{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:35EC4HEMFVYDLVLGFRVDWV34IO","short_pith_number":"pith:35EC4HEM","schema_version":"1.0","canonical_sha256":"df482e1c8c2d7035d5662c6a3b577c4386f54bb49f895b6ca29b71a06a343a39","source":{"kind":"arxiv","id":"2311.12253","version":1},"attestation_state":"computed","paper":{"title":"The limitation of neural nets for approximation and optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Luis Nunes Vicente, Oumaima Sohab, Tommaso Giovannelli","submitted_at":"2023-11-21T00:21:15Z","abstract_excerpt":"We are interested in assessing the use of neural networks as surrogate models to approximate and minimize objective functions in optimization problems. While neural networks are widely used for machine learning tasks such as classification and regression, their application in solving optimization problems has been limited. Our study begins by determining the best activation function for approximating the objective functions of popular nonlinear optimization test problems, and the evidence provided shows that~SiLU has the best performance. We then analyze the accuracy of function value, gradien"},"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":"2311.12253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-21T00:21:15Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"f9ce5cf5708547bdb056cd39bb76a1b9e2e5cfdd8e99adf4f9c4ee4040c3340d","abstract_canon_sha256":"3715436d149308bcd07adb45e8fd18d6958eab205a0724bc284ba5bf7a5f1a6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:02.687377Z","signature_b64":"63rH/N+Rwt6ipTzEptC0rOTcSsEl97X1Pc58tuhQeDimhxQ5HByjgEizIvp5xFFJhJKhDb1Eo0A5S3ozcJO0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df482e1c8c2d7035d5662c6a3b577c4386f54bb49f895b6ca29b71a06a343a39","last_reissued_at":"2026-07-05T07:15:02.686788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:02.686788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The limitation of neural nets for approximation and optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Luis Nunes Vicente, Oumaima Sohab, Tommaso Giovannelli","submitted_at":"2023-11-21T00:21:15Z","abstract_excerpt":"We are interested in assessing the use of neural networks as surrogate models to approximate and minimize objective functions in optimization problems. While neural networks are widely used for machine learning tasks such as classification and regression, their application in solving optimization problems has been limited. Our study begins by determining the best activation function for approximating the objective functions of popular nonlinear optimization test problems, and the evidence provided shows that~SiLU has the best performance. We then analyze the accuracy of function value, gradien"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12253","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/2311.12253/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":"2311.12253","created_at":"2026-07-05T07:15:02.686873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12253v1","created_at":"2026-07-05T07:15:02.686873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12253","created_at":"2026-07-05T07:15:02.686873+00:00"},{"alias_kind":"pith_short_12","alias_value":"35EC4HEMFVYD","created_at":"2026-07-05T07:15:02.686873+00:00"},{"alias_kind":"pith_short_16","alias_value":"35EC4HEMFVYDLVLG","created_at":"2026-07-05T07:15:02.686873+00:00"},{"alias_kind":"pith_short_8","alias_value":"35EC4HEM","created_at":"2026-07-05T07:15:02.686873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07435","citing_title":"Enhancing finite-difference based derivative-free optimization methods with machine learning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO","json":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO.json","graph_json":"https://pith.science/api/pith-number/35EC4HEMFVYDLVLGFRVDWV34IO/graph.json","events_json":"https://pith.science/api/pith-number/35EC4HEMFVYDLVLGFRVDWV34IO/events.json","paper":"https://pith.science/paper/35EC4HEM"},"agent_actions":{"view_html":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO","download_json":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO.json","view_paper":"https://pith.science/paper/35EC4HEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12253&json=true","fetch_graph":"https://pith.science/api/pith-number/35EC4HEMFVYDLVLGFRVDWV34IO/graph.json","fetch_events":"https://pith.science/api/pith-number/35EC4HEMFVYDLVLGFRVDWV34IO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO/action/storage_attestation","attest_author":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO/action/author_attestation","sign_citation":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO/action/citation_signature","submit_replication":"https://pith.science/pith/35EC4HEMFVYDLVLGFRVDWV34IO/action/replication_record"}},"created_at":"2026-07-05T07:15:02.686873+00:00","updated_at":"2026-07-05T07:15:02.686873+00:00"}