{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JKMLER6UVDL4DNEG2YFGCZU22G","short_pith_number":"pith:JKMLER6U","schema_version":"1.0","canonical_sha256":"4a98b247d4a8d7c1b486d60a61669ad1a1a1f667c9c7a6648d098e29b28c976e","source":{"kind":"arxiv","id":"2605.17898","version":1},"attestation_state":"computed","paper":{"title":"Lightweight Gaussian Process Inference in C++ on Metal and CUDA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yu-Hsueh Fang","submitted_at":"2026-05-18T06:03:39Z","abstract_excerpt":"Gaussian process (GP) inference in Python is dominated by libraries such as GPyTorch and GPflow, which are built on deep-learning frameworks and inherit their dispatch overhead and dependency footprint. We present LightGP, a dependency-free C++17 library for GP regression with Python bindings, supporting Apple Metal and NVIDIA CUDA backends alongside tuned CPU paths via Apple Accelerate and OpenBLAS. LightGP provides four inference paths -- exact Cholesky, matrix-free conjugate gradients, sparse variational free energy, and structured kernel interpolation with FFT -- covering problems from $N{"},"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":"2605.17898","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T06:03:39Z","cross_cats_sorted":[],"title_canon_sha256":"b7bb3d0631d7dc35193fe297c938e2589a0f9531f739be72af73eb1eb1120390","abstract_canon_sha256":"bc68581d76456527dcc8124f74664a4f6bf065b40ed4b9a3f42206391e337c07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:04.615503Z","signature_b64":"LXnmYM3e8jOWqp3yzY9sjzE4bZWJGKyi//iikc/rZQgbfS8Fuz8346urauysMilxvoT3ew8Nv7gB/GetSv93CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a98b247d4a8d7c1b486d60a61669ad1a1a1f667c9c7a6648d098e29b28c976e","last_reissued_at":"2026-05-20T00:05:04.614740Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:04.614740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lightweight Gaussian Process Inference in C++ on Metal and CUDA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yu-Hsueh Fang","submitted_at":"2026-05-18T06:03:39Z","abstract_excerpt":"Gaussian process (GP) inference in Python is dominated by libraries such as GPyTorch and GPflow, which are built on deep-learning frameworks and inherit their dispatch overhead and dependency footprint. We present LightGP, a dependency-free C++17 library for GP regression with Python bindings, supporting Apple Metal and NVIDIA CUDA backends alongside tuned CPU paths via Apple Accelerate and OpenBLAS. LightGP provides four inference paths -- exact Cholesky, matrix-free conjugate gradients, sparse variational free energy, and structured kernel interpolation with FFT -- covering problems from $N{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17898","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/2605.17898/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":"2605.17898","created_at":"2026-05-20T00:05:04.614884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17898v1","created_at":"2026-05-20T00:05:04.614884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17898","created_at":"2026-05-20T00:05:04.614884+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKMLER6UVDL4","created_at":"2026-05-20T00:05:04.614884+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKMLER6UVDL4DNEG","created_at":"2026-05-20T00:05:04.614884+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKMLER6U","created_at":"2026-05-20T00:05:04.614884+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/JKMLER6UVDL4DNEG2YFGCZU22G","json":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G.json","graph_json":"https://pith.science/api/pith-number/JKMLER6UVDL4DNEG2YFGCZU22G/graph.json","events_json":"https://pith.science/api/pith-number/JKMLER6UVDL4DNEG2YFGCZU22G/events.json","paper":"https://pith.science/paper/JKMLER6U"},"agent_actions":{"view_html":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G","download_json":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G.json","view_paper":"https://pith.science/paper/JKMLER6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17898&json=true","fetch_graph":"https://pith.science/api/pith-number/JKMLER6UVDL4DNEG2YFGCZU22G/graph.json","fetch_events":"https://pith.science/api/pith-number/JKMLER6UVDL4DNEG2YFGCZU22G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G/action/storage_attestation","attest_author":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G/action/author_attestation","sign_citation":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G/action/citation_signature","submit_replication":"https://pith.science/pith/JKMLER6UVDL4DNEG2YFGCZU22G/action/replication_record"}},"created_at":"2026-05-20T00:05:04.614884+00:00","updated_at":"2026-05-20T00:05:04.614884+00:00"}