{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:A7XI2LOVGQPFOHNDBQHBYPIXBU","short_pith_number":"pith:A7XI2LOV","schema_version":"1.0","canonical_sha256":"07ee8d2dd5341e571da30c0e1c3d170d310387e111c3c0c22df28b7a9945df05","source":{"kind":"arxiv","id":"2206.00794","version":2},"attestation_state":"computed","paper":{"title":"Sequential Bayesian Neural Subnetwork Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Byung-Jun Yoon, Nathan M. Urban, Prasanna Balaprakash, Sandeep Madireddy, Sanket Jantre, Shrijita Bhattacharya, Tapabrata Maiti","submitted_at":"2022-06-01T22:57:52Z","abstract_excerpt":"Deep ensembles have emerged as a powerful technique for improving predictive performance and enhancing model robustness across various applications by leveraging model diversity. However, traditional deep ensemble methods are often computationally expensive and rely on deterministic models, which may limit their flexibility. Additionally, while sparse subnetworks of dense models have shown promise in matching the performance of their dense counterparts and even enhancing robustness, existing methods for inducing sparsity typically incur training costs comparable to those of training a single d"},"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":"2206.00794","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-01T22:57:52Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"baa6c099dd297ac1dc497397d4c849743a13be1a07bff7ce4f7ef133269f9e93","abstract_canon_sha256":"cbe816a1a77ff95dbde1786a104e2f17364b9f3ce3cf311915e09dc0b453c513"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:54.616265Z","signature_b64":"J+trq/JoSbhqlp/KFSJiWG539c9h+AkyZ94ymlO0LzZCVdwvCKfJpTZPi8C3aEaqaDSaAd8Ff8x5RKET6i+VBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07ee8d2dd5341e571da30c0e1c3d170d310387e111c3c0c22df28b7a9945df05","last_reissued_at":"2026-07-05T08:56:54.615841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:54.615841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequential Bayesian Neural Subnetwork Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Byung-Jun Yoon, Nathan M. Urban, Prasanna Balaprakash, Sandeep Madireddy, Sanket Jantre, Shrijita Bhattacharya, Tapabrata Maiti","submitted_at":"2022-06-01T22:57:52Z","abstract_excerpt":"Deep ensembles have emerged as a powerful technique for improving predictive performance and enhancing model robustness across various applications by leveraging model diversity. However, traditional deep ensemble methods are often computationally expensive and rely on deterministic models, which may limit their flexibility. Additionally, while sparse subnetworks of dense models have shown promise in matching the performance of their dense counterparts and even enhancing robustness, existing methods for inducing sparsity typically incur training costs comparable to those of training a single d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00794","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/2206.00794/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":"2206.00794","created_at":"2026-07-05T08:56:54.615891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00794v2","created_at":"2026-07-05T08:56:54.615891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00794","created_at":"2026-07-05T08:56:54.615891+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7XI2LOVGQPF","created_at":"2026-07-05T08:56:54.615891+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7XI2LOVGQPFOHND","created_at":"2026-07-05T08:56:54.615891+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7XI2LOV","created_at":"2026-07-05T08:56:54.615891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06173","citing_title":"Uncertainty-Aware Adaptation of Large Language Models for Protein-Protein Interaction Analysis","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU","json":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU.json","graph_json":"https://pith.science/api/pith-number/A7XI2LOVGQPFOHNDBQHBYPIXBU/graph.json","events_json":"https://pith.science/api/pith-number/A7XI2LOVGQPFOHNDBQHBYPIXBU/events.json","paper":"https://pith.science/paper/A7XI2LOV"},"agent_actions":{"view_html":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU","download_json":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU.json","view_paper":"https://pith.science/paper/A7XI2LOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00794&json=true","fetch_graph":"https://pith.science/api/pith-number/A7XI2LOVGQPFOHNDBQHBYPIXBU/graph.json","fetch_events":"https://pith.science/api/pith-number/A7XI2LOVGQPFOHNDBQHBYPIXBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU/action/storage_attestation","attest_author":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU/action/author_attestation","sign_citation":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU/action/citation_signature","submit_replication":"https://pith.science/pith/A7XI2LOVGQPFOHNDBQHBYPIXBU/action/replication_record"}},"created_at":"2026-07-05T08:56:54.615891+00:00","updated_at":"2026-07-05T08:56:54.615891+00:00"}