{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JM4JJA5YQQ3XUOBJR6MBD6A77E","short_pith_number":"pith:JM4JJA5Y","schema_version":"1.0","canonical_sha256":"4b389483b884377a38298f9811f81ff901be58f182f47bcdfa91bb25cf24e03a","source":{"kind":"arxiv","id":"2503.18098","version":1},"attestation_state":"computed","paper":{"title":"Forward-backward splitting under the light of generalized convexity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Emanuel Laude, Konstantinos Oikonomidis, Panagiotis Patrinos","submitted_at":"2025-03-23T15:05:39Z","abstract_excerpt":"In this paper we present a unifying framework for continuous optimization methods grounded in the concept of generalized convexity. Utilizing the powerful theory of $\\Phi$-convexity, we propose a conceptual algorithm that extends the classical difference-of-convex method, encompassing a broad spectrum of optimization algorithms. Relying exclusively on the tools of generalized convexity we develop a gap function analysis that strictly characterizes the decrease of the function values, leading to simplified and unified convergence results. As an outcome of this analysis, we naturally obtain a ge"},"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":"2503.18098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-03-23T15:05:39Z","cross_cats_sorted":[],"title_canon_sha256":"0ea88099bb861b86e6dfab3a64ffe8457bb5a90fc6df667cb964b346342615ee","abstract_canon_sha256":"ce8fb590a2cd24490cb0c4ad2b109cd830c4478a6f55b6313a88cbd94c0955db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:02.626758Z","signature_b64":"NIFl/3qaSvvGkLotNby4DHUJo6GUjH+BFTYXpI9CoWu7jW86B89BoNYB1bKKAVwCwo70BNrfNg0qEC7jlMvVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b389483b884377a38298f9811f81ff901be58f182f47bcdfa91bb25cf24e03a","last_reissued_at":"2026-07-05T10:38:02.625727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:02.625727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forward-backward splitting under the light of generalized convexity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Emanuel Laude, Konstantinos Oikonomidis, Panagiotis Patrinos","submitted_at":"2025-03-23T15:05:39Z","abstract_excerpt":"In this paper we present a unifying framework for continuous optimization methods grounded in the concept of generalized convexity. Utilizing the powerful theory of $\\Phi$-convexity, we propose a conceptual algorithm that extends the classical difference-of-convex method, encompassing a broad spectrum of optimization algorithms. Relying exclusively on the tools of generalized convexity we develop a gap function analysis that strictly characterizes the decrease of the function values, leading to simplified and unified convergence results. As an outcome of this analysis, we naturally obtain a ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18098","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/2503.18098/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":"2503.18098","created_at":"2026-07-05T10:38:02.625867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18098v1","created_at":"2026-07-05T10:38:02.625867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18098","created_at":"2026-07-05T10:38:02.625867+00:00"},{"alias_kind":"pith_short_12","alias_value":"JM4JJA5YQQ3X","created_at":"2026-07-05T10:38:02.625867+00:00"},{"alias_kind":"pith_short_16","alias_value":"JM4JJA5YQQ3XUOBJ","created_at":"2026-07-05T10:38:02.625867+00:00"},{"alias_kind":"pith_short_8","alias_value":"JM4JJA5Y","created_at":"2026-07-05T10:38:02.625867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27767","citing_title":"Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12666","citing_title":"Newton methods beyond Hessian Lipschitz continuity: A nonlinear preconditioning approach","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E","json":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E.json","graph_json":"https://pith.science/api/pith-number/JM4JJA5YQQ3XUOBJR6MBD6A77E/graph.json","events_json":"https://pith.science/api/pith-number/JM4JJA5YQQ3XUOBJR6MBD6A77E/events.json","paper":"https://pith.science/paper/JM4JJA5Y"},"agent_actions":{"view_html":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E","download_json":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E.json","view_paper":"https://pith.science/paper/JM4JJA5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18098&json=true","fetch_graph":"https://pith.science/api/pith-number/JM4JJA5YQQ3XUOBJR6MBD6A77E/graph.json","fetch_events":"https://pith.science/api/pith-number/JM4JJA5YQQ3XUOBJR6MBD6A77E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E/action/storage_attestation","attest_author":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E/action/author_attestation","sign_citation":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E/action/citation_signature","submit_replication":"https://pith.science/pith/JM4JJA5YQQ3XUOBJR6MBD6A77E/action/replication_record"}},"created_at":"2026-07-05T10:38:02.625867+00:00","updated_at":"2026-07-05T10:38:02.625867+00:00"}