{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EX2A3D7TZ5DKNR2FI6HMC6ES6G","short_pith_number":"pith:EX2A3D7T","canonical_record":{"source":{"id":"2107.01163","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-07-02T16:04:57Z","cross_cats_sorted":["cs.LG","math-ph","math.MP","math.PR"],"title_canon_sha256":"63bcba405c637eac4337ae0c8ab9dbc04203191ecda0cad66e431ce2e08280ff","abstract_canon_sha256":"4bb31c555497ed866cd18df656485ad538f050ba95bfa8fbfccf5fda01523e81"},"schema_version":"1.0"},"canonical_sha256":"25f40d8ff3cf46a6c745478ec17892f1b2efd95771326e1cb126160fb1d19272","source":{"kind":"arxiv","id":"2107.01163","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01163","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01163v5","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01163","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"EX2A3D7TZ5DK","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"pith_short_16","alias_value":"EX2A3D7TZ5DKNR2F","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"pith_short_8","alias_value":"EX2A3D7T","created_at":"2026-07-05T03:56:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EX2A3D7TZ5DKNR2FI6HMC6ES6G","target":"record","payload":{"canonical_record":{"source":{"id":"2107.01163","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-07-02T16:04:57Z","cross_cats_sorted":["cs.LG","math-ph","math.MP","math.PR"],"title_canon_sha256":"63bcba405c637eac4337ae0c8ab9dbc04203191ecda0cad66e431ce2e08280ff","abstract_canon_sha256":"4bb31c555497ed866cd18df656485ad538f050ba95bfa8fbfccf5fda01523e81"},"schema_version":"1.0"},"canonical_sha256":"25f40d8ff3cf46a6c745478ec17892f1b2efd95771326e1cb126160fb1d19272","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:29.865724Z","signature_b64":"5qMRS0RE4reuejKZTzQKrLA5xPclp20lO0JGSFagwbpew8GJsUoX0qyFLPPqxLyfUWEko9wcfpuNU/+gJSwqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25f40d8ff3cf46a6c745478ec17892f1b2efd95771326e1cb126160fb1d19272","last_reissued_at":"2026-07-05T03:56:29.864827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:29.864827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.01163","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5L3vdE2KLckDOwkOvr2fGuppE2ce9qUWikrrlAHe9YF9+aU5BCkiOQ7JPAVSDTzMG+vT5HXPnzZf8hvzOkv2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:30:42.673632Z"},"content_sha256":"0461ee3dcd127b03938fa277d393dd7e63d6d94a1e230dd8b04f6abb3a69aeaa","schema_version":"1.0","event_id":"sha256:0461ee3dcd127b03938fa277d393dd7e63d6d94a1e230dd8b04f6abb3a69aeaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EX2A3D7TZ5DKNR2FI6HMC6ES6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling the structure of wide flat minima in neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math-ph","math.MP","math.PR"],"primary_cat":"cond-mat.dis-nn","authors_text":"Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina","submitted_at":"2021-07-02T16:04:57Z","abstract_excerpt":"The success of deep learning has revealed the application potential of neural networks across the sciences and opened up fundamental theoretical problems. In particular, the fact that learning algorithms based on simple variants of gradient methods are able to find near-optimal minima of highly nonconvex loss functions is an unexpected feature of neural networks. Moreover, such algorithms are able to fit the data even in the presence of noise, and yet they have excellent predictive capabilities. Several empirical results have shown a reproducible correlation between the so-called flatness of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01163","kind":"arxiv","version":5},"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/2107.01163/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bu8MsoHZR3jITk8wydRWwbhn0tmNcf/nK1d4BC/kU+WpnWVWeEivBPUAt+tM7kaU+OleKQFq3ggmL6Lgq48qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T14:30:42.674162Z"},"content_sha256":"b5e9ac3e7574b238c272c73a33e85f95d7d12e00e88bb4843f0216db75219040","schema_version":"1.0","event_id":"sha256:b5e9ac3e7574b238c272c73a33e85f95d7d12e00e88bb4843f0216db75219040"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EX2A3D7TZ5DKNR2FI6HMC6ES6G/bundle.json","state_url":"https://pith.science/pith/EX2A3D7TZ5DKNR2FI6HMC6ES6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EX2A3D7TZ5DKNR2FI6HMC6ES6G/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":"2026-08-15T14:30:42Z","links":{"resolver":"https://pith.science/pith/EX2A3D7TZ5DKNR2FI6HMC6ES6G","bundle":"https://pith.science/pith/EX2A3D7TZ5DKNR2FI6HMC6ES6G/bundle.json","state":"https://pith.science/pith/EX2A3D7TZ5DKNR2FI6HMC6ES6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EX2A3D7TZ5DKNR2FI6HMC6ES6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EX2A3D7TZ5DKNR2FI6HMC6ES6G","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":"4bb31c555497ed866cd18df656485ad538f050ba95bfa8fbfccf5fda01523e81","cross_cats_sorted":["cs.LG","math-ph","math.MP","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-07-02T16:04:57Z","title_canon_sha256":"63bcba405c637eac4337ae0c8ab9dbc04203191ecda0cad66e431ce2e08280ff"},"schema_version":"1.0","source":{"id":"2107.01163","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.01163","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"2107.01163v5","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01163","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"EX2A3D7TZ5DK","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"pith_short_16","alias_value":"EX2A3D7TZ5DKNR2F","created_at":"2026-07-05T03:56:29Z"},{"alias_kind":"pith_short_8","alias_value":"EX2A3D7T","created_at":"2026-07-05T03:56:29Z"}],"graph_snapshots":[{"event_id":"sha256:b5e9ac3e7574b238c272c73a33e85f95d7d12e00e88bb4843f0216db75219040","target":"graph","created_at":"2026-07-05T03:56:29Z","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/2107.01163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of deep learning has revealed the application potential of neural networks across the sciences and opened up fundamental theoretical problems. In particular, the fact that learning algorithms based on simple variants of gradient methods are able to find near-optimal minima of highly nonconvex loss functions is an unexpected feature of neural networks. Moreover, such algorithms are able to fit the data even in the presence of noise, and yet they have excellent predictive capabilities. Several empirical results have shown a reproducible correlation between the so-called flatness of t","authors_text":"Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina","cross_cats":["cs.LG","math-ph","math.MP","math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-07-02T16:04:57Z","title":"Unveiling the structure of wide flat minima in neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01163","kind":"arxiv","version":5},"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":"sha256:0461ee3dcd127b03938fa277d393dd7e63d6d94a1e230dd8b04f6abb3a69aeaa","target":"record","created_at":"2026-07-05T03:56:29Z","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":"4bb31c555497ed866cd18df656485ad538f050ba95bfa8fbfccf5fda01523e81","cross_cats_sorted":["cs.LG","math-ph","math.MP","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2021-07-02T16:04:57Z","title_canon_sha256":"63bcba405c637eac4337ae0c8ab9dbc04203191ecda0cad66e431ce2e08280ff"},"schema_version":"1.0","source":{"id":"2107.01163","kind":"arxiv","version":5}},"canonical_sha256":"25f40d8ff3cf46a6c745478ec17892f1b2efd95771326e1cb126160fb1d19272","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25f40d8ff3cf46a6c745478ec17892f1b2efd95771326e1cb126160fb1d19272","first_computed_at":"2026-07-05T03:56:29.864827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:29.864827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5qMRS0RE4reuejKZTzQKrLA5xPclp20lO0JGSFagwbpew8GJsUoX0qyFLPPqxLyfUWEko9wcfpuNU/+gJSwqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:29.865724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.01163","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0461ee3dcd127b03938fa277d393dd7e63d6d94a1e230dd8b04f6abb3a69aeaa","sha256:b5e9ac3e7574b238c272c73a33e85f95d7d12e00e88bb4843f0216db75219040"],"state_sha256":"5f62d55dee9b49761cd4f6b6d5624aa35c1fcf349cda338e1ee031a2974f6e4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5iS+q/LF4RJIZGjnHCtpY5i+LNjUk+KCpAO9hXwhSTIo0ACj6HYwtpk0+9aUdG5XFkPCn0/s/1cCVkHX6I4nAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T14:30:42.678439Z","bundle_sha256":"67af3c0b6fc36d5d43956109a493a44b0e2435bcb0083fe44d7737ac98a4853a"}}