{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UJR6Y5XNPTEL3TM4YWUXUV2B5T","short_pith_number":"pith:UJR6Y5XN","schema_version":"1.0","canonical_sha256":"a263ec76ed7cc8bdcd9cc5a97a5741ecfba4784c1fc3b3b06c17b7794a7af277","source":{"kind":"arxiv","id":"2307.08934","version":1},"attestation_state":"computed","paper":{"title":"Multi-stage Neural Networks: Function Approximator of Machine Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Ching-Yao Lai, Yongji Wang","submitted_at":"2023-07-18T02:47:32Z","abstract_excerpt":"Deep learning techniques are increasingly applied to scientific problems, where the precision of networks is crucial. Despite being deemed as universal function approximators, neural networks, in practice, struggle to reduce the prediction errors below $O(10^{-5})$ even with large network size and extended training iterations. To address this issue, we developed the multi-stage neural networks that divides the training process into different stages, with each stage using a new network that is optimized to fit the residue from the previous stage. Across successive stages, the residue magnitudes"},"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":"2307.08934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-18T02:47:32Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"d06de12ff93bcd724953af5657f6b9774d44f77592134c02bf6c0cd10b7b8815","abstract_canon_sha256":"8227524d3bc141c9172ede9616827ae37b429ba1f84b81410fa1a7bc99dae574"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:36.251807Z","signature_b64":"q6YMfh2Yut1ER6svW9PAr3BJ5SmhLconFwhHBoiZffhmCk5Y8CeO4f7ADUUSycSppRnieeXb7L6HgFTPb+z2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a263ec76ed7cc8bdcd9cc5a97a5741ecfba4784c1fc3b3b06c17b7794a7af277","last_reissued_at":"2026-07-05T06:31:36.251300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:36.251300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-stage Neural Networks: Function Approximator of Machine Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Ching-Yao Lai, Yongji Wang","submitted_at":"2023-07-18T02:47:32Z","abstract_excerpt":"Deep learning techniques are increasingly applied to scientific problems, where the precision of networks is crucial. Despite being deemed as universal function approximators, neural networks, in practice, struggle to reduce the prediction errors below $O(10^{-5})$ even with large network size and extended training iterations. To address this issue, we developed the multi-stage neural networks that divides the training process into different stages, with each stage using a new network that is optimized to fit the residue from the previous stage. Across successive stages, the residue magnitudes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08934","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/2307.08934/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":"2307.08934","created_at":"2026-07-05T06:31:36.251360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08934v1","created_at":"2026-07-05T06:31:36.251360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08934","created_at":"2026-07-05T06:31:36.251360+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJR6Y5XNPTEL","created_at":"2026-07-05T06:31:36.251360+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJR6Y5XNPTEL3TM4","created_at":"2026-07-05T06:31:36.251360+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJR6Y5XN","created_at":"2026-07-05T06:31:36.251360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.25781","citing_title":"A Practitioner's Guide to Kolmogorov-Arnold Networks","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T","json":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T.json","graph_json":"https://pith.science/api/pith-number/UJR6Y5XNPTEL3TM4YWUXUV2B5T/graph.json","events_json":"https://pith.science/api/pith-number/UJR6Y5XNPTEL3TM4YWUXUV2B5T/events.json","paper":"https://pith.science/paper/UJR6Y5XN"},"agent_actions":{"view_html":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T","download_json":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T.json","view_paper":"https://pith.science/paper/UJR6Y5XN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08934&json=true","fetch_graph":"https://pith.science/api/pith-number/UJR6Y5XNPTEL3TM4YWUXUV2B5T/graph.json","fetch_events":"https://pith.science/api/pith-number/UJR6Y5XNPTEL3TM4YWUXUV2B5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T/action/storage_attestation","attest_author":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T/action/author_attestation","sign_citation":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T/action/citation_signature","submit_replication":"https://pith.science/pith/UJR6Y5XNPTEL3TM4YWUXUV2B5T/action/replication_record"}},"created_at":"2026-07-05T06:31:36.251360+00:00","updated_at":"2026-07-05T06:31:36.251360+00:00"}