{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UNQTC3OY44BAJEBLIQITL5ZY5N","short_pith_number":"pith:UNQTC3OY","schema_version":"1.0","canonical_sha256":"a361316dd8e70204902b441135f738eb4557d8a5feecdf786211bb87bbf8e039","source":{"kind":"arxiv","id":"2607.17855","version":1},"attestation_state":"computed","paper":{"title":"A Hardware-oriented Approach for Efficient Bayesian Inference Computation and Deployment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alessio Burrello, Conor Heins, Igor Jovan\\v{c}evi\\'c, Matteo Risso, Miguel de Prado, Nikola Milovi\\'c, Nikola Pi\\v{z}urica","submitted_at":"2026-07-20T11:52:14Z","abstract_excerpt":"Bayesian inference provides a principled foundation for reasoning under uncertainty, but its computational cost hinders deployment on resource-constrained edge devices. In this paper, we present a hardware-oriented methodology for accelerating discrete Bayesian inference on commercial off-the-shelf embedded GPUs. We identify that the latency of a broad class of variational message-passing algorithms is dominated by tensor contractions. Our approach restructures the memory layout of these operations using two complementary merging strategies that produce compact, regularly-shaped primitives bet"},"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":"2607.17855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T11:52:14Z","cross_cats_sorted":[],"title_canon_sha256":"ff3125bb01f4c694264a86e0d51b21a280940d6460a65acbc29223325fb8cf43","abstract_canon_sha256":"96bb29ca23c4b1e199d102cb8fad5aa9154cbdff3b9d31bef22e28e5131217fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:03.669793Z","signature_b64":"hQQdXjktNt5w1o8PkMLg45hZdpd86cwgJzKPvAQJg9W0yNhHiVjhXgFpdJ/UHkJzse8EKEXREI/6OV/E3lKSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a361316dd8e70204902b441135f738eb4557d8a5feecdf786211bb87bbf8e039","last_reissued_at":"2026-07-21T02:22:03.668862Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:03.668862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hardware-oriented Approach for Efficient Bayesian Inference Computation and Deployment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alessio Burrello, Conor Heins, Igor Jovan\\v{c}evi\\'c, Matteo Risso, Miguel de Prado, Nikola Milovi\\'c, Nikola Pi\\v{z}urica","submitted_at":"2026-07-20T11:52:14Z","abstract_excerpt":"Bayesian inference provides a principled foundation for reasoning under uncertainty, but its computational cost hinders deployment on resource-constrained edge devices. In this paper, we present a hardware-oriented methodology for accelerating discrete Bayesian inference on commercial off-the-shelf embedded GPUs. We identify that the latency of a broad class of variational message-passing algorithms is dominated by tensor contractions. Our approach restructures the memory layout of these operations using two complementary merging strategies that produce compact, regularly-shaped primitives bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17855","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/2607.17855/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":"2607.17855","created_at":"2026-07-21T02:22:03.669298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17855v1","created_at":"2026-07-21T02:22:03.669298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17855","created_at":"2026-07-21T02:22:03.669298+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNQTC3OY44BA","created_at":"2026-07-21T02:22:03.669298+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNQTC3OY44BAJEBL","created_at":"2026-07-21T02:22:03.669298+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNQTC3OY","created_at":"2026-07-21T02:22:03.669298+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/UNQTC3OY44BAJEBLIQITL5ZY5N","json":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N.json","graph_json":"https://pith.science/api/pith-number/UNQTC3OY44BAJEBLIQITL5ZY5N/graph.json","events_json":"https://pith.science/api/pith-number/UNQTC3OY44BAJEBLIQITL5ZY5N/events.json","paper":"https://pith.science/paper/UNQTC3OY"},"agent_actions":{"view_html":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N","download_json":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N.json","view_paper":"https://pith.science/paper/UNQTC3OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17855&json=true","fetch_graph":"https://pith.science/api/pith-number/UNQTC3OY44BAJEBLIQITL5ZY5N/graph.json","fetch_events":"https://pith.science/api/pith-number/UNQTC3OY44BAJEBLIQITL5ZY5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N/action/storage_attestation","attest_author":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N/action/author_attestation","sign_citation":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N/action/citation_signature","submit_replication":"https://pith.science/pith/UNQTC3OY44BAJEBLIQITL5ZY5N/action/replication_record"}},"created_at":"2026-07-21T02:22:03.669298+00:00","updated_at":"2026-07-21T02:22:03.669298+00:00"}