{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K4KXYQM3SSL6OR22ZX7RQUUA2F","short_pith_number":"pith:K4KXYQM3","schema_version":"1.0","canonical_sha256":"57157c419b9497e7475acdff185280d15a0bf1475ea7467ac6043158a92f2762","source":{"kind":"arxiv","id":"2509.09088","version":3},"attestation_state":"computed","paper":{"title":"An entropy formula for the Deep Linear Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DG","math.DS"],"primary_cat":"cs.LG","authors_text":"Govind Menon, Tianmin Yu","submitted_at":"2025-09-11T01:40:46Z","abstract_excerpt":"We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main tools are the use of group actions to analyze overparametrization and the use of Riemannian submersion from the space of parameters to the space of observables. The foliation of the balanced manifold in the parameter space by group orbits is used to define and compute a Boltzmann entropy. We also show that the Riemannian geometry on the space of observables defined in [2] is obtained by Riemannian submersion of the balanced manifold. The main techn"},"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":"2509.09088","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-11T01:40:46Z","cross_cats_sorted":["math.DG","math.DS"],"title_canon_sha256":"56ef74985779b9345f8e247ab89dec7df6d35634b672842a22ceb67ca0402bda","abstract_canon_sha256":"0c43c607c44a215cd75bcada54f2f08d67bb8631d7fc08f8c61f4e011e1c3e27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:15.472260Z","signature_b64":"36i1cRBitERmdqIHh572I6NG/Y6Yews6/JXTo17khneXW0Tt35fU7dL+QbMhc0g1yB2ei9s4Sju8W/pXqY+wDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57157c419b9497e7475acdff185280d15a0bf1475ea7467ac6043158a92f2762","last_reissued_at":"2026-05-22T01:03:15.471375Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:15.471375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An entropy formula for the Deep Linear Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DG","math.DS"],"primary_cat":"cs.LG","authors_text":"Govind Menon, Tianmin Yu","submitted_at":"2025-09-11T01:40:46Z","abstract_excerpt":"We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main tools are the use of group actions to analyze overparametrization and the use of Riemannian submersion from the space of parameters to the space of observables. The foliation of the balanced manifold in the parameter space by group orbits is used to define and compute a Boltzmann entropy. We also show that the Riemannian geometry on the space of observables defined in [2] is obtained by Riemannian submersion of the balanced manifold. The main techn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09088","kind":"arxiv","version":3},"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/2509.09088/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":"2509.09088","created_at":"2026-05-22T01:03:15.471475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09088v3","created_at":"2026-05-22T01:03:15.471475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09088","created_at":"2026-05-22T01:03:15.471475+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4KXYQM3SSL6","created_at":"2026-05-22T01:03:15.471475+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4KXYQM3SSL6OR22","created_at":"2026-05-22T01:03:15.471475+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4KXYQM3","created_at":"2026-05-22T01:03:15.471475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.02108","citing_title":"Geometric and Spectral Alignment for Deep Neural Network I","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F","json":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F.json","graph_json":"https://pith.science/api/pith-number/K4KXYQM3SSL6OR22ZX7RQUUA2F/graph.json","events_json":"https://pith.science/api/pith-number/K4KXYQM3SSL6OR22ZX7RQUUA2F/events.json","paper":"https://pith.science/paper/K4KXYQM3"},"agent_actions":{"view_html":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F","download_json":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F.json","view_paper":"https://pith.science/paper/K4KXYQM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09088&json=true","fetch_graph":"https://pith.science/api/pith-number/K4KXYQM3SSL6OR22ZX7RQUUA2F/graph.json","fetch_events":"https://pith.science/api/pith-number/K4KXYQM3SSL6OR22ZX7RQUUA2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F/action/storage_attestation","attest_author":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F/action/author_attestation","sign_citation":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F/action/citation_signature","submit_replication":"https://pith.science/pith/K4KXYQM3SSL6OR22ZX7RQUUA2F/action/replication_record"}},"created_at":"2026-05-22T01:03:15.471475+00:00","updated_at":"2026-05-22T01:03:15.471475+00:00"}