{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OIOEDOH2IV7ICXMJSBIXIHZ4HS","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":"6169e3a8e316cebb214ee9bdef8cdcc7fa3f57a07222fdbffd471ef2a5ea5053","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T13:56:56Z","title_canon_sha256":"8d1641728fb762dce38dce808628ef613151342ee716f0022889b4a72f69b42b"},"schema_version":"1.0","source":{"id":"1909.11500","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11500","created_at":"2026-07-05T01:56:40Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11500v4","created_at":"2026-07-05T01:56:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11500","created_at":"2026-07-05T01:56:40Z"},{"alias_kind":"pith_short_12","alias_value":"OIOEDOH2IV7I","created_at":"2026-07-05T01:56:40Z"},{"alias_kind":"pith_short_16","alias_value":"OIOEDOH2IV7ICXMJ","created_at":"2026-07-05T01:56:40Z"},{"alias_kind":"pith_short_8","alias_value":"OIOEDOH2","created_at":"2026-07-05T01:56:40Z"}],"graph_snapshots":[{"event_id":"sha256:c0ddd6d79348470e6c89893c45964a946cb7a50ce9ddb5004c3db215790b3f09","target":"graph","created_at":"2026-07-05T01:56:40Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.11500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the reasons for the success of deep neural networks trained using stochastic gradient-based methods is a key open problem for the nascent theory of deep learning. The types of data where these networks are most successful, such as images or sequences of speech, are characterised by intricate correlations. Yet, most theoretical work on neural networks does not explicitly model training data, or assumes that elements of each data sample are drawn independently from some factorised probability distribution. These approaches are thus by construction blind to the correlation structure","authors_text":"Florent Krzakala, Lenka Zdeborov\\'a, Marc M\\'ezard, Sebastian Goldt","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T13:56:56Z","title":"Modelling the influence of data structure on learning in neural networks: the hidden manifold model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11500","kind":"arxiv","version":4},"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":"sha256:13bc57d426d7cec4931103a29197b6e88dd891fa4fc93cd5897c1710ed0c3351","target":"record","created_at":"2026-07-05T01:56:40Z","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":"6169e3a8e316cebb214ee9bdef8cdcc7fa3f57a07222fdbffd471ef2a5ea5053","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-09-25T13:56:56Z","title_canon_sha256":"8d1641728fb762dce38dce808628ef613151342ee716f0022889b4a72f69b42b"},"schema_version":"1.0","source":{"id":"1909.11500","kind":"arxiv","version":4}},"canonical_sha256":"721c41b8fa457e815d899051741f3c3c90c2469c6e54b2061c5a8b59b77c780b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"721c41b8fa457e815d899051741f3c3c90c2469c6e54b2061c5a8b59b77c780b","first_computed_at":"2026-07-05T01:56:40.264911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:40.264911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wTeZb/d2/dHT42VOKE+OzcZ3cf8E40r5AThXpVreB8+Nkadt+WX0mCsJV+ihFJEohoXuY6q31H2oeQ5Paw/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:40.265345Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11500","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13bc57d426d7cec4931103a29197b6e88dd891fa4fc93cd5897c1710ed0c3351","sha256:c0ddd6d79348470e6c89893c45964a946cb7a50ce9ddb5004c3db215790b3f09"],"state_sha256":"4d0e59780e729a1188200e4561dc3cd29e560947c966c15f4f4e63c378493335"}