{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LOCWIAUIVJ6AUWTQNL77V33VGW","short_pith_number":"pith:LOCWIAUI","canonical_record":{"source":{"id":"2203.15794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T17:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"436e23a0ce52f399518733d90e82105556e683760134ca8ff68c52c00ea1974f","abstract_canon_sha256":"1ee50281d2aaeab99806d08695e0a4bff11acbe16bef08e11536082385eaeb98"},"schema_version":"1.0"},"canonical_sha256":"5b85640288aa7c0a5a706afffaef7535b084c64ae361bbeb227ebacaac10425d","source":{"kind":"arxiv","id":"2203.15794","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15794","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15794v1","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15794","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"LOCWIAUIVJ6A","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"LOCWIAUIVJ6AUWTQ","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"LOCWIAUI","created_at":"2026-07-05T04:09:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LOCWIAUIVJ6AUWTQNL77V33VGW","target":"record","payload":{"canonical_record":{"source":{"id":"2203.15794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T17:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"436e23a0ce52f399518733d90e82105556e683760134ca8ff68c52c00ea1974f","abstract_canon_sha256":"1ee50281d2aaeab99806d08695e0a4bff11acbe16bef08e11536082385eaeb98"},"schema_version":"1.0"},"canonical_sha256":"5b85640288aa7c0a5a706afffaef7535b084c64ae361bbeb227ebacaac10425d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:53.200006Z","signature_b64":"4qSGKAZbuXRTxJQmJOkiHqPiRa7xeHvrJlQMWvM1yfad70jyJrtpvIgr0DQokl4QDrzLmIrc+rksvCl7wHRFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b85640288aa7c0a5a706afffaef7535b084c64ae361bbeb227ebacaac10425d","last_reissued_at":"2026-07-05T04:09:53.199536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:53.199536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.15794","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":"2026-07-05T04:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZTIexYzNwAWWu+g5dRukn0Kw6ng3t2TxLkse9wQkyPjKWYL0P9nhgvst9r2hA+jq7rmiHy4gh+7sWphgtP/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:50:45.130873Z"},"content_sha256":"eb57aec4d95624080aee58d64cba8b8917cc03ace24abd27e2bccc26930ff29d","schema_version":"1.0","event_id":"sha256:eb57aec4d95624080aee58d64cba8b8917cc03ace24abd27e2bccc26930ff29d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LOCWIAUIVJ6AUWTQNL77V33VGW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHEX: CHannel EXploration for CNN Model Compression","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Sun, Kun Yuan, Minghai Qin, Rong Jin, Sun-Yuan Kung, Xiaolong Ma, Yen-Kuang Chen, Yi Xu, Yuan Xie, Zejiang Hou","submitted_at":"2022-03-29T17:52:41Z","abstract_excerpt":"Channel pruning has been broadly recognized as an effective technique to reduce the computation and memory cost of deep convolutional neural networks. However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model. Such limitations may lead to sub-optimal model quality as well as excessive memory and training cost. In this paper, we propose a novel Channel Exploration methodology, dubbed as CHEX, to rectify these problems. As opposed to pruning-only strategy, we propose to repeatedly prune and regrow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15794","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.15794/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oC/OJ6Y70w16Q1oCxt3BrE4ZFdgJGtZQmHhmsp1TF6hSHw0VSZL0DuduVD1hYO3V/r7agQaJJ5dGeg6AGlCiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:50:45.131450Z"},"content_sha256":"53523bac90a6ad843399baeda36f2f34e28fa3f444d5b51080381540ddb65ca5","schema_version":"1.0","event_id":"sha256:53523bac90a6ad843399baeda36f2f34e28fa3f444d5b51080381540ddb65ca5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOCWIAUIVJ6AUWTQNL77V33VGW/bundle.json","state_url":"https://pith.science/pith/LOCWIAUIVJ6AUWTQNL77V33VGW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOCWIAUIVJ6AUWTQNL77V33VGW/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":"2026-08-06T08:50:45Z","links":{"resolver":"https://pith.science/pith/LOCWIAUIVJ6AUWTQNL77V33VGW","bundle":"https://pith.science/pith/LOCWIAUIVJ6AUWTQNL77V33VGW/bundle.json","state":"https://pith.science/pith/LOCWIAUIVJ6AUWTQNL77V33VGW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOCWIAUIVJ6AUWTQNL77V33VGW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LOCWIAUIVJ6AUWTQNL77V33VGW","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":"1ee50281d2aaeab99806d08695e0a4bff11acbe16bef08e11536082385eaeb98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T17:52:41Z","title_canon_sha256":"436e23a0ce52f399518733d90e82105556e683760134ca8ff68c52c00ea1974f"},"schema_version":"1.0","source":{"id":"2203.15794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15794","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15794v1","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15794","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"LOCWIAUIVJ6A","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"LOCWIAUIVJ6AUWTQ","created_at":"2026-07-05T04:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"LOCWIAUI","created_at":"2026-07-05T04:09:53Z"}],"graph_snapshots":[{"event_id":"sha256:53523bac90a6ad843399baeda36f2f34e28fa3f444d5b51080381540ddb65ca5","target":"graph","created_at":"2026-07-05T04:09:53Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.15794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Channel pruning has been broadly recognized as an effective technique to reduce the computation and memory cost of deep convolutional neural networks. However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model. Such limitations may lead to sub-optimal model quality as well as excessive memory and training cost. In this paper, we propose a novel Channel Exploration methodology, dubbed as CHEX, to rectify these problems. As opposed to pruning-only strategy, we propose to repeatedly prune and regrow","authors_text":"Fei Sun, Kun Yuan, Minghai Qin, Rong Jin, Sun-Yuan Kung, Xiaolong Ma, Yen-Kuang Chen, Yi Xu, Yuan Xie, Zejiang Hou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T17:52:41Z","title":"CHEX: CHannel EXploration for CNN Model Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15794","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:eb57aec4d95624080aee58d64cba8b8917cc03ace24abd27e2bccc26930ff29d","target":"record","created_at":"2026-07-05T04:09:53Z","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":"1ee50281d2aaeab99806d08695e0a4bff11acbe16bef08e11536082385eaeb98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-29T17:52:41Z","title_canon_sha256":"436e23a0ce52f399518733d90e82105556e683760134ca8ff68c52c00ea1974f"},"schema_version":"1.0","source":{"id":"2203.15794","kind":"arxiv","version":1}},"canonical_sha256":"5b85640288aa7c0a5a706afffaef7535b084c64ae361bbeb227ebacaac10425d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b85640288aa7c0a5a706afffaef7535b084c64ae361bbeb227ebacaac10425d","first_computed_at":"2026-07-05T04:09:53.199536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:53.199536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4qSGKAZbuXRTxJQmJOkiHqPiRa7xeHvrJlQMWvM1yfad70jyJrtpvIgr0DQokl4QDrzLmIrc+rksvCl7wHRFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:53.200006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb57aec4d95624080aee58d64cba8b8917cc03ace24abd27e2bccc26930ff29d","sha256:53523bac90a6ad843399baeda36f2f34e28fa3f444d5b51080381540ddb65ca5"],"state_sha256":"44590126797bc042f24ae1aba6bc09c4e8e67e882bbf3ac3db122b4130d66645"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b3yhBGWNFno8mfSLcQn5qoll9VQpxZMG53IdLvrHsCvkl0kk+kK5OD3m+v8RtQS5JlbH8/4BAy41N6RVGVaACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:50:45.137033Z","bundle_sha256":"51fc8772446f8fda629fb7b02c4373b6dcf6ca942cbee5c379a08cba887a1148"}}