{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UD2BHJ5OHNXZGCD4RYRXGALFJI","short_pith_number":"pith:UD2BHJ5O","canonical_record":{"source":{"id":"2307.00684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T23:34:12Z","cross_cats_sorted":[],"title_canon_sha256":"cce03bcdc1c537b34e0d43ff399235aacb1f2179ba5744c150921f6a53c3cba3","abstract_canon_sha256":"f409a922a06d5273291cbe7e32526f93a1fd44722483ebeacb6de36dd63fdcf2"},"schema_version":"1.0"},"canonical_sha256":"a0f413a7ae3b6f93087c8e237301654a3ed9257f89e57ef58c1034d66af0d5f5","source":{"kind":"arxiv","id":"2307.00684","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00684","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00684v2","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00684","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"UD2BHJ5OHNXZ","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"UD2BHJ5OHNXZGCD4","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"UD2BHJ5O","created_at":"2026-07-05T07:38:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UD2BHJ5OHNXZGCD4RYRXGALFJI","target":"record","payload":{"canonical_record":{"source":{"id":"2307.00684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T23:34:12Z","cross_cats_sorted":[],"title_canon_sha256":"cce03bcdc1c537b34e0d43ff399235aacb1f2179ba5744c150921f6a53c3cba3","abstract_canon_sha256":"f409a922a06d5273291cbe7e32526f93a1fd44722483ebeacb6de36dd63fdcf2"},"schema_version":"1.0"},"canonical_sha256":"a0f413a7ae3b6f93087c8e237301654a3ed9257f89e57ef58c1034d66af0d5f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:51.053047Z","signature_b64":"POlFY1HbkXmN4EjjyOx7s9EU/fTnPdveVpLMBiScGSGwiIoB6tyWUiaTSQOqNxNRnEHsKlv5dFviJ1Q1VM93BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f413a7ae3b6f93087c8e237301654a3ed9257f89e57ef58c1034d66af0d5f5","last_reissued_at":"2026-07-05T07:38:51.052579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:51.052579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.00684","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7lp7zRtc2SHaaEPcOt8WhgQmiuqXqudrx4dWn7IzgQh1QDhEO/gFQJKNKva8PpJtsU0dZVOaEx076lauGzDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T04:08:02.366778Z"},"content_sha256":"6097ee2a9eead0cf1eedcc4e96725e0bcc2799d8dc78ed6a1ce033bc37750a22","schema_version":"1.0","event_id":"sha256:6097ee2a9eead0cf1eedcc4e96725e0bcc2799d8dc78ed6a1ce033bc37750a22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UD2BHJ5OHNXZGCD4RYRXGALFJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Proximal Algorithm for Network Slimming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanghui Xue, Fredrick Park, Jack Xin, Kevin Bui, Yingyong Qi","submitted_at":"2023-07-02T23:34:12Z","abstract_excerpt":"As a popular channel pruning method for convolutional neural networks (CNNs), network slimming (NS) has a three-stage process: (1) it trains a CNN with $\\ell_1$ regularization applied to the scaling factors of the batch normalization layers; (2) it removes channels whose scaling factors are below a chosen threshold; and (3) it retrains the pruned model to recover the original accuracy. This time-consuming, three-step process is a result of using subgradient descent to train CNNs. Because subgradient descent does not exactly train CNNs towards sparse, accurate structures, the latter two steps a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00684","kind":"arxiv","version":2},"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/2307.00684/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":"2026-07-05T07:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a6N4bIWHG+0EY28TtJcDInfp9mKnkE/ZapfNBn4XhD+SO4zml3MNBiDH6XtO6rwWXpYiQC/K0W3+fg+eLiFXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T04:08:02.367159Z"},"content_sha256":"40ca08756d0fccaa42298a612471c9183723a6d421566b58008df801ab2eb5bb","schema_version":"1.0","event_id":"sha256:40ca08756d0fccaa42298a612471c9183723a6d421566b58008df801ab2eb5bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UD2BHJ5OHNXZGCD4RYRXGALFJI/bundle.json","state_url":"https://pith.science/pith/UD2BHJ5OHNXZGCD4RYRXGALFJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UD2BHJ5OHNXZGCD4RYRXGALFJI/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":"2026-07-13T04:08:02Z","links":{"resolver":"https://pith.science/pith/UD2BHJ5OHNXZGCD4RYRXGALFJI","bundle":"https://pith.science/pith/UD2BHJ5OHNXZGCD4RYRXGALFJI/bundle.json","state":"https://pith.science/pith/UD2BHJ5OHNXZGCD4RYRXGALFJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UD2BHJ5OHNXZGCD4RYRXGALFJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UD2BHJ5OHNXZGCD4RYRXGALFJI","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":"f409a922a06d5273291cbe7e32526f93a1fd44722483ebeacb6de36dd63fdcf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T23:34:12Z","title_canon_sha256":"cce03bcdc1c537b34e0d43ff399235aacb1f2179ba5744c150921f6a53c3cba3"},"schema_version":"1.0","source":{"id":"2307.00684","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00684","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00684v2","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00684","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"UD2BHJ5OHNXZ","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"UD2BHJ5OHNXZGCD4","created_at":"2026-07-05T07:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"UD2BHJ5O","created_at":"2026-07-05T07:38:51Z"}],"graph_snapshots":[{"event_id":"sha256:40ca08756d0fccaa42298a612471c9183723a6d421566b58008df801ab2eb5bb","target":"graph","created_at":"2026-07-05T07:38:51Z","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/2307.00684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As a popular channel pruning method for convolutional neural networks (CNNs), network slimming (NS) has a three-stage process: (1) it trains a CNN with $\\ell_1$ regularization applied to the scaling factors of the batch normalization layers; (2) it removes channels whose scaling factors are below a chosen threshold; and (3) it retrains the pruned model to recover the original accuracy. This time-consuming, three-step process is a result of using subgradient descent to train CNNs. Because subgradient descent does not exactly train CNNs towards sparse, accurate structures, the latter two steps a","authors_text":"Fanghui Xue, Fredrick Park, Jack Xin, Kevin Bui, Yingyong Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T23:34:12Z","title":"A Proximal Algorithm for Network Slimming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00684","kind":"arxiv","version":2},"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":"sha256:6097ee2a9eead0cf1eedcc4e96725e0bcc2799d8dc78ed6a1ce033bc37750a22","target":"record","created_at":"2026-07-05T07:38:51Z","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":"f409a922a06d5273291cbe7e32526f93a1fd44722483ebeacb6de36dd63fdcf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-02T23:34:12Z","title_canon_sha256":"cce03bcdc1c537b34e0d43ff399235aacb1f2179ba5744c150921f6a53c3cba3"},"schema_version":"1.0","source":{"id":"2307.00684","kind":"arxiv","version":2}},"canonical_sha256":"a0f413a7ae3b6f93087c8e237301654a3ed9257f89e57ef58c1034d66af0d5f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f413a7ae3b6f93087c8e237301654a3ed9257f89e57ef58c1034d66af0d5f5","first_computed_at":"2026-07-05T07:38:51.052579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:51.052579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"POlFY1HbkXmN4EjjyOx7s9EU/fTnPdveVpLMBiScGSGwiIoB6tyWUiaTSQOqNxNRnEHsKlv5dFviJ1Q1VM93BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:51.053047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00684","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6097ee2a9eead0cf1eedcc4e96725e0bcc2799d8dc78ed6a1ce033bc37750a22","sha256:40ca08756d0fccaa42298a612471c9183723a6d421566b58008df801ab2eb5bb"],"state_sha256":"6c66aa4fa6a634a021439688adf607fee439e6d9613c08718103973cff1e3272"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enadhgOjYQrQ+JdjdQrtQoo7V+f/JZnhnR1Rz4CWccrMJU3E3bXm4E3nGAC2r0YkzJG5K9bwHqIz2589g+iVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T04:08:02.369680Z","bundle_sha256":"a22ae88dc235eb3da12a1be08c64ed794d5922b4ccbb5585b0ad2551317667d1"}}