{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HOTWRKJA2IUHRYKGJFRPCCMI26","short_pith_number":"pith:HOTWRKJA","schema_version":"1.0","canonical_sha256":"3ba768a920d22878e1464962f10988d79a53bc2ec3543820775f44c7cb55f2f1","source":{"kind":"arxiv","id":"2605.16017","version":1},"attestation_state":"computed","paper":{"title":"Accelerated Gradient Descent for Faster Convergence with Minimal Overhead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arlindo Oliveira, Frank Liu, L. Miguel Silveira, Manuel Graca","submitted_at":"2026-05-15T14:50:39Z","abstract_excerpt":"In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD is a general boosting procedure that accelerates first-order methods by explicitly capturing the local curvature using finite-difference quotients, and the development of heuristics aimed at mitigating noise and bias introduced by stochastic mini-batch training. CT-AGD has a comparable storage and computational overhead as adaptive gradient methods such as Adam. Our extensive experiments demonstrate that CT-AGD achi"},"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":"2605.16017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T14:50:39Z","cross_cats_sorted":[],"title_canon_sha256":"06af1cef2fa0d527966d353f1e1f164b7119cddec4128fcdf3f6544e87def59d","abstract_canon_sha256":"2658ff1232890c6277d90a7aa83737d84e704bf2ae4ac7fe43d308d571c9cc58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:49.261610Z","signature_b64":"bU9tcpqEmSDKj+zpheskkABlWfIJoxWrquithlj8tNIXZBphfiPa7cjZFDzO21XCwso9xWzv3hDE0kj4ijxzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ba768a920d22878e1464962f10988d79a53bc2ec3543820775f44c7cb55f2f1","last_reissued_at":"2026-05-20T00:01:49.261086Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:49.261086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerated Gradient Descent for Faster Convergence with Minimal Overhead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arlindo Oliveira, Frank Liu, L. Miguel Silveira, Manuel Graca","submitted_at":"2026-05-15T14:50:39Z","abstract_excerpt":"In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep learning training tasks. CT-AGD is a general boosting procedure that accelerates first-order methods by explicitly capturing the local curvature using finite-difference quotients, and the development of heuristics aimed at mitigating noise and bias introduced by stochastic mini-batch training. CT-AGD has a comparable storage and computational overhead as adaptive gradient methods such as Adam. Our extensive experiments demonstrate that CT-AGD achi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16017","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/2605.16017/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:42.162045Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.639302Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a3beb76dbdbc6b0446395acce7c1f337a130d61c4810841e0482304ccd560cc0"},"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":"2605.16017","created_at":"2026-05-20T00:01:49.261167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16017v1","created_at":"2026-05-20T00:01:49.261167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16017","created_at":"2026-05-20T00:01:49.261167+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOTWRKJA2IUH","created_at":"2026-05-20T00:01:49.261167+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOTWRKJA2IUHRYKG","created_at":"2026-05-20T00:01:49.261167+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOTWRKJA","created_at":"2026-05-20T00:01:49.261167+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/HOTWRKJA2IUHRYKGJFRPCCMI26","json":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26.json","graph_json":"https://pith.science/api/pith-number/HOTWRKJA2IUHRYKGJFRPCCMI26/graph.json","events_json":"https://pith.science/api/pith-number/HOTWRKJA2IUHRYKGJFRPCCMI26/events.json","paper":"https://pith.science/paper/HOTWRKJA"},"agent_actions":{"view_html":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26","download_json":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26.json","view_paper":"https://pith.science/paper/HOTWRKJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16017&json=true","fetch_graph":"https://pith.science/api/pith-number/HOTWRKJA2IUHRYKGJFRPCCMI26/graph.json","fetch_events":"https://pith.science/api/pith-number/HOTWRKJA2IUHRYKGJFRPCCMI26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26/action/storage_attestation","attest_author":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26/action/author_attestation","sign_citation":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26/action/citation_signature","submit_replication":"https://pith.science/pith/HOTWRKJA2IUHRYKGJFRPCCMI26/action/replication_record"}},"created_at":"2026-05-20T00:01:49.261167+00:00","updated_at":"2026-05-20T00:01:49.261167+00:00"}