{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHYG3FB66WQS6CQQESAPUBIMMM","short_pith_number":"pith:NHYG3FB6","schema_version":"1.0","canonical_sha256":"69f06d943ef5a12f0a102480fa050c631033944d8c32a2bbb960bd540451081e","source":{"kind":"arxiv","id":"2505.17856","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Weight Sharing for Bayesian Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrea Patane, Goetz Botterweck, Moule Lin, Shuhao Guan, Weipeng Jing","submitted_at":"2025-05-23T13:07:18Z","abstract_excerpt":"While offering a principled framework for uncertainty quantification in deep learning, the employment of Bayesian Neural Networks (BNNs) is still constrained by their increased computational requirements and the convergence difficulties when training very deep, state-of-the-art architectures. In this work, we reinterpret weight-sharing quantization techniques from a stochastic perspective in the context of training and inference with Bayesian Neural Networks (BNNs). Specifically, we leverage 2D adaptive Gaussian distributions, Wasserstein distance estimations, and alpha blending to encode the "},"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":"2505.17856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T13:07:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd629c68671593fb6e44a754143b28ee0df18048a0e204318fa493758ee8fea7","abstract_canon_sha256":"357791de4cff8650bc7be15877f5f08b36ade02c69564df096dea5e15175f3cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:32.933590Z","signature_b64":"joFS5VGEc2UOklqW55MFrfKWZRzWiIcCrI0he/rrsvbT++CoH+L+iDP8XSK3s1b6bhcP2gsk1sFtzpCAeKmhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69f06d943ef5a12f0a102480fa050c631033944d8c32a2bbb960bd540451081e","last_reissued_at":"2026-07-05T11:08:32.933109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:32.933109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Weight Sharing for Bayesian Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrea Patane, Goetz Botterweck, Moule Lin, Shuhao Guan, Weipeng Jing","submitted_at":"2025-05-23T13:07:18Z","abstract_excerpt":"While offering a principled framework for uncertainty quantification in deep learning, the employment of Bayesian Neural Networks (BNNs) is still constrained by their increased computational requirements and the convergence difficulties when training very deep, state-of-the-art architectures. In this work, we reinterpret weight-sharing quantization techniques from a stochastic perspective in the context of training and inference with Bayesian Neural Networks (BNNs). Specifically, we leverage 2D adaptive Gaussian distributions, Wasserstein distance estimations, and alpha blending to encode the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17856","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/2505.17856/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":"2505.17856","created_at":"2026-07-05T11:08:32.933165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17856v1","created_at":"2026-07-05T11:08:32.933165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17856","created_at":"2026-07-05T11:08:32.933165+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHYG3FB66WQS","created_at":"2026-07-05T11:08:32.933165+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHYG3FB66WQS6CQQ","created_at":"2026-07-05T11:08:32.933165+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHYG3FB6","created_at":"2026-07-05T11:08:32.933165+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/NHYG3FB66WQS6CQQESAPUBIMMM","json":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM.json","graph_json":"https://pith.science/api/pith-number/NHYG3FB66WQS6CQQESAPUBIMMM/graph.json","events_json":"https://pith.science/api/pith-number/NHYG3FB66WQS6CQQESAPUBIMMM/events.json","paper":"https://pith.science/paper/NHYG3FB6"},"agent_actions":{"view_html":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM","download_json":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM.json","view_paper":"https://pith.science/paper/NHYG3FB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17856&json=true","fetch_graph":"https://pith.science/api/pith-number/NHYG3FB66WQS6CQQESAPUBIMMM/graph.json","fetch_events":"https://pith.science/api/pith-number/NHYG3FB66WQS6CQQESAPUBIMMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM/action/storage_attestation","attest_author":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM/action/author_attestation","sign_citation":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM/action/citation_signature","submit_replication":"https://pith.science/pith/NHYG3FB66WQS6CQQESAPUBIMMM/action/replication_record"}},"created_at":"2026-07-05T11:08:32.933165+00:00","updated_at":"2026-07-05T11:08:32.933165+00:00"}