{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3MLA2NGRKHJLLAMU2WUJW6NELC","short_pith_number":"pith:3MLA2NGR","schema_version":"1.0","canonical_sha256":"db160d34d151d2b58194d5a89b79a458b8d9517bf58d9542265364207a2f383b","source":{"kind":"arxiv","id":"2409.11995","version":1},"attestation_state":"computed","paper":{"title":"Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Grabovoy, Nikita Kiselev","submitted_at":"2024-09-18T14:04:15Z","abstract_excerpt":"The loss landscape of neural networks is a critical aspect of their training, and understanding its properties is essential for improving their performance. In this paper, we investigate how the loss surface changes when the sample size increases, a previously unexplored issue. We theoretically analyze the convergence of the loss landscape in a fully connected neural network and derive upper bounds for the difference in loss function values when adding a new object to the sample. Our empirical study confirms these results on various datasets, demonstrating the convergence of the loss function "},"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":"2409.11995","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T14:04:15Z","cross_cats_sorted":[],"title_canon_sha256":"eb8e600d7f8763cd75a7ea3c392ff21ae96f15513c8e4fe2db47fb70f6cb43eb","abstract_canon_sha256":"16b11f78cbd62c17a1312d6911f12af1dcb29d62611a9e38b4db92d4c1cc9e31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:40.719010Z","signature_b64":"4yWUIC9TVsK7cICDy6s3AxBsnmwTmuVP+ddeRQi04ArY8slmrI+Q+L1kpuy8r18R7Q5LHWAu6so3y6XMDNQODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db160d34d151d2b58194d5a89b79a458b8d9517bf58d9542265364207a2f383b","last_reissued_at":"2026-07-05T09:08:40.718514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:40.718514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Grabovoy, Nikita Kiselev","submitted_at":"2024-09-18T14:04:15Z","abstract_excerpt":"The loss landscape of neural networks is a critical aspect of their training, and understanding its properties is essential for improving their performance. In this paper, we investigate how the loss surface changes when the sample size increases, a previously unexplored issue. We theoretically analyze the convergence of the loss landscape in a fully connected neural network and derive upper bounds for the difference in loss function values when adding a new object to the sample. Our empirical study confirms these results on various datasets, demonstrating the convergence of the loss function "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11995","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/2409.11995/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":"2409.11995","created_at":"2026-07-05T09:08:40.718578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11995v1","created_at":"2026-07-05T09:08:40.718578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11995","created_at":"2026-07-05T09:08:40.718578+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MLA2NGRKHJL","created_at":"2026-07-05T09:08:40.718578+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MLA2NGRKHJLLAMU","created_at":"2026-07-05T09:08:40.718578+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MLA2NGR","created_at":"2026-07-05T09:08:40.718578+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/3MLA2NGRKHJLLAMU2WUJW6NELC","json":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC.json","graph_json":"https://pith.science/api/pith-number/3MLA2NGRKHJLLAMU2WUJW6NELC/graph.json","events_json":"https://pith.science/api/pith-number/3MLA2NGRKHJLLAMU2WUJW6NELC/events.json","paper":"https://pith.science/paper/3MLA2NGR"},"agent_actions":{"view_html":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC","download_json":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC.json","view_paper":"https://pith.science/paper/3MLA2NGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11995&json=true","fetch_graph":"https://pith.science/api/pith-number/3MLA2NGRKHJLLAMU2WUJW6NELC/graph.json","fetch_events":"https://pith.science/api/pith-number/3MLA2NGRKHJLLAMU2WUJW6NELC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC/action/storage_attestation","attest_author":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC/action/author_attestation","sign_citation":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC/action/citation_signature","submit_replication":"https://pith.science/pith/3MLA2NGRKHJLLAMU2WUJW6NELC/action/replication_record"}},"created_at":"2026-07-05T09:08:40.718578+00:00","updated_at":"2026-07-05T09:08:40.718578+00:00"}