{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FYZ2H2JBPBAGBX54L5IZ5E63FC","short_pith_number":"pith:FYZ2H2JB","schema_version":"1.0","canonical_sha256":"2e33a3e921784060dfbc5f519e93db28b534d2ea3b7e14f4d66e52f81a5a3f92","source":{"kind":"arxiv","id":"2210.09223","version":2},"attestation_state":"computed","paper":{"title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dan Alistarh, Denis Kuznedelev, Eldar Kurtic, Elias Frantar","submitted_at":"2022-10-14T12:19:09Z","abstract_excerpt":"Driven by significant improvements in architectural design and training pipelines, computer vision has recently experienced dramatic progress in terms of accuracy on classic benchmarks such as ImageNet. These highly-accurate models are challenging to deploy, as they appear harder to compress using standard techniques such as pruning. We address this issue by introducing the Correlation Aware Pruner (CAP), a new unstructured pruning framework which significantly pushes the compressibility limits for state-of-the-art architectures. Our method is based on two technical advancements: a new theoret"},"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":"2210.09223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-14T12:19:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12abb9cef7426a7e0577b2b995a9a406d532b4b33dc9b76bea61d229dfd7dd06","abstract_canon_sha256":"b06cb848fd41b7bceabaa7c331f75cbc1652cbed9b5345f66baa216409d9074a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:43.512300Z","signature_b64":"QgVSpJUF5RMLovIBx+Ih4xeiVoO9Pfh8cVznkxIdhrZ0fKRM/pKiB2anHx0lw1xieHugk/jMDqAbnNNKcvmUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e33a3e921784060dfbc5f519e93db28b534d2ea3b7e14f4d66e52f81a5a3f92","last_reissued_at":"2026-07-05T06:15:43.511808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:43.511808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dan Alistarh, Denis Kuznedelev, Eldar Kurtic, Elias Frantar","submitted_at":"2022-10-14T12:19:09Z","abstract_excerpt":"Driven by significant improvements in architectural design and training pipelines, computer vision has recently experienced dramatic progress in terms of accuracy on classic benchmarks such as ImageNet. These highly-accurate models are challenging to deploy, as they appear harder to compress using standard techniques such as pruning. We address this issue by introducing the Correlation Aware Pruner (CAP), a new unstructured pruning framework which significantly pushes the compressibility limits for state-of-the-art architectures. Our method is based on two technical advancements: a new theoret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09223","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.09223/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":"2210.09223","created_at":"2026-07-05T06:15:43.511877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09223v2","created_at":"2026-07-05T06:15:43.511877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09223","created_at":"2026-07-05T06:15:43.511877+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYZ2H2JBPBAG","created_at":"2026-07-05T06:15:43.511877+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYZ2H2JBPBAGBX54","created_at":"2026-07-05T06:15:43.511877+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYZ2H2JB","created_at":"2026-07-05T06:15:43.511877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02328","citing_title":"Efficient Model Compression Techniques with FishLeg","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC","json":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC.json","graph_json":"https://pith.science/api/pith-number/FYZ2H2JBPBAGBX54L5IZ5E63FC/graph.json","events_json":"https://pith.science/api/pith-number/FYZ2H2JBPBAGBX54L5IZ5E63FC/events.json","paper":"https://pith.science/paper/FYZ2H2JB"},"agent_actions":{"view_html":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC","download_json":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC.json","view_paper":"https://pith.science/paper/FYZ2H2JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09223&json=true","fetch_graph":"https://pith.science/api/pith-number/FYZ2H2JBPBAGBX54L5IZ5E63FC/graph.json","fetch_events":"https://pith.science/api/pith-number/FYZ2H2JBPBAGBX54L5IZ5E63FC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC/action/storage_attestation","attest_author":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC/action/author_attestation","sign_citation":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC/action/citation_signature","submit_replication":"https://pith.science/pith/FYZ2H2JBPBAGBX54L5IZ5E63FC/action/replication_record"}},"created_at":"2026-07-05T06:15:43.511877+00:00","updated_at":"2026-07-05T06:15:43.511877+00:00"}