{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:45IN6M722FZ4UJUBAZBEAQMIVQ","short_pith_number":"pith:45IN6M72","canonical_record":{"source":{"id":"1810.11809","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-28T13:18:50Z","cross_cats_sorted":[],"title_canon_sha256":"3546cd1a4544028d5484b40b4428f750c9bef295874afe58099ea8e66ff0af13","abstract_canon_sha256":"6c438e9f0b677dd159d9c80b3bfd887a8371ea81f20f4fed6e918e1780572d8f"},"schema_version":"1.0"},"canonical_sha256":"e750df33fad173ca26810642404188ac3ea04d23de8b216fa95e456525db35be","source":{"kind":"arxiv","id":"1810.11809","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11809","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11809v3","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11809","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"45IN6M722FZ4","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"45IN6M722FZ4UJUB","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"45IN6M72","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:45IN6M722FZ4UJUBAZBEAQMIVQ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11809","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-28T13:18:50Z","cross_cats_sorted":[],"title_canon_sha256":"3546cd1a4544028d5484b40b4428f750c9bef295874afe58099ea8e66ff0af13","abstract_canon_sha256":"6c438e9f0b677dd159d9c80b3bfd887a8371ea81f20f4fed6e918e1780572d8f"},"schema_version":"1.0"},"canonical_sha256":"e750df33fad173ca26810642404188ac3ea04d23de8b216fa95e456525db35be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:29.278558Z","signature_b64":"oGDVhis8ebqDUSmvsBB8U1Z8gfbyx6V5aua0gZQkBgbbgS09klxSyWSotI4GlgJR3OLKGuYwW4s25HRjZRTQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e750df33fad173ca26810642404188ac3ea04d23de8b216fa95e456525db35be","last_reissued_at":"2026-05-17T23:56:29.278091Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:29.278091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11809","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mCEssv8LkocX45aw9zej33EJ5G97mdwv/N2QuUJn8wQuvfSuLrAEbfOLlCGKyDr6oFWtLzy+64CikQ+n5X8cBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:36:08.722904Z"},"content_sha256":"10d77015f953b983dcf6c83fd0868aa14d80ebaf89235c32a12def4289954965","schema_version":"1.0","event_id":"sha256:10d77015f953b983dcf6c83fd0868aa14d80ebaf89235c32a12def4289954965"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:45IN6M722FZ4UJUBAZBEAQMIVQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discrimination-aware Channel Pruning for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Jing Liu, Jinhui Zhu, Junzhou Huang, Mingkui Tan, Qingyao Wu, Yong Guo, Zhuangwei Zhuang","submitted_at":"2018-10-28T13:18:50Z","abstract_excerpt":"Channel pruning is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature maps and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, whilst the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. To overcome these drawbacks, we investigate a simple-yet-effective method, called discrimination-aware c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11809","kind":"arxiv","version":3},"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":"2026-05-17T23:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3OrqcJQvVncp4euAvrmfC6uRsUJLoWcIxDa+y6OIBo4FRNk0i+/vInHL3j0qot77huv0Ybz9jGTVTyKlzelcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:36:08.723245Z"},"content_sha256":"d47c7c55dafc68451e588f6ce7f5562815c98c11f3462798938901f064fd6af0","schema_version":"1.0","event_id":"sha256:d47c7c55dafc68451e588f6ce7f5562815c98c11f3462798938901f064fd6af0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/45IN6M722FZ4UJUBAZBEAQMIVQ/bundle.json","state_url":"https://pith.science/pith/45IN6M722FZ4UJUBAZBEAQMIVQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/45IN6M722FZ4UJUBAZBEAQMIVQ/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":"2026-06-01T23:36:08Z","links":{"resolver":"https://pith.science/pith/45IN6M722FZ4UJUBAZBEAQMIVQ","bundle":"https://pith.science/pith/45IN6M722FZ4UJUBAZBEAQMIVQ/bundle.json","state":"https://pith.science/pith/45IN6M722FZ4UJUBAZBEAQMIVQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/45IN6M722FZ4UJUBAZBEAQMIVQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:45IN6M722FZ4UJUBAZBEAQMIVQ","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":"6c438e9f0b677dd159d9c80b3bfd887a8371ea81f20f4fed6e918e1780572d8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-28T13:18:50Z","title_canon_sha256":"3546cd1a4544028d5484b40b4428f750c9bef295874afe58099ea8e66ff0af13"},"schema_version":"1.0","source":{"id":"1810.11809","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11809","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11809v3","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11809","created_at":"2026-05-17T23:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"45IN6M722FZ4","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"45IN6M722FZ4UJUB","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"45IN6M72","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:d47c7c55dafc68451e588f6ce7f5562815c98c11f3462798938901f064fd6af0","target":"graph","created_at":"2026-05-17T23:56:29Z","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 is one of the predominant approaches for deep model compression. Existing pruning methods either train from scratch with sparsity constraints on channels, or minimize the reconstruction error between the pre-trained feature maps and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, whilst the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. To overcome these drawbacks, we investigate a simple-yet-effective method, called discrimination-aware c","authors_text":"Bohan Zhuang, Jing Liu, Jinhui Zhu, Junzhou Huang, Mingkui Tan, Qingyao Wu, Yong Guo, Zhuangwei Zhuang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-28T13:18:50Z","title":"Discrimination-aware Channel Pruning for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11809","kind":"arxiv","version":3},"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":"sha256:10d77015f953b983dcf6c83fd0868aa14d80ebaf89235c32a12def4289954965","target":"record","created_at":"2026-05-17T23:56:29Z","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":"6c438e9f0b677dd159d9c80b3bfd887a8371ea81f20f4fed6e918e1780572d8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-28T13:18:50Z","title_canon_sha256":"3546cd1a4544028d5484b40b4428f750c9bef295874afe58099ea8e66ff0af13"},"schema_version":"1.0","source":{"id":"1810.11809","kind":"arxiv","version":3}},"canonical_sha256":"e750df33fad173ca26810642404188ac3ea04d23de8b216fa95e456525db35be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e750df33fad173ca26810642404188ac3ea04d23de8b216fa95e456525db35be","first_computed_at":"2026-05-17T23:56:29.278091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:29.278091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oGDVhis8ebqDUSmvsBB8U1Z8gfbyx6V5aua0gZQkBgbbgS09klxSyWSotI4GlgJR3OLKGuYwW4s25HRjZRTQDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:29.278558Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11809","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10d77015f953b983dcf6c83fd0868aa14d80ebaf89235c32a12def4289954965","sha256:d47c7c55dafc68451e588f6ce7f5562815c98c11f3462798938901f064fd6af0"],"state_sha256":"ae0feda33287aac4e1579f886e59ccd09f1c2038f7b41880549749dd3c8fe450"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6SmpBL1yHTEJ+3J57WTy52oTCKSsrBGCUfFlWcHz0pYg/jsOLq+NJ7t5kHSjopoWwEJgZ6HoAjGS2aUYwBJJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T23:36:08.725098Z","bundle_sha256":"f2721326ecfc9a521bce8f0886ae9b481cbfa1518ef843302c74fe24ddde84c4"}}