{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LKDN24DQOHECLZAAQOLWCIAWA7","short_pith_number":"pith:LKDN24DQ","schema_version":"1.0","canonical_sha256":"5a86dd707071c825e400839761201607f0808553a6751af32cd2971fb4c98cf6","source":{"kind":"arxiv","id":"2012.00172","version":1},"attestation_state":"computed","paper":{"title":"Deconstructing the Structure of Sparse Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Kiana Ehsani, Maxwell Van Gelder, Mitchell Wortsman","submitted_at":"2020-11-30T23:51:33Z","abstract_excerpt":"Although sparse neural networks have been studied extensively, the focus has been primarily on accuracy. In this work, we focus instead on network structure, and analyze three popular algorithms. We first measure performance when structure persists and weights are reset to a different random initialization, thereby extending experiments in Deconstructing Lottery Tickets (Zhou et al., 2019). This experiment reveals that accuracy can be derived from structure alone. Second, to measure structural robustness we investigate the sensitivity of sparse neural networks to further pruning after training"},"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":"2012.00172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T23:51:33Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7e6ea608b7107c10dfd9bb0d26fc5b8e0ecc5255607723db7786ec28b67421c2","abstract_canon_sha256":"63ba9ba90459ca5cab343de921339b5405a95bb9d3667ce49c978303698486a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:33.244307Z","signature_b64":"EUaSu84rarh6BpvG5TCKvAP0vnQeimcdlyCQXfst5YKmg3e/uaw6wbOQRPeXQCq2ADcDD6uG/xpgSOIgfAJuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a86dd707071c825e400839761201607f0808553a6751af32cd2971fb4c98cf6","last_reissued_at":"2026-07-05T01:55:33.243901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:33.243901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deconstructing the Structure of Sparse Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Kiana Ehsani, Maxwell Van Gelder, Mitchell Wortsman","submitted_at":"2020-11-30T23:51:33Z","abstract_excerpt":"Although sparse neural networks have been studied extensively, the focus has been primarily on accuracy. In this work, we focus instead on network structure, and analyze three popular algorithms. We first measure performance when structure persists and weights are reset to a different random initialization, thereby extending experiments in Deconstructing Lottery Tickets (Zhou et al., 2019). This experiment reveals that accuracy can be derived from structure alone. Second, to measure structural robustness we investigate the sensitivity of sparse neural networks to further pruning after training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00172","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/2012.00172/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":"2012.00172","created_at":"2026-07-05T01:55:33.243957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.00172v1","created_at":"2026-07-05T01:55:33.243957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00172","created_at":"2026-07-05T01:55:33.243957+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKDN24DQOHEC","created_at":"2026-07-05T01:55:33.243957+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKDN24DQOHECLZAA","created_at":"2026-07-05T01:55:33.243957+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKDN24DQ","created_at":"2026-07-05T01:55:33.243957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00249","citing_title":"A Hodge-FAST Framework for High-Resolution Dynamic Functional Connectivity Analysis of Higher Order Interactions in EEG Signals","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7","json":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7.json","graph_json":"https://pith.science/api/pith-number/LKDN24DQOHECLZAAQOLWCIAWA7/graph.json","events_json":"https://pith.science/api/pith-number/LKDN24DQOHECLZAAQOLWCIAWA7/events.json","paper":"https://pith.science/paper/LKDN24DQ"},"agent_actions":{"view_html":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7","download_json":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7.json","view_paper":"https://pith.science/paper/LKDN24DQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.00172&json=true","fetch_graph":"https://pith.science/api/pith-number/LKDN24DQOHECLZAAQOLWCIAWA7/graph.json","fetch_events":"https://pith.science/api/pith-number/LKDN24DQOHECLZAAQOLWCIAWA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7/action/storage_attestation","attest_author":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7/action/author_attestation","sign_citation":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7/action/citation_signature","submit_replication":"https://pith.science/pith/LKDN24DQOHECLZAAQOLWCIAWA7/action/replication_record"}},"created_at":"2026-07-05T01:55:33.243957+00:00","updated_at":"2026-07-05T01:55:33.243957+00:00"}