{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UHE7NE4JQ52347DVETXNDK6QR7","short_pith_number":"pith:UHE7NE4J","schema_version":"1.0","canonical_sha256":"a1c9f693898775be7c7524eed1abd08fe69b4acf6643063c047d6f108bc150ed","source":{"kind":"arxiv","id":"2507.05164","version":2},"attestation_state":"computed","paper":{"title":"A Dynamical Systems Perspective on the Analysis of Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","nlin.AO"],"primary_cat":"math.DS","authors_text":"Christian Kuehn, Dennis Chemnitz, Maximilian Engel, Sara-Viola Kuntz","submitted_at":"2025-07-07T16:18:49Z","abstract_excerpt":"In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms. As an expository contribution we demonstrate how to re-formulate a wide variety of challenges from deep neural networks, (stochastic) gradient descent, and related topics into dynamical statements. We also tackle three concrete challenges. First, we consider the process of information propagation through a neural network, i.e., we study the input-output map for different architectures. We explain the universal embedding property for augmented neural ODEs representing arbitrary functions of "},"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":"2507.05164","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.DS","submitted_at":"2025-07-07T16:18:49Z","cross_cats_sorted":["cs.LG","nlin.AO"],"title_canon_sha256":"889725354f5bf2c708a830acd7667ff110dc372154a2a5d682a20a372bb2b1ef","abstract_canon_sha256":"0e04ac6d88bcd34170b672c043fe16ac08c4d7a19794f79d04e103f2df9108f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:09:49.971882Z","signature_b64":"4VQ6Ig3s4y4YQnKQ38dbzlBWOboKxGvhS0J/ctylz3aO65RZzPd6peqm0B9lf96p2DkA8KIBb+yyuilipSfBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1c9f693898775be7c7524eed1abd08fe69b4acf6643063c047d6f108bc150ed","last_reissued_at":"2026-06-19T16:09:49.971464Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:09:49.971464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dynamical Systems Perspective on the Analysis of Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","nlin.AO"],"primary_cat":"math.DS","authors_text":"Christian Kuehn, Dennis Chemnitz, Maximilian Engel, Sara-Viola Kuntz","submitted_at":"2025-07-07T16:18:49Z","abstract_excerpt":"In this chapter, we utilize dynamical systems to analyze several aspects of machine learning algorithms. As an expository contribution we demonstrate how to re-formulate a wide variety of challenges from deep neural networks, (stochastic) gradient descent, and related topics into dynamical statements. We also tackle three concrete challenges. First, we consider the process of information propagation through a neural network, i.e., we study the input-output map for different architectures. We explain the universal embedding property for augmented neural ODEs representing arbitrary functions of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05164","kind":"arxiv","version":2},"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/2507.05164/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":"2507.05164","created_at":"2026-06-19T16:09:49.971521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05164v2","created_at":"2026-06-19T16:09:49.971521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05164","created_at":"2026-06-19T16:09:49.971521+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHE7NE4JQ523","created_at":"2026-06-19T16:09:49.971521+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHE7NE4JQ52347DV","created_at":"2026-06-19T16:09:49.971521+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHE7NE4J","created_at":"2026-06-19T16:09:49.971521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.26085","citing_title":"Spectral Selection in Symmetric Self-Attention Dynamics","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7","json":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7.json","graph_json":"https://pith.science/api/pith-number/UHE7NE4JQ52347DVETXNDK6QR7/graph.json","events_json":"https://pith.science/api/pith-number/UHE7NE4JQ52347DVETXNDK6QR7/events.json","paper":"https://pith.science/paper/UHE7NE4J"},"agent_actions":{"view_html":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7","download_json":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7.json","view_paper":"https://pith.science/paper/UHE7NE4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05164&json=true","fetch_graph":"https://pith.science/api/pith-number/UHE7NE4JQ52347DVETXNDK6QR7/graph.json","fetch_events":"https://pith.science/api/pith-number/UHE7NE4JQ52347DVETXNDK6QR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7/action/storage_attestation","attest_author":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7/action/author_attestation","sign_citation":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7/action/citation_signature","submit_replication":"https://pith.science/pith/UHE7NE4JQ52347DVETXNDK6QR7/action/replication_record"}},"created_at":"2026-06-19T16:09:49.971521+00:00","updated_at":"2026-06-19T16:09:49.971521+00:00"}