{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E3FO4DRRHCHIQIEBFYBBTP3CTC","short_pith_number":"pith:E3FO4DRR","schema_version":"1.0","canonical_sha256":"26caee0e31388e8820812e0219bf62989828eafc149a1e97b9860febe9565672","source":{"kind":"arxiv","id":"2202.07190","version":1},"attestation_state":"computed","paper":{"title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chia-Wen Lin, Ling Shao, Liujuan Cao, Mingbao Lin, Rongrong Ji, Yuxin Zhang","submitted_at":"2022-02-15T04:53:24Z","abstract_excerpt":"This paper focuses on filter-level network pruning. A novel pruning method, termed CLR-RNF, is proposed. We first reveal a \"long-tail\" long-tail pruning problem in magnitude-based weight pruning methods, and then propose a computation-aware measurement for individual weight importance, followed by a Cross-Layer Ranking (CLR) of weights to identify and remove the bottom-ranked weights. Consequently, the per-layer sparsity makes up of the pruned network structure in our filter pruning. Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.07190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-15T04:53:24Z","cross_cats_sorted":[],"title_canon_sha256":"e28537a6fb7b3467b0e2dc8c1d1c51b11c048e21ba394c649408c2f5838fecaa","abstract_canon_sha256":"df95ad3942698e1554cf2c4fd8641a35aaf7069ed73156e91430042f524e7200"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:57.502491Z","signature_b64":"fLXcaX+Mv9dydtIvkIWTQzPEHJdi9PX3RBrJkNY33SPa9FZXwuz24ZqozdABS6RDSzkpOV2mJJxn+nfFnqzCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26caee0e31388e8820812e0219bf62989828eafc149a1e97b9860febe9565672","last_reissued_at":"2026-07-05T03:56:57.501870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:57.501870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chia-Wen Lin, Ling Shao, Liujuan Cao, Mingbao Lin, Rongrong Ji, Yuxin Zhang","submitted_at":"2022-02-15T04:53:24Z","abstract_excerpt":"This paper focuses on filter-level network pruning. A novel pruning method, termed CLR-RNF, is proposed. We first reveal a \"long-tail\" long-tail pruning problem in magnitude-based weight pruning methods, and then propose a computation-aware measurement for individual weight importance, followed by a Cross-Layer Ranking (CLR) of weights to identify and remove the bottom-ranked weights. Consequently, the per-layer sparsity makes up of the pruned network structure in our filter pruning. Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07190","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/2202.07190/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.07190","created_at":"2026-07-05T03:56:57.501946+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07190v1","created_at":"2026-07-05T03:56:57.501946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07190","created_at":"2026-07-05T03:56:57.501946+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3FO4DRRHCHI","created_at":"2026-07-05T03:56:57.501946+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3FO4DRRHCHIQIEB","created_at":"2026-07-05T03:56:57.501946+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3FO4DRR","created_at":"2026-07-05T03:56:57.501946+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC","json":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC.json","graph_json":"https://pith.science/api/pith-number/E3FO4DRRHCHIQIEBFYBBTP3CTC/graph.json","events_json":"https://pith.science/api/pith-number/E3FO4DRRHCHIQIEBFYBBTP3CTC/events.json","paper":"https://pith.science/paper/E3FO4DRR"},"agent_actions":{"view_html":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC","download_json":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC.json","view_paper":"https://pith.science/paper/E3FO4DRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07190&json=true","fetch_graph":"https://pith.science/api/pith-number/E3FO4DRRHCHIQIEBFYBBTP3CTC/graph.json","fetch_events":"https://pith.science/api/pith-number/E3FO4DRRHCHIQIEBFYBBTP3CTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC/action/storage_attestation","attest_author":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC/action/author_attestation","sign_citation":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC/action/citation_signature","submit_replication":"https://pith.science/pith/E3FO4DRRHCHIQIEBFYBBTP3CTC/action/replication_record"}},"created_at":"2026-07-05T03:56:57.501946+00:00","updated_at":"2026-07-05T03:56:57.501946+00:00"}