{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MQ5DYJBFMTGQG33L4HKGU4PAXX","short_pith_number":"pith:MQ5DYJBF","schema_version":"1.0","canonical_sha256":"643a3c242564cd036f6be1d46a71e0bdd37b0d6b719c805a3c11b25296cc79e7","source":{"kind":"arxiv","id":"2605.29013","version":1},"attestation_state":"computed","paper":{"title":"Local Observability and Moving Horizon Estimation-based Training of Feedforward Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Matthias A. M\\\"uller, Victor G. Lopez, Yi Yang","submitted_at":"2026-05-27T19:10:45Z","abstract_excerpt":"In this paper, we propose a moving horizon estimation (MHE)-based training method for feedforward neural networks (FNNs) with rectified linear unit (ReLU) activation functions to determine their ideal weights from a control-theoretic perspective. This allows for a rigorous theoretical analysis of the trained network. First, we reformulate the FNN as a dynamical system with the weights as states. Then, we investigate the local observability of such a system. For two-layer FNNs with fixed output weights, we derive a sufficient condition under which the observability rank condition holds, ensurin"},"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":"2605.29013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2026-05-27T19:10:45Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"8d3fe788f2c939a954e595794004507f108b9873bc161cc63e588917b2ef66d0","abstract_canon_sha256":"0ce4d73608d135704b3369ac4e23aeea1ec197b2198fe150f2829c9299407fee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:43.441929Z","signature_b64":"dPyOG3b8dhF0D4xxsx8jr1cfKo2UZLD3EzOmYP2IxS4HLhiRScRUb2GB/0zchHeckQsx8v102y73z8ugCy6jDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"643a3c242564cd036f6be1d46a71e0bdd37b0d6b719c805a3c11b25296cc79e7","last_reissued_at":"2026-05-29T01:04:43.441526Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:43.441526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Observability and Moving Horizon Estimation-based Training of Feedforward Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Matthias A. M\\\"uller, Victor G. Lopez, Yi Yang","submitted_at":"2026-05-27T19:10:45Z","abstract_excerpt":"In this paper, we propose a moving horizon estimation (MHE)-based training method for feedforward neural networks (FNNs) with rectified linear unit (ReLU) activation functions to determine their ideal weights from a control-theoretic perspective. This allows for a rigorous theoretical analysis of the trained network. First, we reformulate the FNN as a dynamical system with the weights as states. Then, we investigate the local observability of such a system. For two-layer FNNs with fixed output weights, we derive a sufficient condition under which the observability rank condition holds, ensurin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29013","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/2605.29013/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":"2605.29013","created_at":"2026-05-29T01:04:43.441584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29013v1","created_at":"2026-05-29T01:04:43.441584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29013","created_at":"2026-05-29T01:04:43.441584+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQ5DYJBFMTGQ","created_at":"2026-05-29T01:04:43.441584+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQ5DYJBFMTGQG33L","created_at":"2026-05-29T01:04:43.441584+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQ5DYJBF","created_at":"2026-05-29T01:04:43.441584+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/MQ5DYJBFMTGQG33L4HKGU4PAXX","json":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX.json","graph_json":"https://pith.science/api/pith-number/MQ5DYJBFMTGQG33L4HKGU4PAXX/graph.json","events_json":"https://pith.science/api/pith-number/MQ5DYJBFMTGQG33L4HKGU4PAXX/events.json","paper":"https://pith.science/paper/MQ5DYJBF"},"agent_actions":{"view_html":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX","download_json":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX.json","view_paper":"https://pith.science/paper/MQ5DYJBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29013&json=true","fetch_graph":"https://pith.science/api/pith-number/MQ5DYJBFMTGQG33L4HKGU4PAXX/graph.json","fetch_events":"https://pith.science/api/pith-number/MQ5DYJBFMTGQG33L4HKGU4PAXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX/action/storage_attestation","attest_author":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX/action/author_attestation","sign_citation":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX/action/citation_signature","submit_replication":"https://pith.science/pith/MQ5DYJBFMTGQG33L4HKGU4PAXX/action/replication_record"}},"created_at":"2026-05-29T01:04:43.441584+00:00","updated_at":"2026-05-29T01:04:43.441584+00:00"}