09:04Z","title_canon_sha256":"f8435570136d2c32abbb1711377f766fc2134eff01cd6de3bb715e6bf613aa48"},"schema_version":"1.0","source":{"id":"1905.11664","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11664","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11664v5","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11664","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"O7AR2HQSWS6V","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"O7AR2HQSWS6VWKPG","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"O7AR2HQS","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:59ea8a1da674bd5c0c78460ef14ede0e36309c191d28bfd418d0107e0bb7f3e3","target":"graph","created_at":"2026-05-17T23:41:52Z","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":"Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage. However, these methods apply structured sparsity regularization on each layer separately where the correlations between consecutive layers are omitted. In this paper, we first combine one out-channel in current layer and the corresponding in-channel in next layer as a regularization group, namely out-in-channel. Our proposed Out-In-Ch","authors_text":"Ce Ge, Haifeng Sun, Jiashi Li, Jingyu Wang, Qi Qi, Yujian Li, Zhangzhang Yue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-28T08:09:04Z","title":"OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11664","kind":"arxiv","version":5},"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":"sha256:3d07ee6c8f6f325d9a84c46c0f8cbb8dafca2b3c4c04afba30ac47a4de1553b0","target":"record","created_at":"2026-05-17T23:41:52Z","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":"dbe0b25a4e34f3d51b61bff64851d7bb23de4d3cc36f4982e68e6534b00eebe4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-28T08:09:04Z","title_canon_sha256":"f8435570136d2c32abbb1711377f766fc2134eff01cd6de3bb715e6bf613aa48"},"schema_version":"1.0","source":{"id":"1905.11664","kind":"arxiv","version":5}},"canonical_sha256":"77c11d1e12b4bd5b29e6cef71bf8f6c3672396f725450d0051efb2be06a757ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77c11d1e12b4bd5b29e6cef71bf8f6c3672396f725450d0051efb2be06a757ea","first_computed_at":"2026-05-17T23:41:52.961666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:52.961666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p6zmZWM3j4NJKiYeLz5njZDIs8su/SB5JVbMd/JBC8aKSIthx+Pbug5M7E5O/J/bs+wofiXqZDoHgu5wLgx5Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:52.962256Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11664","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d07ee6c8f6f325d9a84c46c0f8cbb8dafca2b3c4c04afba30ac47a4de1553b0","sha256:59ea8a1da674bd5c0c78460ef14ede0e36309c191d28bfd418d0107e0bb7f3e3"],"state_sha256":"d8b9131b1e26f8f47ba32e1b4a2b3124f26e9453bc0b7395456ba6fc7fc9dc96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2XyW05My6THEgiCxC4neSz8BfuWDh2xW7EMDm6rpTtKcjGLMZsEbVgPXXl/YqWe4fZ7n26oQlMwvcn4SL3aBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:51:04.335790Z","bundle_sha256":"b185e5d81d6cbc155108ed7c6d73a70f96a76b8980124b8f9cce5acd0223ed2a"}}