{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AJVU2EZHO5VWKZHWKSNMLDCAI2","short_pith_number":"pith:AJVU2EZH","schema_version":"1.0","canonical_sha256":"026b4d1327776b6564f6549ac58c40469e1ff4d07643a10e91bd42888d596535","source":{"kind":"arxiv","id":"2306.10185","version":1},"attestation_state":"computed","paper":{"title":"Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.ET"],"primary_cat":"cs.LG","authors_text":"Guillaume Prenat, Kamal Danouchi, Lorena Anghel, Mehdi B. Tahoori, Michael Hefenbrock, Soyed Tuhin Ahmed","submitted_at":"2023-06-16T21:38:13Z","abstract_excerpt":"Recently, machine learning systems have gained prominence in real-time, critical decision-making domains, such as autonomous driving and industrial automation. Their implementations should avoid overconfident predictions through uncertainty estimation. Bayesian Neural Networks (BayNNs) are principled methods for estimating predictive uncertainty. However, their computational costs and power consumption hinder their widespread deployment in edge AI. Utilizing Dropout as an approximation of the posterior distribution, binarizing the parameters of BayNNs, and further to that implementing them in "},"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":"2306.10185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-16T21:38:13Z","cross_cats_sorted":["cs.AI","cs.AR","cs.ET"],"title_canon_sha256":"5a6893ac3ce4b49474467020ed7ebec9bce2b2d829fb59e61300f9b5c9fe0a0b","abstract_canon_sha256":"ad67735b319853f1a85f17da535bdfed04b1494d6cf658af478beff8a978d7be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:35.069975Z","signature_b64":"Fo1olwZyrixa/GRGlhU3+zTgdYDFlM1Xnu+mMh6Hx+9kmp2Wh22oUVZzy/yDgUDU+uxz0bNCvxz5RviNNXJdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"026b4d1327776b6564f6549ac58c40469e1ff4d07643a10e91bd42888d596535","last_reissued_at":"2026-07-05T06:21:35.069576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:35.069576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.ET"],"primary_cat":"cs.LG","authors_text":"Guillaume Prenat, Kamal Danouchi, Lorena Anghel, Mehdi B. Tahoori, Michael Hefenbrock, Soyed Tuhin Ahmed","submitted_at":"2023-06-16T21:38:13Z","abstract_excerpt":"Recently, machine learning systems have gained prominence in real-time, critical decision-making domains, such as autonomous driving and industrial automation. Their implementations should avoid overconfident predictions through uncertainty estimation. Bayesian Neural Networks (BayNNs) are principled methods for estimating predictive uncertainty. However, their computational costs and power consumption hinder their widespread deployment in edge AI. Utilizing Dropout as an approximation of the posterior distribution, binarizing the parameters of BayNNs, and further to that implementing them in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10185","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/2306.10185/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":"2306.10185","created_at":"2026-07-05T06:21:35.069639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10185v1","created_at":"2026-07-05T06:21:35.069639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10185","created_at":"2026-07-05T06:21:35.069639+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJVU2EZHO5VW","created_at":"2026-07-05T06:21:35.069639+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJVU2EZHO5VWKZHW","created_at":"2026-07-05T06:21:35.069639+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJVU2EZH","created_at":"2026-07-05T06:21:35.069639+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/AJVU2EZHO5VWKZHWKSNMLDCAI2","json":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2.json","graph_json":"https://pith.science/api/pith-number/AJVU2EZHO5VWKZHWKSNMLDCAI2/graph.json","events_json":"https://pith.science/api/pith-number/AJVU2EZHO5VWKZHWKSNMLDCAI2/events.json","paper":"https://pith.science/paper/AJVU2EZH"},"agent_actions":{"view_html":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2","download_json":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2.json","view_paper":"https://pith.science/paper/AJVU2EZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10185&json=true","fetch_graph":"https://pith.science/api/pith-number/AJVU2EZHO5VWKZHWKSNMLDCAI2/graph.json","fetch_events":"https://pith.science/api/pith-number/AJVU2EZHO5VWKZHWKSNMLDCAI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2/action/storage_attestation","attest_author":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2/action/author_attestation","sign_citation":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2/action/citation_signature","submit_replication":"https://pith.science/pith/AJVU2EZHO5VWKZHWKSNMLDCAI2/action/replication_record"}},"created_at":"2026-07-05T06:21:35.069639+00:00","updated_at":"2026-07-05T06:21:35.069639+00:00"}