{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KTTV7XEGL3DUPJZZ5LQT2PFG5B","short_pith_number":"pith:KTTV7XEG","schema_version":"1.0","canonical_sha256":"54e75fdc865ec747a739eae13d3ca6e866e5c45b3d909ff74ca95ef4307af78a","source":{"kind":"arxiv","id":"2111.11306","version":2},"attestation_state":"computed","paper":{"title":"Learning PSD-valued functions using kernel sums-of-squares","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Rudi, Boris Muzellec, Francis Bach","submitted_at":"2021-11-22T16:07:50Z","abstract_excerpt":"Shape constraints such as positive semi-definiteness (PSD) for matrices or convexity for functions play a central role in many applications in machine learning and sciences, including metric learning, optimal transport, and economics. Yet, very few function models exist that enforce PSD-ness or convexity with good empirical performance and theoretical guarantees. In this paper, we introduce a kernel sum-of-squares model for functions that take values in the PSD cone, which extends kernel sums-of-squares models that were recently proposed to encode non-negative scalar functions. We provide a re"},"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":"2111.11306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-11-22T16:07:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"366aef2a387296861d6ff65851c31e669b21856761f9ab230155c6fbc3c6d5ba","abstract_canon_sha256":"d80b90e4b8d0e0ebf596345b11c830897970856d40bb717e59512d766253e190"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:52.749073Z","signature_b64":"OaOZyNuBRiDOhs3PuXLIiTYeg4qRZFI3DSe1XeQSn+bJyWs1I823t/lP8ptK720L5xue5xwjYGce4juJkUucDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54e75fdc865ec747a739eae13d3ca6e866e5c45b3d909ff74ca95ef4307af78a","last_reissued_at":"2026-07-05T03:50:52.748588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:52.748588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning PSD-valued functions using kernel sums-of-squares","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Rudi, Boris Muzellec, Francis Bach","submitted_at":"2021-11-22T16:07:50Z","abstract_excerpt":"Shape constraints such as positive semi-definiteness (PSD) for matrices or convexity for functions play a central role in many applications in machine learning and sciences, including metric learning, optimal transport, and economics. Yet, very few function models exist that enforce PSD-ness or convexity with good empirical performance and theoretical guarantees. In this paper, we introduce a kernel sum-of-squares model for functions that take values in the PSD cone, which extends kernel sums-of-squares models that were recently proposed to encode non-negative scalar functions. We provide a re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11306","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/2111.11306/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":"2111.11306","created_at":"2026-07-05T03:50:52.748648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11306v2","created_at":"2026-07-05T03:50:52.748648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11306","created_at":"2026-07-05T03:50:52.748648+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTTV7XEGL3DU","created_at":"2026-07-05T03:50:52.748648+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTTV7XEGL3DUPJZZ","created_at":"2026-07-05T03:50:52.748648+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTTV7XEG","created_at":"2026-07-05T03:50:52.748648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12163","citing_title":"Kernel-based identification of nonlinear port-Hamiltonian systems","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B","json":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B.json","graph_json":"https://pith.science/api/pith-number/KTTV7XEGL3DUPJZZ5LQT2PFG5B/graph.json","events_json":"https://pith.science/api/pith-number/KTTV7XEGL3DUPJZZ5LQT2PFG5B/events.json","paper":"https://pith.science/paper/KTTV7XEG"},"agent_actions":{"view_html":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B","download_json":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B.json","view_paper":"https://pith.science/paper/KTTV7XEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11306&json=true","fetch_graph":"https://pith.science/api/pith-number/KTTV7XEGL3DUPJZZ5LQT2PFG5B/graph.json","fetch_events":"https://pith.science/api/pith-number/KTTV7XEGL3DUPJZZ5LQT2PFG5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B/action/storage_attestation","attest_author":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B/action/author_attestation","sign_citation":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B/action/citation_signature","submit_replication":"https://pith.science/pith/KTTV7XEGL3DUPJZZ5LQT2PFG5B/action/replication_record"}},"created_at":"2026-07-05T03:50:52.748648+00:00","updated_at":"2026-07-05T03:50:52.748648+00:00"}