{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:72XUAMTEUCXQ76PUMD33QAEYGZ","short_pith_number":"pith:72XUAMTE","schema_version":"1.0","canonical_sha256":"feaf403264a0af0ff9f460f7b800983649078036e9726cfa9abcc350bb018f6f","source":{"kind":"arxiv","id":"2505.07143","version":1},"attestation_state":"computed","paper":{"title":"Subgradient Regularization: A Descent-Oriented Subgradient Method for Nonsmooth Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hanyang Li, Ying Cui","submitted_at":"2025-05-11T23:03:45Z","abstract_excerpt":"In nonsmooth optimization, a negative subgradient is not necessarily a descent direction, making the design of convergent descent methods based on zeroth-order and first-order information a challenging task. The well-studied bundle methods and gradient sampling algorithms construct descent directions by aggregating subgradients at nearby points in seemingly different ways, and are often complicated or lack deterministic guarantees. In this work, we identify a unifying principle behind these approaches, and develop a general framework of descent methods under the abstract principle that provabl"},"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":"2505.07143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-11T23:03:45Z","cross_cats_sorted":[],"title_canon_sha256":"7b60d81152a5f21745dcc09c97ebb91306e81b3ddcb466ba1ac26caa3e8e8fd5","abstract_canon_sha256":"e6579d97ce64daa443d10fabe1f88497d3ebed5e3d635e0f8d2bcc7315646cc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:43.236523Z","signature_b64":"uj80/2oY16ZelhuU5HuXoQldaXYQ00o++Fxj5DbTHpopP3C8wW230CUMPv7iuFfo7hXxU7lfrPj/fPHolODGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feaf403264a0af0ff9f460f7b800983649078036e9726cfa9abcc350bb018f6f","last_reissued_at":"2026-07-05T11:01:43.236065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:43.236065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subgradient Regularization: A Descent-Oriented Subgradient Method for Nonsmooth Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hanyang Li, Ying Cui","submitted_at":"2025-05-11T23:03:45Z","abstract_excerpt":"In nonsmooth optimization, a negative subgradient is not necessarily a descent direction, making the design of convergent descent methods based on zeroth-order and first-order information a challenging task. The well-studied bundle methods and gradient sampling algorithms construct descent directions by aggregating subgradients at nearby points in seemingly different ways, and are often complicated or lack deterministic guarantees. In this work, we identify a unifying principle behind these approaches, and develop a general framework of descent methods under the abstract principle that provabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07143","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/2505.07143/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":"2505.07143","created_at":"2026-07-05T11:01:43.236120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07143v1","created_at":"2026-07-05T11:01:43.236120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07143","created_at":"2026-07-05T11:01:43.236120+00:00"},{"alias_kind":"pith_short_12","alias_value":"72XUAMTEUCXQ","created_at":"2026-07-05T11:01:43.236120+00:00"},{"alias_kind":"pith_short_16","alias_value":"72XUAMTEUCXQ76PU","created_at":"2026-07-05T11:01:43.236120+00:00"},{"alias_kind":"pith_short_8","alias_value":"72XUAMTE","created_at":"2026-07-05T11:01:43.236120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10219","citing_title":"Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10219","citing_title":"Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10219","citing_title":"Parameterized Complexity of Stationarity Testing for Piecewise-Affine Functions and Shallow CNN Losses","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ","json":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ.json","graph_json":"https://pith.science/api/pith-number/72XUAMTEUCXQ76PUMD33QAEYGZ/graph.json","events_json":"https://pith.science/api/pith-number/72XUAMTEUCXQ76PUMD33QAEYGZ/events.json","paper":"https://pith.science/paper/72XUAMTE"},"agent_actions":{"view_html":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ","download_json":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ.json","view_paper":"https://pith.science/paper/72XUAMTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07143&json=true","fetch_graph":"https://pith.science/api/pith-number/72XUAMTEUCXQ76PUMD33QAEYGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/72XUAMTEUCXQ76PUMD33QAEYGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ/action/storage_attestation","attest_author":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ/action/author_attestation","sign_citation":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ/action/citation_signature","submit_replication":"https://pith.science/pith/72XUAMTEUCXQ76PUMD33QAEYGZ/action/replication_record"}},"created_at":"2026-07-05T11:01:43.236120+00:00","updated_at":"2026-07-05T11:01:43.236120+00:00"}