{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZRAJA2OL4XWRCYNQE5BBDUIK4F","short_pith_number":"pith:ZRAJA2OL","schema_version":"1.0","canonical_sha256":"cc409069cbe5ed1161b0274211d10ae148cafd996bde8ab1a0265f72d1b073e4","source":{"kind":"arxiv","id":"2508.15071","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Orvieto, Aurelien Lucchi, Niccolo Ajroldi, Rustem Islamov","submitted_at":"2025-08-20T21:14:17Z","abstract_excerpt":"Modern optimization algorithms that incorporate momentum and adaptive step-size offer improved performance in numerous challenging deep learning tasks. However, their effectiveness is often highly sensitive to the choice of hyperparameters, especially the step-size. Tuning these parameters is often difficult, resource-intensive, and time-consuming. Therefore, recent efforts have been directed toward enhancing the stability of optimizers across a wide range of hyperparameter choices [Schaipp et al., 2024]. In this paper, we introduce an algorithm that matches the performance of state-of-the-art"},"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":"2508.15071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-20T21:14:17Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5893624e2587cafa8203dd2af4e8d90a20ac5ecc6affc3ca3175f01d6e911a6c","abstract_canon_sha256":"f54d0edd34eafe2875019fc5c3002201f6b0309e4bd0593e6582eb5433581e69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:06.043079Z","signature_b64":"qGfiQlTAO/AB+2bF86jg7SyzshkfFIP07NgaBVOZZWE4VOo3RqgUqVftB99N/EQUpukDdtHx8waMSnG29YigCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc409069cbe5ed1161b0274211d10ae148cafd996bde8ab1a0265f72d1b073e4","last_reissued_at":"2026-07-05T11:57:06.042654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:06.042654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Orvieto, Aurelien Lucchi, Niccolo Ajroldi, Rustem Islamov","submitted_at":"2025-08-20T21:14:17Z","abstract_excerpt":"Modern optimization algorithms that incorporate momentum and adaptive step-size offer improved performance in numerous challenging deep learning tasks. However, their effectiveness is often highly sensitive to the choice of hyperparameters, especially the step-size. Tuning these parameters is often difficult, resource-intensive, and time-consuming. Therefore, recent efforts have been directed toward enhancing the stability of optimizers across a wide range of hyperparameter choices [Schaipp et al., 2024]. In this paper, we introduce an algorithm that matches the performance of state-of-the-art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15071","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/2508.15071/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":"2508.15071","created_at":"2026-07-05T11:57:06.042712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15071v1","created_at":"2026-07-05T11:57:06.042712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15071","created_at":"2026-07-05T11:57:06.042712+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRAJA2OL4XWR","created_at":"2026-07-05T11:57:06.042712+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRAJA2OL4XWRCYNQ","created_at":"2026-07-05T11:57:06.042712+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRAJA2OL","created_at":"2026-07-05T11:57:06.042712+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/ZRAJA2OL4XWRCYNQE5BBDUIK4F","json":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F.json","graph_json":"https://pith.science/api/pith-number/ZRAJA2OL4XWRCYNQE5BBDUIK4F/graph.json","events_json":"https://pith.science/api/pith-number/ZRAJA2OL4XWRCYNQE5BBDUIK4F/events.json","paper":"https://pith.science/paper/ZRAJA2OL"},"agent_actions":{"view_html":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F","download_json":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F.json","view_paper":"https://pith.science/paper/ZRAJA2OL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15071&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRAJA2OL4XWRCYNQE5BBDUIK4F/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRAJA2OL4XWRCYNQE5BBDUIK4F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F/action/storage_attestation","attest_author":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F/action/author_attestation","sign_citation":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F/action/citation_signature","submit_replication":"https://pith.science/pith/ZRAJA2OL4XWRCYNQE5BBDUIK4F/action/replication_record"}},"created_at":"2026-07-05T11:57:06.042712+00:00","updated_at":"2026-07-05T11:57:06.042712+00:00"}