{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YBBMJH6KBZMZSVDVCVR6ZJZTKR","short_pith_number":"pith:YBBMJH6K","schema_version":"1.0","canonical_sha256":"c042c49fca0e599954751563eca733544ffc686cb4b6ffbacb9a7423d5671bbe","source":{"kind":"arxiv","id":"2311.15816","version":2},"attestation_state":"computed","paper":{"title":"Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET"],"primary_cat":"cs.LG","authors_text":"Guillaume Prenat, Kamal Danouchi, Lorena Anghel, Mehdi B. Tahoori, Michael Hefenbrock, Soyed Tuhin Ahmed","submitted_at":"2023-11-27T13:41:20Z","abstract_excerpt":"Uncertainty estimation in Neural Networks (NNs) is vital in improving reliability and confidence in predictions, particularly in safety-critical applications. Bayesian Neural Networks (BayNNs) with Dropout as an approximation offer a systematic approach to quantifying uncertainty, but they inherently suffer from high hardware overhead in terms of power, memory, and computation. Thus, the applicability of BayNNs to edge devices with limited resources or to high-performance applications is challenging. Some of the inherent costs of BayNNs can be reduced by accelerating them in hardware on a Comp"},"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":"2311.15816","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T13:41:20Z","cross_cats_sorted":["cs.AI","cs.ET"],"title_canon_sha256":"f0714b0592adfa616b5f71afc053da44af43851138f20090bd79a8c216cd0dce","abstract_canon_sha256":"ee35ab6dba7611fe1b897057b2fdc67d7c8c69c37d364e1adea02ec4d64f8d9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:25.127942Z","signature_b64":"S7oZ3Ht0W9Sr5T3vG2vbiVSCKD/3GQaLBlgHYyIgYjo2wXMY6JcFrqWEDbhJLN3wFLv7mSAvGVbJQALoNMmxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c042c49fca0e599954751563eca733544ffc686cb4b6ffbacb9a7423d5671bbe","last_reissued_at":"2026-07-05T07:32:25.127416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:25.127416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET"],"primary_cat":"cs.LG","authors_text":"Guillaume Prenat, Kamal Danouchi, Lorena Anghel, Mehdi B. Tahoori, Michael Hefenbrock, Soyed Tuhin Ahmed","submitted_at":"2023-11-27T13:41:20Z","abstract_excerpt":"Uncertainty estimation in Neural Networks (NNs) is vital in improving reliability and confidence in predictions, particularly in safety-critical applications. Bayesian Neural Networks (BayNNs) with Dropout as an approximation offer a systematic approach to quantifying uncertainty, but they inherently suffer from high hardware overhead in terms of power, memory, and computation. Thus, the applicability of BayNNs to edge devices with limited resources or to high-performance applications is challenging. Some of the inherent costs of BayNNs can be reduced by accelerating them in hardware on a Comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15816","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/2311.15816/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":"2311.15816","created_at":"2026-07-05T07:32:25.127486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15816v2","created_at":"2026-07-05T07:32:25.127486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15816","created_at":"2026-07-05T07:32:25.127486+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBBMJH6KBZMZ","created_at":"2026-07-05T07:32:25.127486+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBBMJH6KBZMZSVDV","created_at":"2026-07-05T07:32:25.127486+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBBMJH6K","created_at":"2026-07-05T07:32:25.127486+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/YBBMJH6KBZMZSVDVCVR6ZJZTKR","json":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR.json","graph_json":"https://pith.science/api/pith-number/YBBMJH6KBZMZSVDVCVR6ZJZTKR/graph.json","events_json":"https://pith.science/api/pith-number/YBBMJH6KBZMZSVDVCVR6ZJZTKR/events.json","paper":"https://pith.science/paper/YBBMJH6K"},"agent_actions":{"view_html":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR","download_json":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR.json","view_paper":"https://pith.science/paper/YBBMJH6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15816&json=true","fetch_graph":"https://pith.science/api/pith-number/YBBMJH6KBZMZSVDVCVR6ZJZTKR/graph.json","fetch_events":"https://pith.science/api/pith-number/YBBMJH6KBZMZSVDVCVR6ZJZTKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR/action/storage_attestation","attest_author":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR/action/author_attestation","sign_citation":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR/action/citation_signature","submit_replication":"https://pith.science/pith/YBBMJH6KBZMZSVDVCVR6ZJZTKR/action/replication_record"}},"created_at":"2026-07-05T07:32:25.127486+00:00","updated_at":"2026-07-05T07:32:25.127486+00:00"}