{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:6BZFPFP4VXEAFI6GLVTVU3QDKC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ea0f674d33b0934c4bc765309d97db3b82ca5a9caf74a0a738fa60fbaec7614a","cross_cats_sorted":["cond-mat.stat-mech","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-25T17:26:08Z","title_canon_sha256":"18036ca97762028becdad2bd718f2a037f183e48a855e6c101fef3bf0c9eb229"},"schema_version":"1.0","source":{"id":"1704.08303","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08303","created_at":"2026-05-18T00:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08303v3","created_at":"2026-05-18T00:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08303","created_at":"2026-05-18T00:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"6BZFPFP4VXEA","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"6BZFPFP4VXEAFI6G","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"6BZFPFP4","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:da843163cd8fe5e8488eee00f16176ad0009adef8bda05258e0f05713260656d","target":"graph","created_at":"2026-05-18T00:35:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this work a novel method to quantify spectral ergodicity for random matrices is presented. The new methodology combines approaches rooted in the metrics of Thirumalai-Mountain (TM) and Kullbach-Leibler (KL) divergence. The method is applied to a general study of deep and recurrent neural networks via the analysis of random matrix ensembles mimicking typical weight matrices of those systems. In particular, we examine circular random matrix ensembles: circular unitary ensemble (CUE), circular orthogonal ensemble (COE), and circular symplectic ensemble (CSE). Eigenvalue spectra and spectral er","authors_text":"Cornelius Weber, Joan J. Cerd\\`a, Mehmet S\\\"uzen","cross_cats":["cond-mat.stat-mech","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-25T17:26:08Z","title":"Spectral Ergodicity in Deep Learning Architectures via Surrogate Random Matrices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08303","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c8430258131be54017378b303af510e6319126250946a56b54cdf0eea629fb55","target":"record","created_at":"2026-05-18T00:35:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ea0f674d33b0934c4bc765309d97db3b82ca5a9caf74a0a738fa60fbaec7614a","cross_cats_sorted":["cond-mat.stat-mech","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-25T17:26:08Z","title_canon_sha256":"18036ca97762028becdad2bd718f2a037f183e48a855e6c101fef3bf0c9eb229"},"schema_version":"1.0","source":{"id":"1704.08303","kind":"arxiv","version":3}},"canonical_sha256":"f0725795fcadc802a3c65d675a6e0350812f27ac8eb6c4a0ba87ca6ad444a1aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0725795fcadc802a3c65d675a6e0350812f27ac8eb6c4a0ba87ca6ad444a1aa","first_computed_at":"2026-05-18T00:35:55.208558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:55.208558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTaZ7sQYeKtK4mL4i8nEkWnaFafSf0zzckRiPz+qNpVCCNAbR9qlTsuABX0cZLMHekceETAPHzf1H1OlA3aBCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:55.209071Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.08303","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8430258131be54017378b303af510e6319126250946a56b54cdf0eea629fb55","sha256:da843163cd8fe5e8488eee00f16176ad0009adef8bda05258e0f05713260656d"],"state_sha256":"bfa803d16f6acc75ed5974f6a6916a0149861ead7bae74a94a451ddc3478c05d"}