{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WL3ERSUBUYA7AHHTQPUQ3MVEEP","short_pith_number":"pith:WL3ERSUB","schema_version":"1.0","canonical_sha256":"b2f648ca81a601f01cf383e90db2a423c45c16fc4ff779682f0ee570729a4875","source":{"kind":"arxiv","id":"2001.03371","version":1},"attestation_state":"computed","paper":{"title":"Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Masato Okada, Yuki Yoshida","submitted_at":"2020-01-10T10:17:08Z","abstract_excerpt":"The plateau phenomenon, wherein the loss value stops decreasing during the process of learning, has been reported by various researchers. The phenomenon is actively inspected in the 1990s and found to be due to the fundamental hierarchical structure of neural network models. Then the phenomenon has been thought as inevitable. However, the phenomenon seldom occurs in the context of recent deep learning. There is a gap between theory and reality. In this paper, using statistical mechanical formulation, we clarified the relationship between the plateau phenomenon and the statistical property of t"},"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":"2001.03371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-01-10T10:17:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"822ec35cb8d55cde17f9130030467c43939aaa72f1c81f7c25d80d70b5d1898c","abstract_canon_sha256":"afbab89ac8875e56aef487b863701c577e34b54d33f4e64e12bc99eb6eaedc74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:40.711879Z","signature_b64":"kqw0Ftvl3C3fEeCwogPR83IbM3rGDO/imRGZATvQhEdbv1R4oVbigpih0y3ZPz46288qUcm+4y7u1ICfCxfdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f648ca81a601f01cf383e90db2a423c45c16fc4ff779682f0ee570729a4875","last_reissued_at":"2026-07-05T02:11:40.711491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:40.711491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Masato Okada, Yuki Yoshida","submitted_at":"2020-01-10T10:17:08Z","abstract_excerpt":"The plateau phenomenon, wherein the loss value stops decreasing during the process of learning, has been reported by various researchers. The phenomenon is actively inspected in the 1990s and found to be due to the fundamental hierarchical structure of neural network models. Then the phenomenon has been thought as inevitable. However, the phenomenon seldom occurs in the context of recent deep learning. There is a gap between theory and reality. In this paper, using statistical mechanical formulation, we clarified the relationship between the plateau phenomenon and the statistical property of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.03371","kind":"arxiv","version":1},"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/2001.03371/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2001.03371","created_at":"2026-07-05T02:11:40.711547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.03371v1","created_at":"2026-07-05T02:11:40.711547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.03371","created_at":"2026-07-05T02:11:40.711547+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL3ERSUBUYA7","created_at":"2026-07-05T02:11:40.711547+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL3ERSUBUYA7AHHT","created_at":"2026-07-05T02:11:40.711547+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL3ERSUB","created_at":"2026-07-05T02:11:40.711547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05447","citing_title":"Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP","json":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP.json","graph_json":"https://pith.science/api/pith-number/WL3ERSUBUYA7AHHTQPUQ3MVEEP/graph.json","events_json":"https://pith.science/api/pith-number/WL3ERSUBUYA7AHHTQPUQ3MVEEP/events.json","paper":"https://pith.science/paper/WL3ERSUB"},"agent_actions":{"view_html":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP","download_json":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP.json","view_paper":"https://pith.science/paper/WL3ERSUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.03371&json=true","fetch_graph":"https://pith.science/api/pith-number/WL3ERSUBUYA7AHHTQPUQ3MVEEP/graph.json","fetch_events":"https://pith.science/api/pith-number/WL3ERSUBUYA7AHHTQPUQ3MVEEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP/action/storage_attestation","attest_author":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP/action/author_attestation","sign_citation":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP/action/citation_signature","submit_replication":"https://pith.science/pith/WL3ERSUBUYA7AHHTQPUQ3MVEEP/action/replication_record"}},"created_at":"2026-07-05T02:11:40.711547+00:00","updated_at":"2026-07-05T02:11:40.711547+00:00"}