{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3RR774CXSSVHDCO5FRYLYS3WUA","short_pith_number":"pith:3RR774CX","schema_version":"1.0","canonical_sha256":"dc63fff05794aa7189dd2c70bc4b76a033ea7733a61d89f5355f311da94a5b0c","source":{"kind":"arxiv","id":"2411.00147","version":2},"attestation_state":"computed","paper":{"title":"Mutual Information Preserving Neural Network Pruning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charles Westphal, Mirco Musolesi, Stephen Hailes","submitted_at":"2024-10-31T18:50:15Z","abstract_excerpt":"Pruning has emerged as the primary approach used to limit the resource requirements of large neural networks (NNs). Since the proposal of the lottery ticket hypothesis, researchers have focused either on pruning at initialization or after training. However, recent theoretical findings have shown that the sample efficiency of robust pruned models is proportional to the mutual information (MI) between the pruning masks and the model's training datasets, \\textit{whether at initialization or after training}. In this paper, starting from these results, we introduce Mutual Information Preserving Pru"},"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":"2411.00147","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T18:50:15Z","cross_cats_sorted":[],"title_canon_sha256":"e86d437617ae97267a50adde2a84e2c292d328437bfec21989236c40ed6144ea","abstract_canon_sha256":"96e8e78b48b7dd8bd6f890e558717c9f3e3db7639c040a9d02d74038d10a4eb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:23.993858Z","signature_b64":"a7sgZfissCN6XzUoTmplXujizSm5cECqaavOQmh9qELzHIEXHN3TOCn26Xf0frnxAE5R1RPtB3yHb+TgOeVZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc63fff05794aa7189dd2c70bc4b76a033ea7733a61d89f5355f311da94a5b0c","last_reissued_at":"2026-07-05T10:08:23.993378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:23.993378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mutual Information Preserving Neural Network Pruning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charles Westphal, Mirco Musolesi, Stephen Hailes","submitted_at":"2024-10-31T18:50:15Z","abstract_excerpt":"Pruning has emerged as the primary approach used to limit the resource requirements of large neural networks (NNs). Since the proposal of the lottery ticket hypothesis, researchers have focused either on pruning at initialization or after training. However, recent theoretical findings have shown that the sample efficiency of robust pruned models is proportional to the mutual information (MI) between the pruning masks and the model's training datasets, \\textit{whether at initialization or after training}. In this paper, starting from these results, we introduce Mutual Information Preserving Pru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00147","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/2411.00147/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":"2411.00147","created_at":"2026-07-05T10:08:23.993437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00147v2","created_at":"2026-07-05T10:08:23.993437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00147","created_at":"2026-07-05T10:08:23.993437+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RR774CXSSVH","created_at":"2026-07-05T10:08:23.993437+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RR774CXSSVHDCO5","created_at":"2026-07-05T10:08:23.993437+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RR774CX","created_at":"2026-07-05T10:08:23.993437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14738","citing_title":"TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2510.22767","citing_title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07086","citing_title":"Task Relevance Is Not Local Replaceability: A Two-Axis View of Channel Information","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07086","citing_title":"Task Relevance Is Not Local Replaceability: A Two-Axis View of Channel Information","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA","json":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA.json","graph_json":"https://pith.science/api/pith-number/3RR774CXSSVHDCO5FRYLYS3WUA/graph.json","events_json":"https://pith.science/api/pith-number/3RR774CXSSVHDCO5FRYLYS3WUA/events.json","paper":"https://pith.science/paper/3RR774CX"},"agent_actions":{"view_html":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA","download_json":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA.json","view_paper":"https://pith.science/paper/3RR774CX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00147&json=true","fetch_graph":"https://pith.science/api/pith-number/3RR774CXSSVHDCO5FRYLYS3WUA/graph.json","fetch_events":"https://pith.science/api/pith-number/3RR774CXSSVHDCO5FRYLYS3WUA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA/action/storage_attestation","attest_author":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA/action/author_attestation","sign_citation":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA/action/citation_signature","submit_replication":"https://pith.science/pith/3RR774CXSSVHDCO5FRYLYS3WUA/action/replication_record"}},"created_at":"2026-07-05T10:08:23.993437+00:00","updated_at":"2026-07-05T10:08:23.993437+00:00"}