{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7FJN5R7WM65NBYSG246V47WGKG","short_pith_number":"pith:7FJN5R7W","schema_version":"1.0","canonical_sha256":"f952dec7f667bad0e246d73d5e7ec651bf09ccfd7aa2a49807c2e887a90a800e","source":{"kind":"arxiv","id":"2411.17796","version":1},"attestation_state":"computed","paper":{"title":"Scalable iterative pruning of large language and vision models using block coordinate descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","quant-ph"],"primary_cat":"cs.LG","authors_text":"Elton Yechao Zhu, Gili Rosenberg, Helmut G. Katzgraber, J. Kyle Brubaker, Martin J. A. Schuetz, Serdar Kad{\\i}o\\u{g}lu, Sima E. Borujeni","submitted_at":"2024-11-26T17:54:02Z","abstract_excerpt":"Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pruning technique that builds upon the Combinatorial Brain Surgeon, but solves an optimization problem over a subset of the network weights in an iterative, block-wise manner using block coordinate descent. The iterative, block-based nature of this pruning technique, which we dub ``iterative Combinatorial Brain Surgeon'' (iCBS) allows for scalability to very large models, includi"},"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":"2411.17796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-26T17:54:02Z","cross_cats_sorted":["math.OC","quant-ph"],"title_canon_sha256":"dd97f4f1c3bb7d411dade24d0b821122dc71bd47b5189bba69415fb784ab951e","abstract_canon_sha256":"d33f8c381ce0480878b1a640248d715d1eb7fdc7e7a43ed328b78368d219c4a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:07.094990Z","signature_b64":"mvt7SiqbOVNJsk2WHqMTvgAk9UtsL91Os4w+Qnv8Z7v855gmIhcI77lr8yOGWZoHIIa4QwPHIXkqtXk+2VoNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f952dec7f667bad0e246d73d5e7ec651bf09ccfd7aa2a49807c2e887a90a800e","last_reissued_at":"2026-07-05T09:41:07.094487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:07.094487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable iterative pruning of large language and vision models using block coordinate descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","quant-ph"],"primary_cat":"cs.LG","authors_text":"Elton Yechao Zhu, Gili Rosenberg, Helmut G. Katzgraber, J. Kyle Brubaker, Martin J. A. Schuetz, Serdar Kad{\\i}o\\u{g}lu, Sima E. Borujeni","submitted_at":"2024-11-26T17:54:02Z","abstract_excerpt":"Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pruning technique that builds upon the Combinatorial Brain Surgeon, but solves an optimization problem over a subset of the network weights in an iterative, block-wise manner using block coordinate descent. The iterative, block-based nature of this pruning technique, which we dub ``iterative Combinatorial Brain Surgeon'' (iCBS) allows for scalability to very large models, includi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17796","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/2411.17796/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":"2411.17796","created_at":"2026-07-05T09:41:07.094550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17796v1","created_at":"2026-07-05T09:41:07.094550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17796","created_at":"2026-07-05T09:41:07.094550+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FJN5R7WM65N","created_at":"2026-07-05T09:41:07.094550+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FJN5R7WM65NBYSG","created_at":"2026-07-05T09:41:07.094550+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FJN5R7W","created_at":"2026-07-05T09:41:07.094550+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/7FJN5R7WM65NBYSG246V47WGKG","json":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG.json","graph_json":"https://pith.science/api/pith-number/7FJN5R7WM65NBYSG246V47WGKG/graph.json","events_json":"https://pith.science/api/pith-number/7FJN5R7WM65NBYSG246V47WGKG/events.json","paper":"https://pith.science/paper/7FJN5R7W"},"agent_actions":{"view_html":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG","download_json":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG.json","view_paper":"https://pith.science/paper/7FJN5R7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17796&json=true","fetch_graph":"https://pith.science/api/pith-number/7FJN5R7WM65NBYSG246V47WGKG/graph.json","fetch_events":"https://pith.science/api/pith-number/7FJN5R7WM65NBYSG246V47WGKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG/action/storage_attestation","attest_author":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG/action/author_attestation","sign_citation":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG/action/citation_signature","submit_replication":"https://pith.science/pith/7FJN5R7WM65NBYSG246V47WGKG/action/replication_record"}},"created_at":"2026-07-05T09:41:07.094550+00:00","updated_at":"2026-07-05T09:41:07.094550+00:00"}