{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FWIRZ7PHUB3RE724RHMELNCALU","short_pith_number":"pith:FWIRZ7PH","schema_version":"1.0","canonical_sha256":"2d911cfde7a077127f5c89d845b4405d18469b5b47b0de2d705437c4091ccf29","source":{"kind":"arxiv","id":"2001.08514","version":4},"attestation_state":"computed","paper":{"title":"Filter Sketch for Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzhuang Liu, Liujuan Cao, Mingbao Lin, Qi Tian, Qixiang Ye, Rongrong Ji, Shaojie Li, Yonghong Tian","submitted_at":"2020-01-23T13:57:08Z","abstract_excerpt":"We propose a novel network pruning approach by information preserving of pre-trained network weights (filters). Network pruning with the information preserving is formulated as a matrix sketch problem, which is efficiently solved by the off-the-shelf Frequent Direction method. Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure. FilterSketch requires neither training from scratch nor data-driven iterative optimization, leading to a"},"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":"2001.08514","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-23T13:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"243395543262ca55569463aa089ee214b19375b602b1c38d3282ebb2a9349dc7","abstract_canon_sha256":"9f5098c2ed21df9d18780394b65c5af205a76a48e0318dd3c33aad2405d83c2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:40.577036Z","signature_b64":"uOWG5hkJ0T3gZCVlccB3+o8Jm7WUOMoMw4d6ATudbewj36Mc+BpLtmN0mr6+DpN7AuZYGgMYYtSyQc4rLApFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d911cfde7a077127f5c89d845b4405d18469b5b47b0de2d705437c4091ccf29","last_reissued_at":"2026-07-05T02:42:40.576545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:40.576545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Filter Sketch for Network Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianzhuang Liu, Liujuan Cao, Mingbao Lin, Qi Tian, Qixiang Ye, Rongrong Ji, Shaojie Li, Yonghong Tian","submitted_at":"2020-01-23T13:57:08Z","abstract_excerpt":"We propose a novel network pruning approach by information preserving of pre-trained network weights (filters). Network pruning with the information preserving is formulated as a matrix sketch problem, which is efficiently solved by the off-the-shelf Frequent Direction method. Our approach, referred to as FilterSketch, encodes the second-order information of pre-trained weights, which enables the representation capacity of pruned networks to be recovered with a simple fine-tuning procedure. FilterSketch requires neither training from scratch nor data-driven iterative optimization, leading to a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08514","kind":"arxiv","version":4},"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/2001.08514/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":"2001.08514","created_at":"2026-07-05T02:42:40.576604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.08514v4","created_at":"2026-07-05T02:42:40.576604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08514","created_at":"2026-07-05T02:42:40.576604+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWIRZ7PHUB3R","created_at":"2026-07-05T02:42:40.576604+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWIRZ7PHUB3RE724","created_at":"2026-07-05T02:42:40.576604+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWIRZ7PH","created_at":"2026-07-05T02:42:40.576604+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/FWIRZ7PHUB3RE724RHMELNCALU","json":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU.json","graph_json":"https://pith.science/api/pith-number/FWIRZ7PHUB3RE724RHMELNCALU/graph.json","events_json":"https://pith.science/api/pith-number/FWIRZ7PHUB3RE724RHMELNCALU/events.json","paper":"https://pith.science/paper/FWIRZ7PH"},"agent_actions":{"view_html":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU","download_json":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU.json","view_paper":"https://pith.science/paper/FWIRZ7PH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.08514&json=true","fetch_graph":"https://pith.science/api/pith-number/FWIRZ7PHUB3RE724RHMELNCALU/graph.json","fetch_events":"https://pith.science/api/pith-number/FWIRZ7PHUB3RE724RHMELNCALU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU/action/storage_attestation","attest_author":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU/action/author_attestation","sign_citation":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU/action/citation_signature","submit_replication":"https://pith.science/pith/FWIRZ7PHUB3RE724RHMELNCALU/action/replication_record"}},"created_at":"2026-07-05T02:42:40.576604+00:00","updated_at":"2026-07-05T02:42:40.576604+00:00"}