{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LF6ZQ6XVCMLVE6LVO3AL4FRT6D","short_pith_number":"pith:LF6ZQ6XV","schema_version":"1.0","canonical_sha256":"597d987af5131752797576c0be1633f0fd0cc435ea027b06770619b18eff3dee","source":{"kind":"arxiv","id":"2501.12747","version":2},"attestation_state":"computed","paper":{"title":"Singular leaning coefficients and efficiency in learning theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Miki Aoyagi","submitted_at":"2025-01-22T09:31:02Z","abstract_excerpt":"Singular learning models with non-positive Fisher information matrices include neural networks, reduced-rank regression, Boltzmann machines, normal mixture models, and others. These models have been widely used in the development of learning machines. However, theoretical analysis is still in its early stages. In this paper, we examine learning coefficients, which indicate the general learning efficiency of deep linear learning models and three-layer neural network models with ReLU units. Finally, we extend the results to include the case of the Softmax function."},"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":"2501.12747","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-01-22T09:31:02Z","cross_cats_sorted":["cs.LG","math.AG","math.ST","stat.TH"],"title_canon_sha256":"7f8dcdbcb9e755df3907e49f77955dcf5c95e0bbaaf69be3e42fbb760d1d4fad","abstract_canon_sha256":"5a9c98562663034846126b517a010032d6d8afa05f765aa8d5fd958c2da12128"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:25.496669Z","signature_b64":"eIuR6qlqdtBXBAllqZgSyGfJLE4e5hxLOSKnGzFgDsJ6VuaZ9UBrnLocBwExfqeO8uJBE+T/VzEyaE5W6R6SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"597d987af5131752797576c0be1633f0fd0cc435ea027b06770619b18eff3dee","last_reissued_at":"2026-07-05T10:12:25.496156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:25.496156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Singular leaning coefficients and efficiency in learning theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.AG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Miki Aoyagi","submitted_at":"2025-01-22T09:31:02Z","abstract_excerpt":"Singular learning models with non-positive Fisher information matrices include neural networks, reduced-rank regression, Boltzmann machines, normal mixture models, and others. These models have been widely used in the development of learning machines. However, theoretical analysis is still in its early stages. In this paper, we examine learning coefficients, which indicate the general learning efficiency of deep linear learning models and three-layer neural network models with ReLU units. Finally, we extend the results to include the case of the Softmax function."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12747","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/2501.12747/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":"2501.12747","created_at":"2026-07-05T10:12:25.496215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12747v2","created_at":"2026-07-05T10:12:25.496215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12747","created_at":"2026-07-05T10:12:25.496215+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF6ZQ6XVCMLV","created_at":"2026-07-05T10:12:25.496215+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF6ZQ6XVCMLVE6LV","created_at":"2026-07-05T10:12:25.496215+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF6ZQ6XV","created_at":"2026-07-05T10:12:25.496215+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17219","citing_title":"PAC-Bayes Bounds for Gibbs Posteriors via Singular Learning Theory","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D","json":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D.json","graph_json":"https://pith.science/api/pith-number/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/graph.json","events_json":"https://pith.science/api/pith-number/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/events.json","paper":"https://pith.science/paper/LF6ZQ6XV"},"agent_actions":{"view_html":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D","download_json":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D.json","view_paper":"https://pith.science/paper/LF6ZQ6XV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12747&json=true","fetch_graph":"https://pith.science/api/pith-number/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/graph.json","fetch_events":"https://pith.science/api/pith-number/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/action/storage_attestation","attest_author":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/action/author_attestation","sign_citation":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/action/citation_signature","submit_replication":"https://pith.science/pith/LF6ZQ6XVCMLVE6LVO3AL4FRT6D/action/replication_record"}},"created_at":"2026-07-05T10:12:25.496215+00:00","updated_at":"2026-07-05T10:12:25.496215+00:00"}