{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KOUWXSGAV56P5GGV34QGWFLYEW","short_pith_number":"pith:KOUWXSGA","schema_version":"1.0","canonical_sha256":"53a96bc8c0af7cfe98d5df206b1578258a5219583725faf21efa8df2f46c74e4","source":{"kind":"arxiv","id":"2408.04583","version":1},"attestation_state":"computed","paper":{"title":"Unveiling the Power of Sparse Neural Networks for Feature Selection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Decebal Constantin Mocanu, Mihaela van der Schaar, Mykola Pechenizkiy, Raymond Veldhuis, Tennison Liu, Zahra Atashgahi","submitted_at":"2024-08-08T16:48:33Z","abstract_excerpt":"Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared t"},"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":"2408.04583","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T16:48:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef6ccbedf9ae58cfeac48cde72a2d68ba16f2fd5aec5e99d0f54b1517b4cfe51","abstract_canon_sha256":"752d679096a9b9624d73f64850674204eb2dadfa95ba8e0c8f5087377c128393"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:35.200669Z","signature_b64":"DFZ9wTW52Qoass8S3fSxLr1Ix1yAPwCx0RzGeBxV+yMpUuG4zFqbK4KUqK2aLsZbVcCkpQINIixmRpyja+S+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53a96bc8c0af7cfe98d5df206b1578258a5219583725faf21efa8df2f46c74e4","last_reissued_at":"2026-07-05T08:53:35.200055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:35.200055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling the Power of Sparse Neural Networks for Feature Selection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Decebal Constantin Mocanu, Mihaela van der Schaar, Mykola Pechenizkiy, Raymond Veldhuis, Tennison Liu, Zahra Atashgahi","submitted_at":"2024-08-08T16:48:33Z","abstract_excerpt":"Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04583","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/2408.04583/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":"2408.04583","created_at":"2026-07-05T08:53:35.200132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04583v1","created_at":"2026-07-05T08:53:35.200132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04583","created_at":"2026-07-05T08:53:35.200132+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOUWXSGAV56P","created_at":"2026-07-05T08:53:35.200132+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOUWXSGAV56P5GGV","created_at":"2026-07-05T08:53:35.200132+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOUWXSGA","created_at":"2026-07-05T08:53:35.200132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07613","citing_title":"Sparse Self-Federated Learning for Energy Efficient Cooperative Intelligence in Society 5.0","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW","json":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW.json","graph_json":"https://pith.science/api/pith-number/KOUWXSGAV56P5GGV34QGWFLYEW/graph.json","events_json":"https://pith.science/api/pith-number/KOUWXSGAV56P5GGV34QGWFLYEW/events.json","paper":"https://pith.science/paper/KOUWXSGA"},"agent_actions":{"view_html":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW","download_json":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW.json","view_paper":"https://pith.science/paper/KOUWXSGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04583&json=true","fetch_graph":"https://pith.science/api/pith-number/KOUWXSGAV56P5GGV34QGWFLYEW/graph.json","fetch_events":"https://pith.science/api/pith-number/KOUWXSGAV56P5GGV34QGWFLYEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW/action/storage_attestation","attest_author":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW/action/author_attestation","sign_citation":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW/action/citation_signature","submit_replication":"https://pith.science/pith/KOUWXSGAV56P5GGV34QGWFLYEW/action/replication_record"}},"created_at":"2026-07-05T08:53:35.200132+00:00","updated_at":"2026-07-05T08:53:35.200132+00:00"}