{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VJCQDWCMSPOEALCCMX7QVLIZ2R","short_pith_number":"pith:VJCQDWCM","schema_version":"1.0","canonical_sha256":"aa4501d84c93dc402c4265ff0aad19d4684a0bf54c024a87dc6bac319aa50904","source":{"kind":"arxiv","id":"2309.06015","version":1},"attestation_state":"computed","paper":{"title":"Interpolation, Approximation and Controllability of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","math.OC"],"primary_cat":"cs.LG","authors_text":"Jingpu Cheng, Qianxiao Li, Ting Lin, Zuowei Shen","submitted_at":"2023-09-12T07:29:47Z","abstract_excerpt":"We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that arise from supervised learning, namely universal interpolation - the ability to match arbitrary input and target training samples - and the closely related notion of universal approximation - the ability to approximate input-target functional relationships via flow maps. Under the assumption of affine invariance of the control family, we give a characterisation of universal interpolation, showing that it holds for e"},"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":"2309.06015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-12T07:29:47Z","cross_cats_sorted":["math.DS","math.OC"],"title_canon_sha256":"0abe699db958f974ca0b9030c8a54a6a54952e5f71aaa68e66000406dd16ba84","abstract_canon_sha256":"722d46232cd476fabd1302440d324e9cc64868f05bb61675e4b27012bca86d28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:50.002626Z","signature_b64":"+vshYkZ2QdHl8tlp35GSvmMYwFFg5C5CsXSaQJnqPvM2tvRhCY1VuHa4zr3n8BgHurXzeH5gMovqwV8hMg6RAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa4501d84c93dc402c4265ff0aad19d4684a0bf54c024a87dc6bac319aa50904","last_reissued_at":"2026-07-05T06:49:50.002231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:50.002231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpolation, Approximation and Controllability of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS","math.OC"],"primary_cat":"cs.LG","authors_text":"Jingpu Cheng, Qianxiao Li, Ting Lin, Zuowei Shen","submitted_at":"2023-09-12T07:29:47Z","abstract_excerpt":"We investigate the expressive power of deep residual neural networks idealized as continuous dynamical systems through control theory. Specifically, we consider two properties that arise from supervised learning, namely universal interpolation - the ability to match arbitrary input and target training samples - and the closely related notion of universal approximation - the ability to approximate input-target functional relationships via flow maps. Under the assumption of affine invariance of the control family, we give a characterisation of universal interpolation, showing that it holds for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06015","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/2309.06015/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":"2309.06015","created_at":"2026-07-05T06:49:50.002289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06015v1","created_at":"2026-07-05T06:49:50.002289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06015","created_at":"2026-07-05T06:49:50.002289+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJCQDWCMSPOE","created_at":"2026-07-05T06:49:50.002289+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJCQDWCMSPOEALCC","created_at":"2026-07-05T06:49:50.002289+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJCQDWCM","created_at":"2026-07-05T06:49:50.002289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19366","citing_title":"Constructive approximate transport maps with normalizing flows","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R","json":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R.json","graph_json":"https://pith.science/api/pith-number/VJCQDWCMSPOEALCCMX7QVLIZ2R/graph.json","events_json":"https://pith.science/api/pith-number/VJCQDWCMSPOEALCCMX7QVLIZ2R/events.json","paper":"https://pith.science/paper/VJCQDWCM"},"agent_actions":{"view_html":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R","download_json":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R.json","view_paper":"https://pith.science/paper/VJCQDWCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06015&json=true","fetch_graph":"https://pith.science/api/pith-number/VJCQDWCMSPOEALCCMX7QVLIZ2R/graph.json","fetch_events":"https://pith.science/api/pith-number/VJCQDWCMSPOEALCCMX7QVLIZ2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R/action/storage_attestation","attest_author":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R/action/author_attestation","sign_citation":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R/action/citation_signature","submit_replication":"https://pith.science/pith/VJCQDWCMSPOEALCCMX7QVLIZ2R/action/replication_record"}},"created_at":"2026-07-05T06:49:50.002289+00:00","updated_at":"2026-07-05T06:49:50.002289+00:00"}