{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VZZMNIMNNPE4FNTIGPAZNF26OY","short_pith_number":"pith:VZZMNIMN","schema_version":"1.0","canonical_sha256":"ae72c6a18d6bc9c2b66833c196975e762650e070fc1e276066c2f8b9b53be75a","source":{"kind":"arxiv","id":"2501.06962","version":1},"attestation_state":"computed","paper":{"title":"Compact Bayesian Neural Networks via pruned MCMC sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jody M. Webster, Ratneel Deo, Rohitash Chandra, Scott Sisson","submitted_at":"2025-01-12T22:48:04Z","abstract_excerpt":"Bayesian Neural Networks (BNNs) offer robust uncertainty quantification in model predictions, but training them presents a significant computational challenge. This is mainly due to the problem of sampling multimodal posterior distributions using Markov Chain Monte Carlo (MCMC) sampling and variational inference algorithms. Moreover, the number of model parameters scales exponentially with additional hidden layers, neurons, and features in the dataset. Typically, a significant portion of these densely connected parameters are redundant and pruning a neural network not only improves portability"},"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":"2501.06962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-12T22:48:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5319b4d3de1df5b06451e2e79677eb6639f31bb156145195f5f8a8c8289365f5","abstract_canon_sha256":"998027766b6893680dbcdc0d2eb7a97e65b0529e5a2a65adcbe02e1d9befbe8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:13.012659Z","signature_b64":"sLYiT8Jx4tjluFSR8kOGJ4CFHy+ujbP/UnVZQirYT58kUEjRam+JCkH3jWxTvc19gWZlMTmmuRaahqQiFR9dDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae72c6a18d6bc9c2b66833c196975e762650e070fc1e276066c2f8b9b53be75a","last_reissued_at":"2026-07-05T10:00:13.012158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:13.012158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compact Bayesian Neural Networks via pruned MCMC sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jody M. Webster, Ratneel Deo, Rohitash Chandra, Scott Sisson","submitted_at":"2025-01-12T22:48:04Z","abstract_excerpt":"Bayesian Neural Networks (BNNs) offer robust uncertainty quantification in model predictions, but training them presents a significant computational challenge. This is mainly due to the problem of sampling multimodal posterior distributions using Markov Chain Monte Carlo (MCMC) sampling and variational inference algorithms. Moreover, the number of model parameters scales exponentially with additional hidden layers, neurons, and features in the dataset. Typically, a significant portion of these densely connected parameters are redundant and pruning a neural network not only improves portability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06962","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/2501.06962/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":"2501.06962","created_at":"2026-07-05T10:00:13.012221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06962v1","created_at":"2026-07-05T10:00:13.012221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06962","created_at":"2026-07-05T10:00:13.012221+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZZMNIMNNPE4","created_at":"2026-07-05T10:00:13.012221+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZZMNIMNNPE4FNTI","created_at":"2026-07-05T10:00:13.012221+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZZMNIMN","created_at":"2026-07-05T10:00:13.012221+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/VZZMNIMNNPE4FNTIGPAZNF26OY","json":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY.json","graph_json":"https://pith.science/api/pith-number/VZZMNIMNNPE4FNTIGPAZNF26OY/graph.json","events_json":"https://pith.science/api/pith-number/VZZMNIMNNPE4FNTIGPAZNF26OY/events.json","paper":"https://pith.science/paper/VZZMNIMN"},"agent_actions":{"view_html":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY","download_json":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY.json","view_paper":"https://pith.science/paper/VZZMNIMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06962&json=true","fetch_graph":"https://pith.science/api/pith-number/VZZMNIMNNPE4FNTIGPAZNF26OY/graph.json","fetch_events":"https://pith.science/api/pith-number/VZZMNIMNNPE4FNTIGPAZNF26OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY/action/storage_attestation","attest_author":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY/action/author_attestation","sign_citation":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY/action/citation_signature","submit_replication":"https://pith.science/pith/VZZMNIMNNPE4FNTIGPAZNF26OY/action/replication_record"}},"created_at":"2026-07-05T10:00:13.012221+00:00","updated_at":"2026-07-05T10:00:13.012221+00:00"}