{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RJP6CA5BQGQRXWLFC5W7IFA4BY","short_pith_number":"pith:RJP6CA5B","canonical_record":{"source":{"id":"1811.00250","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-01T06:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"8bdb6ff75116a700b47c391e000d340ba9f922f437dc0758f16de8845ecdd702","abstract_canon_sha256":"b9a1f82e91936c3835f9680de52edb0d02f394315e0cbf8727576f7240227e91"},"schema_version":"1.0"},"canonical_sha256":"8a5fe103a181a11bd965176df4141c0e012206ff0d1c8d6a7dc9f331d060fd5f","source":{"kind":"arxiv","id":"1811.00250","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00250","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00250v3","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00250","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"RJP6CA5BQGQR","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RJP6CA5BQGQRXWLF","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RJP6CA5B","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RJP6CA5BQGQRXWLFC5W7IFA4BY","target":"record","payload":{"canonical_record":{"source":{"id":"1811.00250","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-01T06:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"8bdb6ff75116a700b47c391e000d340ba9f922f437dc0758f16de8845ecdd702","abstract_canon_sha256":"b9a1f82e91936c3835f9680de52edb0d02f394315e0cbf8727576f7240227e91"},"schema_version":"1.0"},"canonical_sha256":"8a5fe103a181a11bd965176df4141c0e012206ff0d1c8d6a7dc9f331d060fd5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:41.453276Z","signature_b64":"zk3mvYYSbQ3SodeJYXepIKXep78+At9D+2zqZqXTjhWdYcZobWhsCkiYDhXbwouBBD71l4ZAr2Aj3sqtB9u6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a5fe103a181a11bd965176df4141c0e012206ff0d1c8d6a7dc9f331d060fd5f","last_reissued_at":"2026-05-17T23:40:41.452691Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:41.452691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.00250","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":"2026-05-17T23:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pbFF1Tg7QHO0IRucGX9zMhKB3fZh8gfhFm1L2LvLcFjz85AKluWWyE+9EIafizZEDXP+OdHSR23zittr5r6BCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T04:25:25.773965Z"},"content_sha256":"2b9154ad8d3c0801c92b650a8febee10af73188996aaaa30b47abc69d82d5caf","schema_version":"1.0","event_id":"sha256:2b9154ad8d3c0801c92b650a8febee10af73188996aaaa30b47abc69d82d5caf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RJP6CA5BQGQRXWLFC5W7IFA4BY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ping Liu, Yang He, Yi Yang, Zhilan Hu, Ziwei Wang","submitted_at":"2018-11-01T06:03:05Z","abstract_excerpt":"Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small. To solve this problem, we propose a novel filter pruning method, namely Filter Pruning via Geometric Median (FPGM), to compress the model regardless of those two requirements. Unlike previous methods, FPGM c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00250","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":"2026-05-17T23:40:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8z/YcrtOYXiaAKASCA2V0QL6MF3KonRkY1MfwN07E2utT5zOkYcZYgV8Q34R5vN/YyK25qRw5qnygBm/XuiFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T04:25:25.774653Z"},"content_sha256":"38d8688d0cc726fd0578b4be53ab50c73add080729664f5bce9da3d11564fac5","schema_version":"1.0","event_id":"sha256:38d8688d0cc726fd0578b4be53ab50c73add080729664f5bce9da3d11564fac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJP6CA5BQGQRXWLFC5W7IFA4BY/bundle.json","state_url":"https://pith.science/pith/RJP6CA5BQGQRXWLFC5W7IFA4BY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJP6CA5BQGQRXWLFC5W7IFA4BY/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":"2026-05-25T04:25:25Z","links":{"resolver":"https://pith.science/pith/RJP6CA5BQGQRXWLFC5W7IFA4BY","bundle":"https://pith.science/pith/RJP6CA5BQGQRXWLFC5W7IFA4BY/bundle.json","state":"https://pith.science/pith/RJP6CA5BQGQRXWLFC5W7IFA4BY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJP6CA5BQGQRXWLFC5W7IFA4BY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RJP6CA5BQGQRXWLFC5W7IFA4BY","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":"b9a1f82e91936c3835f9680de52edb0d02f394315e0cbf8727576f7240227e91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-01T06:03:05Z","title_canon_sha256":"8bdb6ff75116a700b47c391e000d340ba9f922f437dc0758f16de8845ecdd702"},"schema_version":"1.0","source":{"id":"1811.00250","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00250","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00250v3","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00250","created_at":"2026-05-17T23:40:41Z"},{"alias_kind":"pith_short_12","alias_value":"RJP6CA5BQGQR","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RJP6CA5BQGQRXWLF","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RJP6CA5B","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:38d8688d0cc726fd0578b4be53ab50c73add080729664f5bce9da3d11564fac5","target":"graph","created_at":"2026-05-17T23:40:41Z","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":"Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small. To solve this problem, we propose a novel filter pruning method, namely Filter Pruning via Geometric Median (FPGM), to compress the model regardless of those two requirements. Unlike previous methods, FPGM c","authors_text":"Ping Liu, Yang He, Yi Yang, Zhilan Hu, Ziwei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-01T06:03:05Z","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00250","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":"sha256:2b9154ad8d3c0801c92b650a8febee10af73188996aaaa30b47abc69d82d5caf","target":"record","created_at":"2026-05-17T23:40:41Z","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":"b9a1f82e91936c3835f9680de52edb0d02f394315e0cbf8727576f7240227e91","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-01T06:03:05Z","title_canon_sha256":"8bdb6ff75116a700b47c391e000d340ba9f922f437dc0758f16de8845ecdd702"},"schema_version":"1.0","source":{"id":"1811.00250","kind":"arxiv","version":3}},"canonical_sha256":"8a5fe103a181a11bd965176df4141c0e012206ff0d1c8d6a7dc9f331d060fd5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a5fe103a181a11bd965176df4141c0e012206ff0d1c8d6a7dc9f331d060fd5f","first_computed_at":"2026-05-17T23:40:41.452691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:41.452691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zk3mvYYSbQ3SodeJYXepIKXep78+At9D+2zqZqXTjhWdYcZobWhsCkiYDhXbwouBBD71l4ZAr2Aj3sqtB9u6CA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:41.453276Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00250","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b9154ad8d3c0801c92b650a8febee10af73188996aaaa30b47abc69d82d5caf","sha256:38d8688d0cc726fd0578b4be53ab50c73add080729664f5bce9da3d11564fac5"],"state_sha256":"23a260b2ed692c14ae6513a7039997fa672021ff5b9bdea64fdd0022cd480298"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+W2+VWNG6SuQciQz+mGgb3RNFanMk3ORx3rJHS7iOYQDAhISlER7gFywrQUCIna8sVCM2DdExeydwd+CerYrCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T04:25:25.778469Z","bundle_sha256":"a1fb19891396a5d5f33967d76fa18dd1ea9d73c3492f206f917986eee11f98b8"}}