{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:STWH4F4NW3PUK5NFZ2IU44M73Y","short_pith_number":"pith:STWH4F4N","schema_version":"1.0","canonical_sha256":"94ec7e178db6df4575a5ce914e719fde140fad564acba0efd94ba3342dc63221","source":{"kind":"arxiv","id":"2109.09612","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Kovalenko, Magda Friedjungov\\'a, Pavel Kord\\'ik","submitted_at":"2021-09-20T15:12:16Z","abstract_excerpt":"Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks, where now excessively large models are used. However, such models face several problems during the learning process, mainly due to the redundancy of the individual neurons, which results in sub-optimal accuracy or the need for additional training steps. Here, we explore the diversity of the neurons within the hidden layer during the learning process, and analyze how the diversity of the neurons affects predictions of the model. As following, we introduce"},"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":"2109.09612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T15:12:16Z","cross_cats_sorted":[],"title_canon_sha256":"b29283d4296dfbf389b4a3d33b2f26ad8bdbbde7009c973411fbc2a5b4abd5eb","abstract_canon_sha256":"77469d3662da502eb8809f8090e56d739de1c9052aaf90c408d06be9b4460332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:47.918217Z","signature_b64":"fBNf69+oTfNuSOuFeJXS5eInvOixNG+TVF6zRSjsd2RdE3EAmSICxJx5lpfnl+ST3wwDbNQy+4nUwZ++JQZmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94ec7e178db6df4575a5ce914e719fde140fad564acba0efd94ba3342dc63221","last_reissued_at":"2026-07-05T03:15:47.917720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:47.917720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Kovalenko, Magda Friedjungov\\'a, Pavel Kord\\'ik","submitted_at":"2021-09-20T15:12:16Z","abstract_excerpt":"Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks, where now excessively large models are used. However, such models face several problems during the learning process, mainly due to the redundancy of the individual neurons, which results in sub-optimal accuracy or the need for additional training steps. Here, we explore the diversity of the neurons within the hidden layer during the learning process, and analyze how the diversity of the neurons affects predictions of the model. As following, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09612","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/2109.09612/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":"2109.09612","created_at":"2026-07-05T03:15:47.917782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09612v1","created_at":"2026-07-05T03:15:47.917782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09612","created_at":"2026-07-05T03:15:47.917782+00:00"},{"alias_kind":"pith_short_12","alias_value":"STWH4F4NW3PU","created_at":"2026-07-05T03:15:47.917782+00:00"},{"alias_kind":"pith_short_16","alias_value":"STWH4F4NW3PUK5NF","created_at":"2026-07-05T03:15:47.917782+00:00"},{"alias_kind":"pith_short_8","alias_value":"STWH4F4N","created_at":"2026-07-05T03:15:47.917782+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/STWH4F4NW3PUK5NFZ2IU44M73Y","json":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y.json","graph_json":"https://pith.science/api/pith-number/STWH4F4NW3PUK5NFZ2IU44M73Y/graph.json","events_json":"https://pith.science/api/pith-number/STWH4F4NW3PUK5NFZ2IU44M73Y/events.json","paper":"https://pith.science/paper/STWH4F4N"},"agent_actions":{"view_html":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y","download_json":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y.json","view_paper":"https://pith.science/paper/STWH4F4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09612&json=true","fetch_graph":"https://pith.science/api/pith-number/STWH4F4NW3PUK5NFZ2IU44M73Y/graph.json","fetch_events":"https://pith.science/api/pith-number/STWH4F4NW3PUK5NFZ2IU44M73Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y/action/storage_attestation","attest_author":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y/action/author_attestation","sign_citation":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y/action/citation_signature","submit_replication":"https://pith.science/pith/STWH4F4NW3PUK5NFZ2IU44M73Y/action/replication_record"}},"created_at":"2026-07-05T03:15:47.917782+00:00","updated_at":"2026-07-05T03:15:47.917782+00:00"}