{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4AS2ZKMOYSXQNPV7YB34JPDMRG","short_pith_number":"pith:4AS2ZKMO","schema_version":"1.0","canonical_sha256":"e025aca98ec4af06bebfc077c4bc6c898facda784a249858c50a7ed67961ffe3","source":{"kind":"arxiv","id":"2607.07637","version":1},"attestation_state":"computed","paper":{"title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"C G Krishnanunni, Tan Bui-Thanh, Thomas Scott","submitted_at":"2026-07-08T16:55:16Z","abstract_excerpt":"This work presents a novel approach for adapting neural network architecture along the depth based on a posteriori error estimation. By formulating neural network training as a continuous-time optimal control problem, we derive rigorous error estimates that quantify how approximation error distributes across network layers. This error decomposition enables a principled depth adaptation strategy: new layers are inserted at locations of maximum estimated error, allowing the network to efficiently capture complex, nonlinear variations in the underlying problem. Our framework introduces a novel 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":"2607.07637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T16:55:16Z","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"title_canon_sha256":"43a70e7b1ff9e03a87ce005bad5e46b7e643f5010e0f4877847c9af8e15feed7","abstract_canon_sha256":"35119e717249990fe4052de2b8bf831c40d3fa67fc7ec1a859530abc6c3d7d9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:37.632446Z","signature_b64":"IceCxUUbi1U1XOZyxQ+SAsI++6xAJxyHDlHALUVzMT6LpS3jgf3FX+NLoFnfYBCvZ9fhte12V6rXQ5spDf1fAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e025aca98ec4af06bebfc077c4bc6c898facda784a249858c50a7ed67961ffe3","last_reissued_at":"2026-07-09T01:20:37.632001Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:37.632001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An optimal control approach for neural network architecture adaptation with a posteriori error estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"C G Krishnanunni, Tan Bui-Thanh, Thomas Scott","submitted_at":"2026-07-08T16:55:16Z","abstract_excerpt":"This work presents a novel approach for adapting neural network architecture along the depth based on a posteriori error estimation. By formulating neural network training as a continuous-time optimal control problem, we derive rigorous error estimates that quantify how approximation error distributes across network layers. This error decomposition enables a principled depth adaptation strategy: new layers are inserted at locations of maximum estimated error, allowing the network to efficiently capture complex, nonlinear variations in the underlying problem. Our framework introduces a novel ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07637","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/2607.07637/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":"2607.07637","created_at":"2026-07-09T01:20:37.632057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07637v1","created_at":"2026-07-09T01:20:37.632057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07637","created_at":"2026-07-09T01:20:37.632057+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AS2ZKMOYSXQ","created_at":"2026-07-09T01:20:37.632057+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AS2ZKMOYSXQNPV7","created_at":"2026-07-09T01:20:37.632057+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AS2ZKMO","created_at":"2026-07-09T01:20:37.632057+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/4AS2ZKMOYSXQNPV7YB34JPDMRG","json":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG.json","graph_json":"https://pith.science/api/pith-number/4AS2ZKMOYSXQNPV7YB34JPDMRG/graph.json","events_json":"https://pith.science/api/pith-number/4AS2ZKMOYSXQNPV7YB34JPDMRG/events.json","paper":"https://pith.science/paper/4AS2ZKMO"},"agent_actions":{"view_html":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG","download_json":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG.json","view_paper":"https://pith.science/paper/4AS2ZKMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07637&json=true","fetch_graph":"https://pith.science/api/pith-number/4AS2ZKMOYSXQNPV7YB34JPDMRG/graph.json","fetch_events":"https://pith.science/api/pith-number/4AS2ZKMOYSXQNPV7YB34JPDMRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG/action/storage_attestation","attest_author":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG/action/author_attestation","sign_citation":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG/action/citation_signature","submit_replication":"https://pith.science/pith/4AS2ZKMOYSXQNPV7YB34JPDMRG/action/replication_record"}},"created_at":"2026-07-09T01:20:37.632057+00:00","updated_at":"2026-07-09T01:20:37.632057+00:00"}