{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MCATZGAZ2MAUFRW7LPG7EAYUTS","short_pith_number":"pith:MCATZGAZ","canonical_record":{"source":{"id":"1802.00124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-01T01:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"39b4d16f8691d8f3245c7a8fa926499569915831ca312e76efef72b466fe20a6","abstract_canon_sha256":"8a6b52683a8423c566502c588d2b0071529754e7231be2d386c1364022032572"},"schema_version":"1.0"},"canonical_sha256":"60813c9819d30142c6df5bcdf203149ca06dd83d48c291f21ac39e7b847a7530","source":{"kind":"arxiv","id":"1802.00124","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00124","created_at":"2026-05-18T00:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00124v2","created_at":"2026-05-18T00:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00124","created_at":"2026-05-18T00:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"MCATZGAZ2MAU","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MCATZGAZ2MAUFRW7","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MCATZGAZ","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MCATZGAZ2MAUFRW7LPG7EAYUTS","target":"record","payload":{"canonical_record":{"source":{"id":"1802.00124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-01T01:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"39b4d16f8691d8f3245c7a8fa926499569915831ca312e76efef72b466fe20a6","abstract_canon_sha256":"8a6b52683a8423c566502c588d2b0071529754e7231be2d386c1364022032572"},"schema_version":"1.0"},"canonical_sha256":"60813c9819d30142c6df5bcdf203149ca06dd83d48c291f21ac39e7b847a7530","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:28.229490Z","signature_b64":"pzwTyd5Zi+gf9ONULMrImNHajDKA6ba6FtDSlxlbZLw5FPgzUM38g0pFURS/RUnhZ+YNiNPwRiaAqfSu50NPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60813c9819d30142c6df5bcdf203149ca06dd83d48c291f21ac39e7b847a7530","last_reissued_at":"2026-05-18T00:24:28.228821Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:28.228821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.00124","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":"2026-05-18T00:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"irQip3VnXrxn8vzcR7eSXhJ/xMFYxtPGMMHx+DuD7496K03+M1Ldb+tIoH/4kntfcLxiFrROU2XVOGIUQ+EGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:43:03.155308Z"},"content_sha256":"3d403d865b5008041c0e1176ef6a5ccf5fe5c5be4cc2118e32c0aa6a6904f374","schema_version":"1.0","event_id":"sha256:3d403d865b5008041c0e1176ef6a5ccf5fe5c5be4cc2118e32c0aa6a6904f374"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MCATZGAZ2MAUFRW7LPG7EAYUTS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James Z. Wang, Jianbo Ye, Xin Lu, Zhe Lin","submitted_at":"2018-02-01T01:58:22Z","abstract_excerpt":"Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a smaller-norm parameter or feature plays a less informative role at the inference time. In this paper, we propose a channel pruning technique for accelerating the computations of deep convolutional neural networks (CNNs) that does not critically rely on this assumption. Instead, it focuses on direct simplification of the channel-to-channel computation graph of a CNN wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00124","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":""},"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":"2026-05-18T00:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tr4Q/EnuRWZet7VrcseQPvWNAL8C9cKyO634eyfyWBhtLqt0sONreYs3htL4zOvZqBNCPQR+0+m8lIjXo18KDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:43:03.155966Z"},"content_sha256":"8bfbab3d4503fd2cec0efa806bf465941bf99ee923d9c93689112df46e6c2034","schema_version":"1.0","event_id":"sha256:8bfbab3d4503fd2cec0efa806bf465941bf99ee923d9c93689112df46e6c2034"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCATZGAZ2MAUFRW7LPG7EAYUTS/bundle.json","state_url":"https://pith.science/pith/MCATZGAZ2MAUFRW7LPG7EAYUTS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCATZGAZ2MAUFRW7LPG7EAYUTS/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":"2026-06-04T01:43:03Z","links":{"resolver":"https://pith.science/pith/MCATZGAZ2MAUFRW7LPG7EAYUTS","bundle":"https://pith.science/pith/MCATZGAZ2MAUFRW7LPG7EAYUTS/bundle.json","state":"https://pith.science/pith/MCATZGAZ2MAUFRW7LPG7EAYUTS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCATZGAZ2MAUFRW7LPG7EAYUTS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MCATZGAZ2MAUFRW7LPG7EAYUTS","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":"8a6b52683a8423c566502c588d2b0071529754e7231be2d386c1364022032572","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-01T01:58:22Z","title_canon_sha256":"39b4d16f8691d8f3245c7a8fa926499569915831ca312e76efef72b466fe20a6"},"schema_version":"1.0","source":{"id":"1802.00124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.00124","created_at":"2026-05-18T00:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"1802.00124v2","created_at":"2026-05-18T00:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00124","created_at":"2026-05-18T00:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"MCATZGAZ2MAU","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MCATZGAZ2MAUFRW7","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MCATZGAZ","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:8bfbab3d4503fd2cec0efa806bf465941bf99ee923d9c93689112df46e6c2034","target":"graph","created_at":"2026-05-18T00:24:28Z","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":"Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a smaller-norm parameter or feature plays a less informative role at the inference time. In this paper, we propose a channel pruning technique for accelerating the computations of deep convolutional neural networks (CNNs) that does not critically rely on this assumption. Instead, it focuses on direct simplification of the channel-to-channel computation graph of a CNN wi","authors_text":"James Z. Wang, Jianbo Ye, Xin Lu, Zhe Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-01T01:58:22Z","title":"Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00124","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":"sha256:3d403d865b5008041c0e1176ef6a5ccf5fe5c5be4cc2118e32c0aa6a6904f374","target":"record","created_at":"2026-05-18T00:24:28Z","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":"8a6b52683a8423c566502c588d2b0071529754e7231be2d386c1364022032572","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-01T01:58:22Z","title_canon_sha256":"39b4d16f8691d8f3245c7a8fa926499569915831ca312e76efef72b466fe20a6"},"schema_version":"1.0","source":{"id":"1802.00124","kind":"arxiv","version":2}},"canonical_sha256":"60813c9819d30142c6df5bcdf203149ca06dd83d48c291f21ac39e7b847a7530","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60813c9819d30142c6df5bcdf203149ca06dd83d48c291f21ac39e7b847a7530","first_computed_at":"2026-05-18T00:24:28.228821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:24:28.228821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pzwTyd5Zi+gf9ONULMrImNHajDKA6ba6FtDSlxlbZLw5FPgzUM38g0pFURS/RUnhZ+YNiNPwRiaAqfSu50NPCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:24:28.229490Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.00124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d403d865b5008041c0e1176ef6a5ccf5fe5c5be4cc2118e32c0aa6a6904f374","sha256:8bfbab3d4503fd2cec0efa806bf465941bf99ee923d9c93689112df46e6c2034"],"state_sha256":"c71bc02c5fbcc5eac89506cda711bba0ad0d8dce733725c6d4fd3addc1566d3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCgJ5VXP0htW7X+8w2Mdc9/yrDqWIfseaC5IOtfvmIVj6G0bv7CCKMpvUNScGcmA6DfvqWwXudyfYLcduZ0yBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T01:43:03.160850Z","bundle_sha256":"7c92d5f503923c4a4ef83d0dc56d70a044fcb44382765ba14f12dbd67a0da7ed"}}