{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7JOVL3YM2XD4FYUNMBSTQ35MCW","short_pith_number":"pith:7JOVL3YM","schema_version":"1.0","canonical_sha256":"fa5d55ef0cd5c7c2e28d6065386fac1593bfbe153730819283859f20923eb03a","source":{"kind":"arxiv","id":"2206.00944","version":1},"attestation_state":"computed","paper":{"title":"Feature Space Particle Inference for Neural Network Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ikuro Sato, Kohta Ishikawa, Rei Kawakami, Shingo Yashima, Teppei Suzuki","submitted_at":"2022-06-02T09:16:26Z","abstract_excerpt":"Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-based inference methods offer a promising approach from a Bayesian perspective. However, the best way to apply these methods to neural networks is still unclear: seeking samples from the weight-space posterior suffers from inefficiency due to the over-parameterization issues, while seeking samples directly from the function-space posterior often results in serious underfitting. In this study, we propose optimizing parti"},"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":"2206.00944","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T09:16:26Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"7f6a980c3317a38ae925305d0be4ad9b0f63d662f493960142ba277c71a78f5b","abstract_canon_sha256":"95db8e0867e03f814d9e485907a9b8afdaa1827a667733b2b8bd249cc4ac0092"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:35.324634Z","signature_b64":"Bln4lA6Wav2bu+aRPrGuEBBRo+G42PYp5hgV3YItz9Zf6Fe40JckxBrLt+UgGjlp6whI3I6x0L18bHO/pC8PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa5d55ef0cd5c7c2e28d6065386fac1593bfbe153730819283859f20923eb03a","last_reissued_at":"2026-07-05T04:28:35.324181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:35.324181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Space Particle Inference for Neural Network Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ikuro Sato, Kohta Ishikawa, Rei Kawakami, Shingo Yashima, Teppei Suzuki","submitted_at":"2022-06-02T09:16:26Z","abstract_excerpt":"Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-based inference methods offer a promising approach from a Bayesian perspective. However, the best way to apply these methods to neural networks is still unclear: seeking samples from the weight-space posterior suffers from inefficiency due to the over-parameterization issues, while seeking samples directly from the function-space posterior often results in serious underfitting. In this study, we propose optimizing parti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00944","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/2206.00944/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":"2206.00944","created_at":"2026-07-05T04:28:35.324240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00944v1","created_at":"2026-07-05T04:28:35.324240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00944","created_at":"2026-07-05T04:28:35.324240+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JOVL3YM2XD4","created_at":"2026-07-05T04:28:35.324240+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JOVL3YM2XD4FYUN","created_at":"2026-07-05T04:28:35.324240+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JOVL3YM","created_at":"2026-07-05T04:28:35.324240+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/7JOVL3YM2XD4FYUNMBSTQ35MCW","json":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW.json","graph_json":"https://pith.science/api/pith-number/7JOVL3YM2XD4FYUNMBSTQ35MCW/graph.json","events_json":"https://pith.science/api/pith-number/7JOVL3YM2XD4FYUNMBSTQ35MCW/events.json","paper":"https://pith.science/paper/7JOVL3YM"},"agent_actions":{"view_html":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW","download_json":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW.json","view_paper":"https://pith.science/paper/7JOVL3YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00944&json=true","fetch_graph":"https://pith.science/api/pith-number/7JOVL3YM2XD4FYUNMBSTQ35MCW/graph.json","fetch_events":"https://pith.science/api/pith-number/7JOVL3YM2XD4FYUNMBSTQ35MCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW/action/storage_attestation","attest_author":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW/action/author_attestation","sign_citation":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW/action/citation_signature","submit_replication":"https://pith.science/pith/7JOVL3YM2XD4FYUNMBSTQ35MCW/action/replication_record"}},"created_at":"2026-07-05T04:28:35.324240+00:00","updated_at":"2026-07-05T04:28:35.324240+00:00"}