{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AC4FRKG4N7KGK5AYZP6GG4RD2U","short_pith_number":"pith:AC4FRKG4","schema_version":"1.0","canonical_sha256":"00b858a8dc6fd4657418cbfc637223d52e30f6cc2a1a8efa83744bfd577b1919","source":{"kind":"arxiv","id":"2512.11587","version":2},"attestation_state":"computed","paper":{"title":"Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Alexander Tyurin","submitted_at":"2025-12-12T14:16:35Z","abstract_excerpt":"Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function value oscillations, and especially its implicit acceleration, remains a challenging problem. We analyze nonlinear models with the logistic loss and show that the steps of GD reduce to those of generalized perceptron algorithms (Rosenblatt, 1958), providing a new perspective on the dynamics. This reduction yields significantly simpler algorithmic steps, which we analyze using classical linear algebra tools. Using these "},"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":"2512.11587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-12T14:16:35Z","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"title_canon_sha256":"c0ff70bc7d128aab7f49e611ec5c2ef95ff926ad5952f9ebb0fa9e5c21eaafe3","abstract_canon_sha256":"45588a8731113b1431860e66437af001b435100852be188c8315b31069870a2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:52.125640Z","signature_b64":"YlBU8wv00xCmpxyvM/dAB3BYTv0mqKfdL0NPcu8To9MZThTaQctvl5cl7GIGZMJ3IGpT7DOeMUb4+EZZOicQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00b858a8dc6fd4657418cbfc637223d52e30f6cc2a1a8efa83744bfd577b1919","last_reissued_at":"2026-05-22T01:03:52.124528Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:52.124528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC"],"primary_cat":"cs.LG","authors_text":"Alexander Tyurin","submitted_at":"2025-12-12T14:16:35Z","abstract_excerpt":"Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function value oscillations, and especially its implicit acceleration, remains a challenging problem. We analyze nonlinear models with the logistic loss and show that the steps of GD reduce to those of generalized perceptron algorithms (Rosenblatt, 1958), providing a new perspective on the dynamics. This reduction yields significantly simpler algorithmic steps, which we analyze using classical linear algebra tools. Using these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11587","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/2512.11587/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":"2512.11587","created_at":"2026-05-22T01:03:52.124663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.11587v2","created_at":"2026-05-22T01:03:52.124663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11587","created_at":"2026-05-22T01:03:52.124663+00:00"},{"alias_kind":"pith_short_12","alias_value":"AC4FRKG4N7KG","created_at":"2026-05-22T01:03:52.124663+00:00"},{"alias_kind":"pith_short_16","alias_value":"AC4FRKG4N7KGK5AY","created_at":"2026-05-22T01:03:52.124663+00:00"},{"alias_kind":"pith_short_8","alias_value":"AC4FRKG4","created_at":"2026-05-22T01:03:52.124663+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/AC4FRKG4N7KGK5AYZP6GG4RD2U","json":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U.json","graph_json":"https://pith.science/api/pith-number/AC4FRKG4N7KGK5AYZP6GG4RD2U/graph.json","events_json":"https://pith.science/api/pith-number/AC4FRKG4N7KGK5AYZP6GG4RD2U/events.json","paper":"https://pith.science/paper/AC4FRKG4"},"agent_actions":{"view_html":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U","download_json":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U.json","view_paper":"https://pith.science/paper/AC4FRKG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.11587&json=true","fetch_graph":"https://pith.science/api/pith-number/AC4FRKG4N7KGK5AYZP6GG4RD2U/graph.json","fetch_events":"https://pith.science/api/pith-number/AC4FRKG4N7KGK5AYZP6GG4RD2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U/action/storage_attestation","attest_author":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U/action/author_attestation","sign_citation":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U/action/citation_signature","submit_replication":"https://pith.science/pith/AC4FRKG4N7KGK5AYZP6GG4RD2U/action/replication_record"}},"created_at":"2026-05-22T01:03:52.124663+00:00","updated_at":"2026-05-22T01:03:52.124663+00:00"}