{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:B4CNZMLS32VHATHMH4RLRAWLDA","short_pith_number":"pith:B4CNZMLS","schema_version":"1.0","canonical_sha256":"0f04dcb172deaa704cec3f22b882cb182d08805c94bd2c5d13fcae6faab0aa24","source":{"kind":"arxiv","id":"1802.03646","version":4},"attestation_state":"computed","paper":{"title":"On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jinglan Liu, Jinjun Xiong, Yiyu Shi, Yukun Ding","submitted_at":"2018-02-10T19:43:42Z","abstract_excerpt":"Compression is a key step to deploy large neural networks on resource-constrained platforms. As a popular compression technique, quantization constrains the number of distinct weight values and thus reducing the number of bits required to represent and store each weight. In this paper, we study the representation power of quantized neural networks. First, we prove the universal approximability of quantized ReLU networks on a wide class of functions. Then we provide upper bounds on the number of weights and the memory size for a given approximation error bound and the bit-width of weights for f"},"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":"1802.03646","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-10T19:43:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a5abf6386631ad1ff9c4fa2f70aa40dbeb2c127ade6c2ee20b580fa80c984da4","abstract_canon_sha256":"5d49117226c65c9e224d62810c677ea835819e0aaab0871cff9a9a5cc07609e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:30.007235Z","signature_b64":"EJUdpkxot72wXAhEslixrFWURERYHEll2R5mo6lQJNlT+b1LjGvCpvIc53Y+q3O3/T39zmMEvddrLzqHYPgOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f04dcb172deaa704cec3f22b882cb182d08805c94bd2c5d13fcae6faab0aa24","last_reissued_at":"2026-05-17T23:56:30.006852Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:30.006852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jinglan Liu, Jinjun Xiong, Yiyu Shi, Yukun Ding","submitted_at":"2018-02-10T19:43:42Z","abstract_excerpt":"Compression is a key step to deploy large neural networks on resource-constrained platforms. As a popular compression technique, quantization constrains the number of distinct weight values and thus reducing the number of bits required to represent and store each weight. In this paper, we study the representation power of quantized neural networks. First, we prove the universal approximability of quantized ReLU networks on a wide class of functions. Then we provide upper bounds on the number of weights and the memory size for a given approximation error bound and the bit-width of weights for f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03646","kind":"arxiv","version":4},"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":"1802.03646","created_at":"2026-05-17T23:56:30.006910+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03646v4","created_at":"2026-05-17T23:56:30.006910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03646","created_at":"2026-05-17T23:56:30.006910+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4CNZMLS32VH","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4CNZMLS32VHATHM","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4CNZMLS","created_at":"2026-05-18T12:32:13.499390+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/B4CNZMLS32VHATHMH4RLRAWLDA","json":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA.json","graph_json":"https://pith.science/api/pith-number/B4CNZMLS32VHATHMH4RLRAWLDA/graph.json","events_json":"https://pith.science/api/pith-number/B4CNZMLS32VHATHMH4RLRAWLDA/events.json","paper":"https://pith.science/paper/B4CNZMLS"},"agent_actions":{"view_html":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA","download_json":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA.json","view_paper":"https://pith.science/paper/B4CNZMLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03646&json=true","fetch_graph":"https://pith.science/api/pith-number/B4CNZMLS32VHATHMH4RLRAWLDA/graph.json","fetch_events":"https://pith.science/api/pith-number/B4CNZMLS32VHATHMH4RLRAWLDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA/action/storage_attestation","attest_author":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA/action/author_attestation","sign_citation":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA/action/citation_signature","submit_replication":"https://pith.science/pith/B4CNZMLS32VHATHMH4RLRAWLDA/action/replication_record"}},"created_at":"2026-05-17T23:56:30.006910+00:00","updated_at":"2026-05-17T23:56:30.006910+00:00"}