{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AILSCWHWCL37K3XC7P4TICWREV","short_pith_number":"pith:AILSCWHW","canonical_record":{"source":{"id":"1808.06866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-21T12:22:38Z","cross_cats_sorted":[],"title_canon_sha256":"66a72316ed0b163918947fa965103b3548283d4fa6b550e0ce989c42fd60a00a","abstract_canon_sha256":"b5b9fe84e96aec012ac6d7ca14a1608f8b85ee5c7358e8d20624910c99ee00b9"},"schema_version":"1.0"},"canonical_sha256":"02172158f612f7f56ee2fbf9340ad1256575fa8d2ea1d7b29710c909bd1d5abc","source":{"kind":"arxiv","id":"1808.06866","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.06866","created_at":"2026-05-18T00:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"1808.06866v1","created_at":"2026-05-18T00:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06866","created_at":"2026-05-18T00:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"AILSCWHWCL37","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AILSCWHWCL37K3XC","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AILSCWHW","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AILSCWHWCL37K3XC7P4TICWREV","target":"record","payload":{"canonical_record":{"source":{"id":"1808.06866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-21T12:22:38Z","cross_cats_sorted":[],"title_canon_sha256":"66a72316ed0b163918947fa965103b3548283d4fa6b550e0ce989c42fd60a00a","abstract_canon_sha256":"b5b9fe84e96aec012ac6d7ca14a1608f8b85ee5c7358e8d20624910c99ee00b9"},"schema_version":"1.0"},"canonical_sha256":"02172158f612f7f56ee2fbf9340ad1256575fa8d2ea1d7b29710c909bd1d5abc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:38.831708Z","signature_b64":"rX6G3S+ot21Y/G7w0LY8bK0n5I56QJJKsJiuQ2YY/oefSmPer4nw6oM6obFN/fZ9A3qz7fYnLbbBGFt43T67Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02172158f612f7f56ee2fbf9340ad1256575fa8d2ea1d7b29710c909bd1d5abc","last_reissued_at":"2026-05-18T00:07:38.831028Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:38.831028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.06866","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":"2026-05-18T00:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KUpKD2vCltohdTG9ck5NeseNJbiq1YCjmnhmxRru0M3ud5ggzaQ16PZ/zRgvJq9FlTh4NntiMa+e75b4p+KwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:14:22.777804Z"},"content_sha256":"28cd63645efa68a414bdaf7a785d284cc904916c12e67b91fc170bf7f47e9a54","schema_version":"1.0","event_id":"sha256:28cd63645efa68a414bdaf7a785d284cc904916c12e67b91fc170bf7f47e9a54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AILSCWHWCL37K3XC7P4TICWREV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoliang Kang, Xuanyi Dong, Yang He, Yanwei Fu, Yi Yang","submitted_at":"2018-08-21T12:22:38Z","abstract_excerpt":"This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pre-trained model. Large "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06866","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":""},"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":"2026-05-18T00:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+t5LyvaZ4LNRKKVcKoYpe6kBy7C1/XVKrGk6rKJa5DlDTyWLwamEaj/jehTzlj+QluT2SjAn8iyqdOvi5BGDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:14:22.778456Z"},"content_sha256":"a1aabe7b42f1c41ad8b132ecf86f83332661990c63ba9bd22d6001ea54fa0556","schema_version":"1.0","event_id":"sha256:a1aabe7b42f1c41ad8b132ecf86f83332661990c63ba9bd22d6001ea54fa0556"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AILSCWHWCL37K3XC7P4TICWREV/bundle.json","state_url":"https://pith.science/pith/AILSCWHWCL37K3XC7P4TICWREV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AILSCWHWCL37K3XC7P4TICWREV/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":"2026-05-30T07:14:22Z","links":{"resolver":"https://pith.science/pith/AILSCWHWCL37K3XC7P4TICWREV","bundle":"https://pith.science/pith/AILSCWHWCL37K3XC7P4TICWREV/bundle.json","state":"https://pith.science/pith/AILSCWHWCL37K3XC7P4TICWREV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AILSCWHWCL37K3XC7P4TICWREV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AILSCWHWCL37K3XC7P4TICWREV","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":"b5b9fe84e96aec012ac6d7ca14a1608f8b85ee5c7358e8d20624910c99ee00b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-21T12:22:38Z","title_canon_sha256":"66a72316ed0b163918947fa965103b3548283d4fa6b550e0ce989c42fd60a00a"},"schema_version":"1.0","source":{"id":"1808.06866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.06866","created_at":"2026-05-18T00:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"1808.06866v1","created_at":"2026-05-18T00:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.06866","created_at":"2026-05-18T00:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"AILSCWHWCL37","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AILSCWHWCL37K3XC","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AILSCWHW","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:a1aabe7b42f1c41ad8b132ecf86f83332661990c63ba9bd22d6001ea54fa0556","target":"graph","created_at":"2026-05-18T00:07:38Z","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":"This paper proposed a Soft Filter Pruning (SFP) method to accelerate the inference procedure of deep Convolutional Neural Networks (CNNs). Specifically, the proposed SFP enables the pruned filters to be updated when training the model after pruning. SFP has two advantages over previous works: (1) Larger model capacity. Updating previously pruned filters provides our approach with larger optimization space than fixing the filters to zero. Therefore, the network trained by our method has a larger model capacity to learn from the training data. (2) Less dependence on the pre-trained model. Large ","authors_text":"Guoliang Kang, Xuanyi Dong, Yang He, Yanwei Fu, Yi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-21T12:22:38Z","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.06866","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":"sha256:28cd63645efa68a414bdaf7a785d284cc904916c12e67b91fc170bf7f47e9a54","target":"record","created_at":"2026-05-18T00:07:38Z","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":"b5b9fe84e96aec012ac6d7ca14a1608f8b85ee5c7358e8d20624910c99ee00b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-21T12:22:38Z","title_canon_sha256":"66a72316ed0b163918947fa965103b3548283d4fa6b550e0ce989c42fd60a00a"},"schema_version":"1.0","source":{"id":"1808.06866","kind":"arxiv","version":1}},"canonical_sha256":"02172158f612f7f56ee2fbf9340ad1256575fa8d2ea1d7b29710c909bd1d5abc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02172158f612f7f56ee2fbf9340ad1256575fa8d2ea1d7b29710c909bd1d5abc","first_computed_at":"2026-05-18T00:07:38.831028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:38.831028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rX6G3S+ot21Y/G7w0LY8bK0n5I56QJJKsJiuQ2YY/oefSmPer4nw6oM6obFN/fZ9A3qz7fYnLbbBGFt43T67Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:38.831708Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.06866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28cd63645efa68a414bdaf7a785d284cc904916c12e67b91fc170bf7f47e9a54","sha256:a1aabe7b42f1c41ad8b132ecf86f83332661990c63ba9bd22d6001ea54fa0556"],"state_sha256":"71aed5f9f2bf4a3c0cb2d927b45dad9183729ef6e423245b7ee4f2826bcefb64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZwaJlvTShqF/ThxuUWagNqx4z3kXS0RHgCPRCHcg+s1FrU8dQDWWvTGEPenHd9MvsZf5T+T+fMtVLaj9W69uDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:14:22.782005Z","bundle_sha256":"7a448210079f0ffce7197c0e1178c990d22a67975991b774391db4064c260e5f"}}