{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E7EMALARBQ7VBG5SQYMDLIMTYO","short_pith_number":"pith:E7EMALAR","schema_version":"1.0","canonical_sha256":"27c8c02c110c3f509bb2861835a193c397238a739b6d455ff2d60bc46fb68ef4","source":{"kind":"arxiv","id":"2112.13896","version":1},"attestation_state":"computed","paper":{"title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Kevin Lee Hunter, Lawrence Spracklen, Subutai Ahmad","submitted_at":"2021-12-27T20:41:01Z","abstract_excerpt":"In principle, sparse neural networks should be significantly more efficient than traditional dense networks. Neurons in the brain exhibit two types of sparsity; they are sparsely interconnected and sparsely active. These two types of sparsity, called weight sparsity and activation sparsity, when combined, offer the potential to reduce the computational cost of neural networks by two orders of magnitude. Despite this potential, today's neural networks deliver only modest performance benefits using just weight sparsity, because traditional computing hardware cannot efficiently process sparse net"},"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":"2112.13896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-27T20:41:01Z","cross_cats_sorted":["cs.AI","cs.AR","cs.NE"],"title_canon_sha256":"eb862d944db5ca2613614bb214c1c5d42ec4f0814c542e4b94c0723f928c5e8c","abstract_canon_sha256":"fed1b884dc0a2eacfdbc4727ccc435a85f38c943cfd243d10476ceb21c06d122"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:00.083245Z","signature_b64":"yK601sK+pkbz87ivKO72ZmCdPXA39wBEoRmoY8iUP+/JOzsP75TA4JBr17D3NNsmyb96faYPVzPqgKESbNM1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27c8c02c110c3f509bb2861835a193c397238a739b6d455ff2d60bc46fb68ef4","last_reissued_at":"2026-07-05T03:44:00.082854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:00.082854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Kevin Lee Hunter, Lawrence Spracklen, Subutai Ahmad","submitted_at":"2021-12-27T20:41:01Z","abstract_excerpt":"In principle, sparse neural networks should be significantly more efficient than traditional dense networks. Neurons in the brain exhibit two types of sparsity; they are sparsely interconnected and sparsely active. These two types of sparsity, called weight sparsity and activation sparsity, when combined, offer the potential to reduce the computational cost of neural networks by two orders of magnitude. Despite this potential, today's neural networks deliver only modest performance benefits using just weight sparsity, because traditional computing hardware cannot efficiently process sparse net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13896","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/2112.13896/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":"2112.13896","created_at":"2026-07-05T03:44:00.082910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.13896v1","created_at":"2026-07-05T03:44:00.082910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13896","created_at":"2026-07-05T03:44:00.082910+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7EMALARBQ7V","created_at":"2026-07-05T03:44:00.082910+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7EMALARBQ7VBG5S","created_at":"2026-07-05T03:44:00.082910+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7EMALAR","created_at":"2026-07-05T03:44:00.082910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21468","citing_title":"TopK Language Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO","json":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO.json","graph_json":"https://pith.science/api/pith-number/E7EMALARBQ7VBG5SQYMDLIMTYO/graph.json","events_json":"https://pith.science/api/pith-number/E7EMALARBQ7VBG5SQYMDLIMTYO/events.json","paper":"https://pith.science/paper/E7EMALAR"},"agent_actions":{"view_html":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO","download_json":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO.json","view_paper":"https://pith.science/paper/E7EMALAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.13896&json=true","fetch_graph":"https://pith.science/api/pith-number/E7EMALARBQ7VBG5SQYMDLIMTYO/graph.json","fetch_events":"https://pith.science/api/pith-number/E7EMALARBQ7VBG5SQYMDLIMTYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO/action/storage_attestation","attest_author":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO/action/author_attestation","sign_citation":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO/action/citation_signature","submit_replication":"https://pith.science/pith/E7EMALARBQ7VBG5SQYMDLIMTYO/action/replication_record"}},"created_at":"2026-07-05T03:44:00.082910+00:00","updated_at":"2026-07-05T03:44:00.082910+00:00"}