{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXM2KQ2J5IHWMFI7LRSDZFSB3M","short_pith_number":"pith:MXM2KQ2J","schema_version":"1.0","canonical_sha256":"65d9a54349ea0f66151f5c643c9641db01474b58f59c74f879b573c5f51483d2","source":{"kind":"arxiv","id":"2512.13537","version":2},"attestation_state":"computed","paper":{"title":"A Generalized Energy-Based Adaptive Gradient Method for Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hailiang Liu, Lin Feng","submitted_at":"2025-12-15T17:00:48Z","abstract_excerpt":"Adaptive Gradient Descent with Energy (AEGD) is a variant of Gradient Descent (GD) designed to address step size sensitivity through an energy-based formulation. AEGD is notable for its unconditional energy stability, ensuring convergence in energy regardless of the initial step size. In this work, we propose the Generalized Energy-Based Adaptive Gradient (gAEGD) method, which extends AEGD by generalizing the energy function beyond the square root form to a broader class of functions. We prove that gAEGD retains the unconditional energy stability property, remains robust to step size selection"},"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":"2512.13537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-12-15T17:00:48Z","cross_cats_sorted":[],"title_canon_sha256":"9f3b0d3e3ace7dff774788dccd80a5bb5cc875c05d3c0bbeaec60d942428e8a5","abstract_canon_sha256":"756605ca2294f8d1604903e7ff3f56493cd0c213e247ff9ba051e0263d633845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:09:16.436347Z","signature_b64":"EcyvGcwJ4AfOFn9i78eVe11n0jj4WZfAB70u0A39JActz/k4dqQ4UbE0/XzSMuQUq748M+KXCfr8Wv91sOSjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d9a54349ea0f66151f5c643c9641db01474b58f59c74f879b573c5f51483d2","last_reissued_at":"2026-08-04T02:09:16.434522Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:09:16.434522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generalized Energy-Based Adaptive Gradient Method for Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hailiang Liu, Lin Feng","submitted_at":"2025-12-15T17:00:48Z","abstract_excerpt":"Adaptive Gradient Descent with Energy (AEGD) is a variant of Gradient Descent (GD) designed to address step size sensitivity through an energy-based formulation. AEGD is notable for its unconditional energy stability, ensuring convergence in energy regardless of the initial step size. In this work, we propose the Generalized Energy-Based Adaptive Gradient (gAEGD) method, which extends AEGD by generalizing the energy function beyond the square root form to a broader class of functions. We prove that gAEGD retains the unconditional energy stability property, remains robust to step size selection"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.13537","kind":"arxiv","version":2},"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/2512.13537/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":"2512.13537","created_at":"2026-08-04T02:09:16.436160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.13537v2","created_at":"2026-08-04T02:09:16.436160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.13537","created_at":"2026-08-04T02:09:16.436160+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXM2KQ2J5IHW","created_at":"2026-08-04T02:09:16.436160+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXM2KQ2J5IHWMFI7","created_at":"2026-08-04T02:09:16.436160+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXM2KQ2J","created_at":"2026-08-04T02:09:16.436160+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/MXM2KQ2J5IHWMFI7LRSDZFSB3M","json":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M.json","graph_json":"https://pith.science/api/pith-number/MXM2KQ2J5IHWMFI7LRSDZFSB3M/graph.json","events_json":"https://pith.science/api/pith-number/MXM2KQ2J5IHWMFI7LRSDZFSB3M/events.json","paper":"https://pith.science/paper/MXM2KQ2J"},"agent_actions":{"view_html":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M","download_json":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M.json","view_paper":"https://pith.science/paper/MXM2KQ2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.13537&json=true","fetch_graph":"https://pith.science/api/pith-number/MXM2KQ2J5IHWMFI7LRSDZFSB3M/graph.json","fetch_events":"https://pith.science/api/pith-number/MXM2KQ2J5IHWMFI7LRSDZFSB3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M/action/storage_attestation","attest_author":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M/action/author_attestation","sign_citation":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M/action/citation_signature","submit_replication":"https://pith.science/pith/MXM2KQ2J5IHWMFI7LRSDZFSB3M/action/replication_record"}},"created_at":"2026-08-04T02:09:16.436160+00:00","updated_at":"2026-08-04T02:09:16.436160+00:00"}