{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:KSFPEA7K5MDCIVI32S35V35JER","short_pith_number":"pith:KSFPEA7K","schema_version":"1.0","canonical_sha256":"548af203eaeb0624551bd4b7daefa924678baca7373fb62f2335c608df95cbd1","source":{"kind":"arxiv","id":"1605.06444","version":3},"attestation_state":"computed","paper":{"title":"Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Ingrosso, Carlo Baldassi, Carlo Lucibello, Christian Borgs, Jennifer Chayes, Luca Saglietti, Riccardo Zecchina","submitted_at":"2016-05-20T17:27:18Z","abstract_excerpt":"In artificial neural networks, learning from data is a computationally demanding task in which a large number of connection weights are iteratively tuned through stochastic-gradient-based heuristic processes over a cost-function. It is not well understood how learning occurs in these systems, in particular how they avoid getting trapped in configurations with poor computational performance. Here we study the difficult case of networks with discrete weights, where the optimization landscape is very rough even for simple architectures, and provide theoretical and numerical evidence of the existe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1605.06444","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-05-20T17:27:18Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG"],"title_canon_sha256":"efecdb7377d1b61538bf1bc019a047dc91bfe59ae6622f6d040cc62ac92be97b","abstract_canon_sha256":"b52bedc3c041eb23729e0def02ee069ba1badcf2f8e043273a98f68b69441178"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:10.596044Z","signature_b64":"TIzvMdWIUA3oaB9jmBQ3NqUlWFu9Kon2yi77dCaWaBPYGF9s0QLH3y1z6CHsfYBLCog3gXiLP8TgAzpn40KmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548af203eaeb0624551bd4b7daefa924678baca7373fb62f2335c608df95cbd1","last_reissued_at":"2026-05-18T00:56:10.595577Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:10.595577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Ingrosso, Carlo Baldassi, Carlo Lucibello, Christian Borgs, Jennifer Chayes, Luca Saglietti, Riccardo Zecchina","submitted_at":"2016-05-20T17:27:18Z","abstract_excerpt":"In artificial neural networks, learning from data is a computationally demanding task in which a large number of connection weights are iteratively tuned through stochastic-gradient-based heuristic processes over a cost-function. It is not well understood how learning occurs in these systems, in particular how they avoid getting trapped in configurations with poor computational performance. Here we study the difficult case of networks with discrete weights, where the optimization landscape is very rough even for simple architectures, and provide theoretical and numerical evidence of the existe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06444","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1605.06444","created_at":"2026-05-18T00:56:10.595653+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.06444v3","created_at":"2026-05-18T00:56:10.595653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06444","created_at":"2026-05-18T00:56:10.595653+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSFPEA7K5MDC","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSFPEA7K5MDCIVI3","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSFPEA7K","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER","json":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER.json","graph_json":"https://pith.science/api/pith-number/KSFPEA7K5MDCIVI32S35V35JER/graph.json","events_json":"https://pith.science/api/pith-number/KSFPEA7K5MDCIVI32S35V35JER/events.json","paper":"https://pith.science/paper/KSFPEA7K"},"agent_actions":{"view_html":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER","download_json":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER.json","view_paper":"https://pith.science/paper/KSFPEA7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.06444&json=true","fetch_graph":"https://pith.science/api/pith-number/KSFPEA7K5MDCIVI32S35V35JER/graph.json","fetch_events":"https://pith.science/api/pith-number/KSFPEA7K5MDCIVI32S35V35JER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER/action/storage_attestation","attest_author":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER/action/author_attestation","sign_citation":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER/action/citation_signature","submit_replication":"https://pith.science/pith/KSFPEA7K5MDCIVI32S35V35JER/action/replication_record"}},"created_at":"2026-05-18T00:56:10.595653+00:00","updated_at":"2026-05-18T00:56:10.595653+00:00"}