{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XACDQQPNYVZR3MADPTFX5ZMR64","short_pith_number":"pith:XACDQQPN","schema_version":"1.0","canonical_sha256":"b8043841edc5731db0037ccb7ee591f7388dd3d283c1bc0544d13856d08bfd32","source":{"kind":"arxiv","id":"2110.06081","version":3},"attestation_state":"computed","paper":{"title":"On Expressivity and Trainability of Quadratic Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Fei Wang, Feng-lei Fan, Ge Wang, Mengzhou Li, Rongjie Lai","submitted_at":"2021-10-12T15:33:32Z","abstract_excerpt":"Inspired by the diversity of biological neurons, quadratic artificial neurons can play an important role in deep learning models. The type of quadratic neurons of our interest replaces the inner-product operation in the conventional neuron with a quadratic function. Despite promising results so far achieved by networks of quadratic neurons, there are important issues not well addressed. Theoretically, the superior expressivity of a quadratic network over either a conventional network or a conventional network via quadratic activation is not fully elucidated, which makes the use of quadratic ne"},"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":"2110.06081","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T15:33:32Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"ef77b562ac2e41b14636720de539c6869a6a52eb635bc253193413c6b2d43a60","abstract_canon_sha256":"2c4b46d1d26aa0d15adf325a462d40a4ccbe675affdc4edf7719d7f60729f4b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:00.807194Z","signature_b64":"N6QDbgay9K+q8SIaNy3yYOUEfF3lxjVq6mye3waZe5TRTj5t2bO9RKlraYf4CmE0CjMLKpBJMRPx4p1rB37nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8043841edc5731db0037ccb7ee591f7388dd3d283c1bc0544d13856d08bfd32","last_reissued_at":"2026-07-05T06:49:00.806683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:00.806683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Expressivity and Trainability of Quadratic Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Fei Wang, Feng-lei Fan, Ge Wang, Mengzhou Li, Rongjie Lai","submitted_at":"2021-10-12T15:33:32Z","abstract_excerpt":"Inspired by the diversity of biological neurons, quadratic artificial neurons can play an important role in deep learning models. The type of quadratic neurons of our interest replaces the inner-product operation in the conventional neuron with a quadratic function. Despite promising results so far achieved by networks of quadratic neurons, there are important issues not well addressed. Theoretically, the superior expressivity of a quadratic network over either a conventional network or a conventional network via quadratic activation is not fully elucidated, which makes the use of quadratic ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06081","kind":"arxiv","version":3},"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/2110.06081/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":"2110.06081","created_at":"2026-07-05T06:49:00.806745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06081v3","created_at":"2026-07-05T06:49:00.806745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06081","created_at":"2026-07-05T06:49:00.806745+00:00"},{"alias_kind":"pith_short_12","alias_value":"XACDQQPNYVZR","created_at":"2026-07-05T06:49:00.806745+00:00"},{"alias_kind":"pith_short_16","alias_value":"XACDQQPNYVZR3MAD","created_at":"2026-07-05T06:49:00.806745+00:00"},{"alias_kind":"pith_short_8","alias_value":"XACDQQPN","created_at":"2026-07-05T06:49:00.806745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11255","citing_title":"Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64","json":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64.json","graph_json":"https://pith.science/api/pith-number/XACDQQPNYVZR3MADPTFX5ZMR64/graph.json","events_json":"https://pith.science/api/pith-number/XACDQQPNYVZR3MADPTFX5ZMR64/events.json","paper":"https://pith.science/paper/XACDQQPN"},"agent_actions":{"view_html":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64","download_json":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64.json","view_paper":"https://pith.science/paper/XACDQQPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06081&json=true","fetch_graph":"https://pith.science/api/pith-number/XACDQQPNYVZR3MADPTFX5ZMR64/graph.json","fetch_events":"https://pith.science/api/pith-number/XACDQQPNYVZR3MADPTFX5ZMR64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64/action/storage_attestation","attest_author":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64/action/author_attestation","sign_citation":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64/action/citation_signature","submit_replication":"https://pith.science/pith/XACDQQPNYVZR3MADPTFX5ZMR64/action/replication_record"}},"created_at":"2026-07-05T06:49:00.806745+00:00","updated_at":"2026-07-05T06:49:00.806745+00:00"}