{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZWRBBPI5SYP3GLKKUFCXD3NGEY","short_pith_number":"pith:ZWRBBPI5","schema_version":"1.0","canonical_sha256":"cda210bd1d961fb32d4aa14571eda62624937786ed4a44dd219cf244319f6fa8","source":{"kind":"arxiv","id":"2411.09004","version":1},"attestation_state":"computed","paper":{"title":"The geometry of the deep linear network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.DS","math.PR","nlin.AO"],"primary_cat":"cs.NE","authors_text":"Govind Menon","submitted_at":"2024-11-13T20:15:50Z","abstract_excerpt":"This article provides an expository account of training dynamics in the Deep Linear Network (DLN) from the perspective of the geometric theory of dynamical systems. Rigorous results by several authors are unified into a thermodynamic framework for deep learning.\n  The analysis begins with a characterization of the invariant manifolds and Riemannian geometry in the DLN. This is followed by exact formulas for a Boltzmann entropy, as well as stochastic gradient descent of free energy using a Riemannian Langevin Equation. Several links between the DLN and other areas of mathematics are discussed, "},"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":"2411.09004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-11-13T20:15:50Z","cross_cats_sorted":["math.DS","math.PR","nlin.AO"],"title_canon_sha256":"fcd9e49d1906576c6fb3d0d175d49650f1c355644c0dafd5f9ffef27fa081484","abstract_canon_sha256":"024c77fc59feae948b95812dff65a322dc9059ca228734d2fd26bbbde0f245ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:18.286764Z","signature_b64":"YAy2CV/JdR+UGYThE17wm0soZOfEm9vEM83C+lDJbTrecqGfMpsjhMyI/QUvAmzSju8cu6vK2qSXBIqLseWiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cda210bd1d961fb32d4aa14571eda62624937786ed4a44dd219cf244319f6fa8","last_reissued_at":"2026-07-05T09:35:18.286339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:18.286339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The geometry of the deep linear network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.DS","math.PR","nlin.AO"],"primary_cat":"cs.NE","authors_text":"Govind Menon","submitted_at":"2024-11-13T20:15:50Z","abstract_excerpt":"This article provides an expository account of training dynamics in the Deep Linear Network (DLN) from the perspective of the geometric theory of dynamical systems. Rigorous results by several authors are unified into a thermodynamic framework for deep learning.\n  The analysis begins with a characterization of the invariant manifolds and Riemannian geometry in the DLN. This is followed by exact formulas for a Boltzmann entropy, as well as stochastic gradient descent of free energy using a Riemannian Langevin Equation. Several links between the DLN and other areas of mathematics are discussed, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09004","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/2411.09004/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":"2411.09004","created_at":"2026-07-05T09:35:18.286401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09004v1","created_at":"2026-07-05T09:35:18.286401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09004","created_at":"2026-07-05T09:35:18.286401+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWRBBPI5SYP3","created_at":"2026-07-05T09:35:18.286401+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWRBBPI5SYP3GLKK","created_at":"2026-07-05T09:35:18.286401+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWRBBPI5","created_at":"2026-07-05T09:35:18.286401+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19268","citing_title":"Patnaik-Pearson intrinsic dimension for internal representations of neural networks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19268","citing_title":"Patnaik-Pearson intrinsic dimension for internal representations of neural networks","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13453","citing_title":"Rapid mixing for Gibbs measures in Riemannian manifolds","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.07324","citing_title":"Geodesics in the Deep Linear Network","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY","json":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY.json","graph_json":"https://pith.science/api/pith-number/ZWRBBPI5SYP3GLKKUFCXD3NGEY/graph.json","events_json":"https://pith.science/api/pith-number/ZWRBBPI5SYP3GLKKUFCXD3NGEY/events.json","paper":"https://pith.science/paper/ZWRBBPI5"},"agent_actions":{"view_html":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY","download_json":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY.json","view_paper":"https://pith.science/paper/ZWRBBPI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09004&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWRBBPI5SYP3GLKKUFCXD3NGEY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWRBBPI5SYP3GLKKUFCXD3NGEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY/action/storage_attestation","attest_author":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY/action/author_attestation","sign_citation":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY/action/citation_signature","submit_replication":"https://pith.science/pith/ZWRBBPI5SYP3GLKKUFCXD3NGEY/action/replication_record"}},"created_at":"2026-07-05T09:35:18.286401+00:00","updated_at":"2026-07-05T09:35:18.286401+00:00"}