{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QWEQKSQHWXR5KAJVUXTGLQX3BN","short_pith_number":"pith:QWEQKSQH","schema_version":"1.0","canonical_sha256":"8589054a07b5e3d50135a5e665c2fb0b676ebdfeb0103333c266ad4ab9f94a18","source":{"kind":"arxiv","id":"1909.02603","version":2},"attestation_state":"computed","paper":{"title":"Additive function approximation in the brain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.NC","stat.ML"],"primary_cat":"cs.NE","authors_text":"Kameron Decker Harris","submitted_at":"2019-09-05T19:07:33Z","abstract_excerpt":"Many biological learning systems such as the mushroom body, hippocampus, and cerebellum are built from sparsely connected networks of neurons. For a new understanding of such networks, we study the function spaces induced by sparse random features and characterize what functions may and may not be learned. A network with $d$ inputs per neuron is found to be equivalent to an additive model of order $d$, whereas with a degree distribution the network combines additive terms of different orders. We identify three specific advantages of sparsity: additive function approximation is a powerful induc"},"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":"1909.02603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-09-05T19:07:33Z","cross_cats_sorted":["cs.LG","q-bio.NC","stat.ML"],"title_canon_sha256":"096f502e55d8c81d9caa700a6fea8005c35e35bfe257dabd523daeab7cfa7512","abstract_canon_sha256":"d067d0158da4855d0edea9a790817d571bdb1745ff22da380d60efc4fec4fab6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:12.347143Z","signature_b64":"2tZnnT2kMLF9i4R4iH4dhnm+oCQcqlXq+HULwKN3q40eUge/plt3VIjcVn8Y/5pxp00APUg8LnOEAmPYjxS0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8589054a07b5e3d50135a5e665c2fb0b676ebdfeb0103333c266ad4ab9f94a18","last_reissued_at":"2026-07-05T03:58:12.346502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:12.346502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Additive function approximation in the brain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.NC","stat.ML"],"primary_cat":"cs.NE","authors_text":"Kameron Decker Harris","submitted_at":"2019-09-05T19:07:33Z","abstract_excerpt":"Many biological learning systems such as the mushroom body, hippocampus, and cerebellum are built from sparsely connected networks of neurons. For a new understanding of such networks, we study the function spaces induced by sparse random features and characterize what functions may and may not be learned. A network with $d$ inputs per neuron is found to be equivalent to an additive model of order $d$, whereas with a degree distribution the network combines additive terms of different orders. We identify three specific advantages of sparsity: additive function approximation is a powerful induc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02603","kind":"arxiv","version":2},"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/1909.02603/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":"1909.02603","created_at":"2026-07-05T03:58:12.346579+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02603v2","created_at":"2026-07-05T03:58:12.346579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02603","created_at":"2026-07-05T03:58:12.346579+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWEQKSQHWXR5","created_at":"2026-07-05T03:58:12.346579+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWEQKSQHWXR5KAJV","created_at":"2026-07-05T03:58:12.346579+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWEQKSQH","created_at":"2026-07-05T03:58:12.346579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02385","citing_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN","json":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN.json","graph_json":"https://pith.science/api/pith-number/QWEQKSQHWXR5KAJVUXTGLQX3BN/graph.json","events_json":"https://pith.science/api/pith-number/QWEQKSQHWXR5KAJVUXTGLQX3BN/events.json","paper":"https://pith.science/paper/QWEQKSQH"},"agent_actions":{"view_html":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN","download_json":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN.json","view_paper":"https://pith.science/paper/QWEQKSQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02603&json=true","fetch_graph":"https://pith.science/api/pith-number/QWEQKSQHWXR5KAJVUXTGLQX3BN/graph.json","fetch_events":"https://pith.science/api/pith-number/QWEQKSQHWXR5KAJVUXTGLQX3BN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN/action/storage_attestation","attest_author":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN/action/author_attestation","sign_citation":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN/action/citation_signature","submit_replication":"https://pith.science/pith/QWEQKSQHWXR5KAJVUXTGLQX3BN/action/replication_record"}},"created_at":"2026-07-05T03:58:12.346579+00:00","updated_at":"2026-07-05T03:58:12.346579+00:00"}