{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:6BZFPFP4VXEAFI6GLVTVU3QDKC","short_pith_number":"pith:6BZFPFP4","canonical_record":{"source":{"id":"1704.08303","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-25T17:26:08Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"18036ca97762028becdad2bd718f2a037f183e48a855e6c101fef3bf0c9eb229","abstract_canon_sha256":"ea0f674d33b0934c4bc765309d97db3b82ca5a9caf74a0a738fa60fbaec7614a"},"schema_version":"1.0"},"canonical_sha256":"f0725795fcadc802a3c65d675a6e0350812f27ac8eb6c4a0ba87ca6ad444a1aa","source":{"kind":"arxiv","id":"1704.08303","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:6BZFPFP4VXEAFI6GLVTVU3QDKC","target":"record","payload":{"canonical_record":{"source":{"id":"1704.08303","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-04-25T17:26:08Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"18036ca97762028becdad2bd718f2a037f183e48a855e6c101fef3bf0c9eb229","abstract_canon_sha256":"ea0f674d33b0934c4bc765309d97db3b82ca5a9caf74a0a738fa60fbaec7614a"},"schema_version":"1.0"},"canonical_sha256":"f0725795fcadc802a3c65d675a6e0350812f27ac8eb6c4a0ba87ca6ad444a1aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:55.209071Z","signature_b64":"eTaZ7sQYeKtK4mL4i8nEkWnaFafSf0zzckRiPz+qNpVCCNAbR9qlTsuABX0cZLMHekceETAPHzf1H1OlA3aBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0725795fcadc802a3c65d675a6e0350812f27ac8eb6c4a0ba87ca6ad444a1aa","last_reissued_at":"2026-05-18T00:35:55.208558Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:55.208558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.08303","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpq26BrixXUp0S2GLyrWRJ74wpoHLbOIQCnxcdHzlzJIH+ZFuPHHs5bppuSbSNLDlEViq8y78Q5imy0qB9UtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T19:55:17.467921Z"},"content_sha256":"c8430258131be54017378b303af510e6319126250946a56b54cdf0eea629fb55","schema_version":"1.0","event_id":"sha256:c8430258131be54017378b303af510e6319126250946a56b54cdf0eea629fb55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:6BZFPFP4VXEAFI6GLVTVU3QDKC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spectral Ergodicity in Deep Learning Architectures via Surrogate Random Matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG"],"primary_cat":"stat.ML","authors_text":"Cornelius Weber, Joan J. Cerd\\`a, Mehmet S\\\"uzen","submitted_at":"2017-04-25T17:26:08Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08303","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DnsKHVftZ1+FaLAC/n3hSLBmRK5/AkVhN03mugvAAEPpvZgWNaBTH6pILbiljv6CcYLKR+QlKoYnkF69TgYDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T19:55:17.468268Z"},"content_sha256":"da843163cd8fe5e8488eee00f16176ad0009adef8bda05258e0f05713260656d","schema_version":"1.0","event_id":"sha256:da843163cd8fe5e8488eee00f16176ad0009adef8bda05258e0f05713260656d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6BZFPFP4VXEAFI6GLVTVU3QDKC/bundle.json","state_url":"https://pith.science/pith/6BZFPFP4VXEAFI6GLVTVU3QDKC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6BZFPFP4VXEAFI6GLVTVU3QDKC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T19:55:17Z","links":{"resolver":"https://pith.science/pith/6BZFPFP4VXEAFI6GLVTVU3QDKC","bundle":"https://pith.science/pith/6BZFPFP4VXEAFI6GLVTVU3QDKC/bundle.json","state":"https://pith.science/pith/6BZFPFP4VXEAFI6GLVTVU3QDKC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6BZFPFP4VXEAFI6GLVTVU3QDKC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r0jxw61S8CtNXFCUPzagg6PVv+jq1bHKaXQa9N2sppThw2jRwqM9V/vEvmMRltMVGGZ7OM0RuAue8mwIZVTRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T19:55:17.470164Z","bundle_sha256":"79483f2a3fc66bcc959b1629cd3f715b54fbe6d74bc2c66e4529c6f7dad74fd9"}}