{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OKMUOYQKNL6LKMSQQMAWSR6LV2","short_pith_number":"pith:OKMUOYQK","schema_version":"1.0","canonical_sha256":"729947620a6afcb5325083016947cbae862bcdc52682c55f0f7608227fc897a0","source":{"kind":"arxiv","id":"1906.11626","version":1},"attestation_state":"computed","paper":{"title":"On improving deep learning generalization with adaptive sparse connectivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Decebal Constantin Mocanu, Mykola Pechenizkiy, Shiwei Liu","submitted_at":"2019-06-27T13:31:30Z","abstract_excerpt":"Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse neural networks with adaptive sparse connectivity, which by design have a strict parameter budget during the training phase, have better generalization capabilities than their fully-connected counterparts. Besides this, we propose a new technique to train these sparse models by combining the Sparse Evolutionary Training (SET) procedure with neurons pruning. Ope"},"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":"1906.11626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-06-27T13:31:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"015e198d828596d5c9c0c402347cb731e41d9b3f3e70dcb731a14dee9724be68","abstract_canon_sha256":"b81a4f3bbfea077cf4a3c0ec385d1a50600c8e3819db398e956a8449c7da39b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:04.273284Z","signature_b64":"mBzObX4/f95lNaNydL6BJM0xGobbJUSP/VyFlU0rzLmRVZXwkSNomSGCNALP/Czwy3GG8apNS6+5wTG6K21/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"729947620a6afcb5325083016947cbae862bcdc52682c55f0f7608227fc897a0","last_reissued_at":"2026-05-17T23:42:04.272653Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:04.272653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On improving deep learning generalization with adaptive sparse connectivity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.NE","authors_text":"Decebal Constantin Mocanu, Mykola Pechenizkiy, Shiwei Liu","submitted_at":"2019-06-27T13:31:30Z","abstract_excerpt":"Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse neural networks with adaptive sparse connectivity, which by design have a strict parameter budget during the training phase, have better generalization capabilities than their fully-connected counterparts. Besides this, we propose a new technique to train these sparse models by combining the Sparse Evolutionary Training (SET) procedure with neurons pruning. Ope"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11626","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":""},"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":"1906.11626","created_at":"2026-05-17T23:42:04.272745+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11626v1","created_at":"2026-05-17T23:42:04.272745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11626","created_at":"2026-05-17T23:42:04.272745+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKMUOYQKNL6L","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKMUOYQKNL6LKMSQ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKMUOYQK","created_at":"2026-05-18T12:33:24.271573+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/OKMUOYQKNL6LKMSQQMAWSR6LV2","json":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2.json","graph_json":"https://pith.science/api/pith-number/OKMUOYQKNL6LKMSQQMAWSR6LV2/graph.json","events_json":"https://pith.science/api/pith-number/OKMUOYQKNL6LKMSQQMAWSR6LV2/events.json","paper":"https://pith.science/paper/OKMUOYQK"},"agent_actions":{"view_html":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2","download_json":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2.json","view_paper":"https://pith.science/paper/OKMUOYQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11626&json=true","fetch_graph":"https://pith.science/api/pith-number/OKMUOYQKNL6LKMSQQMAWSR6LV2/graph.json","fetch_events":"https://pith.science/api/pith-number/OKMUOYQKNL6LKMSQQMAWSR6LV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2/action/storage_attestation","attest_author":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2/action/author_attestation","sign_citation":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2/action/citation_signature","submit_replication":"https://pith.science/pith/OKMUOYQKNL6LKMSQQMAWSR6LV2/action/replication_record"}},"created_at":"2026-05-17T23:42:04.272745+00:00","updated_at":"2026-05-17T23:42:04.272745+00:00"}