{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7QFAOIMG765ACZLX7GQOU32RBE","short_pith_number":"pith:7QFAOIMG","canonical_record":{"source":{"id":"1905.07833","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T00:33:54Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"4a05a79c08777feb30da47015c0c51df85e7364dbcd0a7b96c8947541fc96cdd","abstract_canon_sha256":"e1e5540338c829f10abe7d3d539d57520b60f6a486af3d651de914b7d8e8cb9b"},"schema_version":"1.0"},"canonical_sha256":"fc0a072186ffba016577f9a0ea6f510915b284df85a55f9a51c336b8fae703b8","source":{"kind":"arxiv","id":"1905.07833","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07833","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07833v4","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07833","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"7QFAOIMG765A","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"7QFAOIMG765ACZLX","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"7QFAOIMG","created_at":"2026-07-05T00:47:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7QFAOIMG765ACZLX7GQOU32RBE","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07833","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T00:33:54Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"4a05a79c08777feb30da47015c0c51df85e7364dbcd0a7b96c8947541fc96cdd","abstract_canon_sha256":"e1e5540338c829f10abe7d3d539d57520b60f6a486af3d651de914b7d8e8cb9b"},"schema_version":"1.0"},"canonical_sha256":"fc0a072186ffba016577f9a0ea6f510915b284df85a55f9a51c336b8fae703b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:16.657187Z","signature_b64":"ksDKcOqAanIblOh9yQqKVG7wikuB1Keq+ZXfyvja7jXDPoHDpXBvH6VMDFOvOEMIApds7uRwhFz1rHvoBc5dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc0a072186ffba016577f9a0ea6f510915b284df85a55f9a51c336b8fae703b8","last_reissued_at":"2026-07-05T00:47:16.656715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:16.656715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07833","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qn/cfDuzE79ip82qnvFtnLlohkocqlToHrcBzv2jSj3+W12W+8WdGPX5yFZsNPZFYTc5+uhk57upMJuenY7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:48:38.220818Z"},"content_sha256":"d63e08f1bd9aa09367aff0e125498beb9057ac5c261e66b55f057321721db8c0","schema_version":"1.0","event_id":"sha256:d63e08f1bd9aa09367aff0e125498beb9057ac5c261e66b55f057321721db8c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7QFAOIMG765ACZLX7GQOU32RBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shaping the learning landscape in neural networks around wide flat minima","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Baldassi, Fabrizio Pittorino, Riccardo Zecchina","submitted_at":"2019-05-20T00:33:54Z","abstract_excerpt":"Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers without getting stuck in local critical points, and that such minimizers are often satisfactory at avoiding overfitting. How these two features can be kept under control in nonlinear devices composed of millions of tunable connections is a profound and far reaching open question. In this paper we study basic non-convex one- and two-layer neural network models w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07833","kind":"arxiv","version":4},"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/1905.07833/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":"2026-07-05T00:47:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pf3boQsJdVNSnYsuNhfoPAL5zeXKbM00txYXhs7+LqDyTDQLQk/Uh5LV41QFeLslWjAuJctOmSlosxhoibvYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:48:38.221199Z"},"content_sha256":"348296ff9962ea145d319c60419ae93344eedf7e9091cb1fd54ac0b8d3e793ca","schema_version":"1.0","event_id":"sha256:348296ff9962ea145d319c60419ae93344eedf7e9091cb1fd54ac0b8d3e793ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QFAOIMG765ACZLX7GQOU32RBE/bundle.json","state_url":"https://pith.science/pith/7QFAOIMG765ACZLX7GQOU32RBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QFAOIMG765ACZLX7GQOU32RBE/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":"2026-08-06T05:48:38Z","links":{"resolver":"https://pith.science/pith/7QFAOIMG765ACZLX7GQOU32RBE","bundle":"https://pith.science/pith/7QFAOIMG765ACZLX7GQOU32RBE/bundle.json","state":"https://pith.science/pith/7QFAOIMG765ACZLX7GQOU32RBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QFAOIMG765ACZLX7GQOU32RBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7QFAOIMG765ACZLX7GQOU32RBE","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":"e1e5540338c829f10abe7d3d539d57520b60f6a486af3d651de914b7d8e8cb9b","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T00:33:54Z","title_canon_sha256":"4a05a79c08777feb30da47015c0c51df85e7364dbcd0a7b96c8947541fc96cdd"},"schema_version":"1.0","source":{"id":"1905.07833","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07833","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07833v4","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07833","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"pith_short_12","alias_value":"7QFAOIMG765A","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"pith_short_16","alias_value":"7QFAOIMG765ACZLX","created_at":"2026-07-05T00:47:16Z"},{"alias_kind":"pith_short_8","alias_value":"7QFAOIMG","created_at":"2026-07-05T00:47:16Z"}],"graph_snapshots":[{"event_id":"sha256:348296ff9962ea145d319c60419ae93344eedf7e9091cb1fd54ac0b8d3e793ca","target":"graph","created_at":"2026-07-05T00:47:16Z","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/1905.07833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers without getting stuck in local critical points, and that such minimizers are often satisfactory at avoiding overfitting. How these two features can be kept under control in nonlinear devices composed of millions of tunable connections is a profound and far reaching open question. In this paper we study basic non-convex one- and two-layer neural network models w","authors_text":"Carlo Baldassi, Fabrizio Pittorino, Riccardo Zecchina","cross_cats":["cond-mat.dis-nn","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T00:33:54Z","title":"Shaping the learning landscape in neural networks around wide flat minima"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07833","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:d63e08f1bd9aa09367aff0e125498beb9057ac5c261e66b55f057321721db8c0","target":"record","created_at":"2026-07-05T00:47:16Z","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":"e1e5540338c829f10abe7d3d539d57520b60f6a486af3d651de914b7d8e8cb9b","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T00:33:54Z","title_canon_sha256":"4a05a79c08777feb30da47015c0c51df85e7364dbcd0a7b96c8947541fc96cdd"},"schema_version":"1.0","source":{"id":"1905.07833","kind":"arxiv","version":4}},"canonical_sha256":"fc0a072186ffba016577f9a0ea6f510915b284df85a55f9a51c336b8fae703b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc0a072186ffba016577f9a0ea6f510915b284df85a55f9a51c336b8fae703b8","first_computed_at":"2026-07-05T00:47:16.656715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:47:16.656715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ksDKcOqAanIblOh9yQqKVG7wikuB1Keq+ZXfyvja7jXDPoHDpXBvH6VMDFOvOEMIApds7uRwhFz1rHvoBc5dCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:47:16.657187Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07833","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d63e08f1bd9aa09367aff0e125498beb9057ac5c261e66b55f057321721db8c0","sha256:348296ff9962ea145d319c60419ae93344eedf7e9091cb1fd54ac0b8d3e793ca"],"state_sha256":"181082e9d74580087092d9c769100fa07ab5f5b094cd16ff82b2c667889ff1c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0rGcLZ9/dvepkQNPdOsYxRtyXH4GE9/cNoQ+OsbXZTY74+cxZgIMQBIX/62X1PTE0QM08ERYvNr+9HbkgvgHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:48:38.225336Z","bundle_sha256":"35158f05702a0677df568f0a574a1baf6f65495f23eababb16558efb37fcd23d"}}