{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QUAY5QWOIBP4O6GAN7DQ3BVW2D","short_pith_number":"pith:QUAY5QWO","schema_version":"1.0","canonical_sha256":"85018ec2ce405fc778c06fc70d86b6d0d1bb48fae217a4424d93bdbdaf8bf198","source":{"kind":"arxiv","id":"2501.15646","version":1},"attestation_state":"computed","paper":{"title":"Mathematical analysis of the gradients in deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Arnulf Jentzen, Frederic Weber, Steffen Dereich, Thang Do","submitted_at":"2025-01-26T19:11:57Z","abstract_excerpt":"Deep learning algorithms -- typically consisting of a class of deep artificial neural networks (ANNs) trained by a stochastic gradient descent (SGD) optimization method -- are nowadays an integral part in many areas of science, industry, and also our day to day life. Roughly speaking, in their most basic form, ANNs can be regarded as functions that consist of a series of compositions of affine-linear functions with multidimensional versions of so-called activation functions. One of the most popular of such activation functions is the rectified linear unit (ReLU) function $\\mathbb{R} \\ni x \\map"},"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":"2501.15646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-26T19:11:57Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"93fb18694cd73532fae9f0bfe8f16195da92cb170524b94f7e10fb4678992861","abstract_canon_sha256":"5fe52fcf38a37b6e836f5170cf5566e9d37329fe31841d341370b3623fe56eba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:32.372532Z","signature_b64":"tf8dhMI5GscKWqQjPbE66aa1DHbHK2PrFcl0oxrS7PvSZxMmdlLY/mE8frRPJis9EoIqERJBc+0sp1bWGGhrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85018ec2ce405fc778c06fc70d86b6d0d1bb48fae217a4424d93bdbdaf8bf198","last_reissued_at":"2026-07-05T10:05:32.372046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:32.372046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mathematical analysis of the gradients in deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Arnulf Jentzen, Frederic Weber, Steffen Dereich, Thang Do","submitted_at":"2025-01-26T19:11:57Z","abstract_excerpt":"Deep learning algorithms -- typically consisting of a class of deep artificial neural networks (ANNs) trained by a stochastic gradient descent (SGD) optimization method -- are nowadays an integral part in many areas of science, industry, and also our day to day life. Roughly speaking, in their most basic form, ANNs can be regarded as functions that consist of a series of compositions of affine-linear functions with multidimensional versions of so-called activation functions. One of the most popular of such activation functions is the rectified linear unit (ReLU) function $\\mathbb{R} \\ni x \\map"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15646","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/2501.15646/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":"2501.15646","created_at":"2026-07-05T10:05:32.372102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15646v1","created_at":"2026-07-05T10:05:32.372102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15646","created_at":"2026-07-05T10:05:32.372102+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUAY5QWOIBP4","created_at":"2026-07-05T10:05:32.372102+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUAY5QWOIBP4O6GA","created_at":"2026-07-05T10:05:32.372102+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUAY5QWO","created_at":"2026-07-05T10:05:32.372102+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/QUAY5QWOIBP4O6GAN7DQ3BVW2D","json":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D.json","graph_json":"https://pith.science/api/pith-number/QUAY5QWOIBP4O6GAN7DQ3BVW2D/graph.json","events_json":"https://pith.science/api/pith-number/QUAY5QWOIBP4O6GAN7DQ3BVW2D/events.json","paper":"https://pith.science/paper/QUAY5QWO"},"agent_actions":{"view_html":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D","download_json":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D.json","view_paper":"https://pith.science/paper/QUAY5QWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15646&json=true","fetch_graph":"https://pith.science/api/pith-number/QUAY5QWOIBP4O6GAN7DQ3BVW2D/graph.json","fetch_events":"https://pith.science/api/pith-number/QUAY5QWOIBP4O6GAN7DQ3BVW2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D/action/storage_attestation","attest_author":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D/action/author_attestation","sign_citation":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D/action/citation_signature","submit_replication":"https://pith.science/pith/QUAY5QWOIBP4O6GAN7DQ3BVW2D/action/replication_record"}},"created_at":"2026-07-05T10:05:32.372102+00:00","updated_at":"2026-07-05T10:05:32.372102+00:00"}