{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5T5WPHL4XV55S26SVEYR2NQWFE","short_pith_number":"pith:5T5WPHL4","canonical_record":{"source":{"id":"2110.00683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T23:28:07Z","cross_cats_sorted":["cond-mat.dis-nn","math.PR","stat.ML"],"title_canon_sha256":"e9314069280827d7d383ae4eccf91636a06c5ac5ce24744b56a06e392903fd0e","abstract_canon_sha256":"d8a8a36a9f89153df676b5fe7caa343659d92e4851b29cd5c7aa324a32b53fc0"},"schema_version":"1.0"},"canonical_sha256":"ecfb679d7cbd7bd96bd2a9311d3616290dfd25d4266051430e4270ea0434272a","source":{"kind":"arxiv","id":"2110.00683","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00683","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00683v2","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00683","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"5T5WPHL4XV55","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"pith_short_16","alias_value":"5T5WPHL4XV55S26S","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"pith_short_8","alias_value":"5T5WPHL4","created_at":"2026-07-05T04:43:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5T5WPHL4XV55S26SVEYR2NQWFE","target":"record","payload":{"canonical_record":{"source":{"id":"2110.00683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T23:28:07Z","cross_cats_sorted":["cond-mat.dis-nn","math.PR","stat.ML"],"title_canon_sha256":"e9314069280827d7d383ae4eccf91636a06c5ac5ce24744b56a06e392903fd0e","abstract_canon_sha256":"d8a8a36a9f89153df676b5fe7caa343659d92e4851b29cd5c7aa324a32b53fc0"},"schema_version":"1.0"},"canonical_sha256":"ecfb679d7cbd7bd96bd2a9311d3616290dfd25d4266051430e4270ea0434272a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:43:34.745452Z","signature_b64":"gD9t3JAFx/ktqFf0f1/fc0YgkinK09ekDbuBlCaB8u1+X0lhMhBosKqXoyDIOhRP7hrmzg6NM2DhXyQJwn+vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecfb679d7cbd7bd96bd2a9311d3616290dfd25d4266051430e4270ea0434272a","last_reissued_at":"2026-07-05T04:43:34.744969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:43:34.744969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.00683","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:43:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1t4o6nkJPkvkGzJJ8TsDVHk6fe7fXv2GEHbJ39jRVM0ZNgman1qaE5+EJGKrnoeVlVL4tHrkrgtOC5K9HNyGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:22:12.225887Z"},"content_sha256":"dafb8ec3c37d7325287ef51b2ca06c4e0ba21ca8f42d1cf66986d537690e921f","schema_version":"1.0","event_id":"sha256:dafb8ec3c37d7325287ef51b2ca06c4e0ba21ca8f42d1cf66986d537690e921f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5T5WPHL4XV55S26SVEYR2NQWFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning through atypical \"phase transitions\" in overparameterized neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina, Rosalba Pacelli","submitted_at":"2021-10-01T23:28:07Z","abstract_excerpt":"Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of prediction accuracy without overfitting. These are formidable results that defy predictions of statistical learning and pose conceptual challenges for non-convex optimization. In this paper, we use methods from statistical physics of disordered systems to analytically study the computational fallout of overparameterization in non-convex binary neural network models,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00683","kind":"arxiv","version":2},"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/2110.00683/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":"2026-07-05T04:43:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k8r5a77HKQWb4kwuGDPMneRhFHNlToodQ+6jJOJnTxBG6aKNlC/T6SrpN+dB7iffHiJNzZGbc4GH1R6ihEG6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:22:12.226284Z"},"content_sha256":"3c2edfbe452bb22aba63cb0750209c76ad255adb8483322e3dd1858e52562267","schema_version":"1.0","event_id":"sha256:3c2edfbe452bb22aba63cb0750209c76ad255adb8483322e3dd1858e52562267"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5T5WPHL4XV55S26SVEYR2NQWFE/bundle.json","state_url":"https://pith.science/pith/5T5WPHL4XV55S26SVEYR2NQWFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5T5WPHL4XV55S26SVEYR2NQWFE/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":"2026-08-06T00:22:12Z","links":{"resolver":"https://pith.science/pith/5T5WPHL4XV55S26SVEYR2NQWFE","bundle":"https://pith.science/pith/5T5WPHL4XV55S26SVEYR2NQWFE/bundle.json","state":"https://pith.science/pith/5T5WPHL4XV55S26SVEYR2NQWFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5T5WPHL4XV55S26SVEYR2NQWFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5T5WPHL4XV55S26SVEYR2NQWFE","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":"d8a8a36a9f89153df676b5fe7caa343659d92e4851b29cd5c7aa324a32b53fc0","cross_cats_sorted":["cond-mat.dis-nn","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T23:28:07Z","title_canon_sha256":"e9314069280827d7d383ae4eccf91636a06c5ac5ce24744b56a06e392903fd0e"},"schema_version":"1.0","source":{"id":"2110.00683","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00683","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00683v2","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00683","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"5T5WPHL4XV55","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"pith_short_16","alias_value":"5T5WPHL4XV55S26S","created_at":"2026-07-05T04:43:34Z"},{"alias_kind":"pith_short_8","alias_value":"5T5WPHL4","created_at":"2026-07-05T04:43:34Z"}],"graph_snapshots":[{"event_id":"sha256:3c2edfbe452bb22aba63cb0750209c76ad255adb8483322e3dd1858e52562267","target":"graph","created_at":"2026-07-05T04:43:34Z","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/2110.00683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current deep neural networks are highly overparameterized (up to billions of connection weights) and nonlinear. Yet they can fit data almost perfectly through variants of gradient descent algorithms and achieve unexpected levels of prediction accuracy without overfitting. These are formidable results that defy predictions of statistical learning and pose conceptual challenges for non-convex optimization. In this paper, we use methods from statistical physics of disordered systems to analytically study the computational fallout of overparameterization in non-convex binary neural network models,","authors_text":"Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina, Rosalba Pacelli","cross_cats":["cond-mat.dis-nn","math.PR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T23:28:07Z","title":"Learning through atypical \"phase transitions\" in overparameterized neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00683","kind":"arxiv","version":2},"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:dafb8ec3c37d7325287ef51b2ca06c4e0ba21ca8f42d1cf66986d537690e921f","target":"record","created_at":"2026-07-05T04:43:34Z","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":"d8a8a36a9f89153df676b5fe7caa343659d92e4851b29cd5c7aa324a32b53fc0","cross_cats_sorted":["cond-mat.dis-nn","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-01T23:28:07Z","title_canon_sha256":"e9314069280827d7d383ae4eccf91636a06c5ac5ce24744b56a06e392903fd0e"},"schema_version":"1.0","source":{"id":"2110.00683","kind":"arxiv","version":2}},"canonical_sha256":"ecfb679d7cbd7bd96bd2a9311d3616290dfd25d4266051430e4270ea0434272a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecfb679d7cbd7bd96bd2a9311d3616290dfd25d4266051430e4270ea0434272a","first_computed_at":"2026-07-05T04:43:34.744969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:43:34.744969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gD9t3JAFx/ktqFf0f1/fc0YgkinK09ekDbuBlCaB8u1+X0lhMhBosKqXoyDIOhRP7hrmzg6NM2DhXyQJwn+vBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:43:34.745452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00683","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dafb8ec3c37d7325287ef51b2ca06c4e0ba21ca8f42d1cf66986d537690e921f","sha256:3c2edfbe452bb22aba63cb0750209c76ad255adb8483322e3dd1858e52562267"],"state_sha256":"71f7cf4995bcd5bf8f291e0d9198ac6755d9a6ec3297543ea3223adf7998979b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wwm4yJ9z4VUsCtcLprAlABuoLKZZ+XKtzon+YbSvzqswxcrZcbb+B6Alt9rzkmw8wHq4xrjWd+YjRt2yp0e7Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:22:12.229699Z","bundle_sha256":"0ae087e72c61668c8bfb12dcf1e2cfccf389a14e469564d14785690b78527c23"}}