{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:46AABOSWGZ4MNJWI5ETTAHPTEW","short_pith_number":"pith:46AABOSW","canonical_record":{"source":{"id":"2206.01606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-02T12:12:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"acb32e06d7348eda164e83ed8aed880c4fd414cc106adbebdc918e66c2dae490","abstract_canon_sha256":"47cde9f7b43b3b2ddcd5973a559a75d9e739e2f3719ca74dde8390d4096a89a6"},"schema_version":"1.0"},"canonical_sha256":"e78000ba563678c6a6c8e927301df32583d2154fb74082923b4f5b79ec6504b4","source":{"kind":"arxiv","id":"2206.01606","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01606","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01606v2","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01606","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"46AABOSWGZ4M","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"46AABOSWGZ4MNJWI","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"46AABOSW","created_at":"2026-07-05T05:05:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:46AABOSWGZ4MNJWI5ETTAHPTEW","target":"record","payload":{"canonical_record":{"source":{"id":"2206.01606","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-02T12:12:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"acb32e06d7348eda164e83ed8aed880c4fd414cc106adbebdc918e66c2dae490","abstract_canon_sha256":"47cde9f7b43b3b2ddcd5973a559a75d9e739e2f3719ca74dde8390d4096a89a6"},"schema_version":"1.0"},"canonical_sha256":"e78000ba563678c6a6c8e927301df32583d2154fb74082923b4f5b79ec6504b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:06.088554Z","signature_b64":"wz3CGXlzIQWcrwKSpC/pqsynmCJnoRBtv2iIb6I0QIIUi+bK96mb+Bt7gg3eYXOSNKe2lhEClQdtwAw3sfHiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78000ba563678c6a6c8e927301df32583d2154fb74082923b4f5b79ec6504b4","last_reissued_at":"2026-07-05T05:05:06.088127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:06.088127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.01606","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P6/TM/f+ASxeMoRElqUZ3pepzzCNGhS5Lo61HxoY+pR6ymMDvKp+WZGlGqx11HBtgAkrqqWBNFs8uTHbYGpxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:51:34.078734Z"},"content_sha256":"5d2bdf4c4323ccf6516c2da46ebb310ec564d8be01bf63a68ed4568cc86fa004","schema_version":"1.0","event_id":"sha256:5d2bdf4c4323ccf6516c2da46ebb310ec564d8be01bf63a68ed4568cc86fa004"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:46AABOSWGZ4MNJWI5ETTAHPTEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Excess risk analysis for epistemic uncertainty with application to variational inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Futoshi Futami, Issei Sato, Masashi Sugiyama, Naonori Ueda, Tomoharu Iwata","submitted_at":"2022-06-02T12:12:24Z","abstract_excerpt":"Bayesian deep learning plays an important role especially for its ability evaluating epistemic uncertainty (EU). Due to computational complexity issues, approximation methods such as variational inference (VI) have been used in practice to obtain posterior distributions and their generalization abilities have been analyzed extensively, for example, by PAC-Bayesian theory; however, little analysis exists on EU, although many numerical experiments have been conducted on it. In this study, we analyze the EU of supervised learning in approximate Bayesian inference by focusing on its excess risk. F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01606","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/2206.01606/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:05:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W6i6FfunJU8aWU7RGU5zfHfhPuGRA5uocKS0Vp9+pjYPi1LiT1NMFInJTeyJBPJpozpQzdM1XMsdry/3uCEHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:51:34.079107Z"},"content_sha256":"0ff8d8a2119628f7db4fac5582eca29b9a2ec7223ded9fdb4619399678dbfeb3","schema_version":"1.0","event_id":"sha256:0ff8d8a2119628f7db4fac5582eca29b9a2ec7223ded9fdb4619399678dbfeb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46AABOSWGZ4MNJWI5ETTAHPTEW/bundle.json","state_url":"https://pith.science/pith/46AABOSWGZ4MNJWI5ETTAHPTEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46AABOSWGZ4MNJWI5ETTAHPTEW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T14:51:34Z","links":{"resolver":"https://pith.science/pith/46AABOSWGZ4MNJWI5ETTAHPTEW","bundle":"https://pith.science/pith/46AABOSWGZ4MNJWI5ETTAHPTEW/bundle.json","state":"https://pith.science/pith/46AABOSWGZ4MNJWI5ETTAHPTEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46AABOSWGZ4MNJWI5ETTAHPTEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:46AABOSWGZ4MNJWI5ETTAHPTEW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"47cde9f7b43b3b2ddcd5973a559a75d9e739e2f3719ca74dde8390d4096a89a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-02T12:12:24Z","title_canon_sha256":"acb32e06d7348eda164e83ed8aed880c4fd414cc106adbebdc918e66c2dae490"},"schema_version":"1.0","source":{"id":"2206.01606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01606","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01606v2","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01606","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"46AABOSWGZ4M","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"46AABOSWGZ4MNJWI","created_at":"2026-07-05T05:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"46AABOSW","created_at":"2026-07-05T05:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:0ff8d8a2119628f7db4fac5582eca29b9a2ec7223ded9fdb4619399678dbfeb3","target":"graph","created_at":"2026-07-05T05:05:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.01606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bayesian deep learning plays an important role especially for its ability evaluating epistemic uncertainty (EU). Due to computational complexity issues, approximation methods such as variational inference (VI) have been used in practice to obtain posterior distributions and their generalization abilities have been analyzed extensively, for example, by PAC-Bayesian theory; however, little analysis exists on EU, although many numerical experiments have been conducted on it. In this study, we analyze the EU of supervised learning in approximate Bayesian inference by focusing on its excess risk. F","authors_text":"Futoshi Futami, Issei Sato, Masashi Sugiyama, Naonori Ueda, Tomoharu Iwata","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-02T12:12:24Z","title":"Excess risk analysis for epistemic uncertainty with application to variational inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01606","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5d2bdf4c4323ccf6516c2da46ebb310ec564d8be01bf63a68ed4568cc86fa004","target":"record","created_at":"2026-07-05T05:05:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"47cde9f7b43b3b2ddcd5973a559a75d9e739e2f3719ca74dde8390d4096a89a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-02T12:12:24Z","title_canon_sha256":"acb32e06d7348eda164e83ed8aed880c4fd414cc106adbebdc918e66c2dae490"},"schema_version":"1.0","source":{"id":"2206.01606","kind":"arxiv","version":2}},"canonical_sha256":"e78000ba563678c6a6c8e927301df32583d2154fb74082923b4f5b79ec6504b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e78000ba563678c6a6c8e927301df32583d2154fb74082923b4f5b79ec6504b4","first_computed_at":"2026-07-05T05:05:06.088127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:06.088127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wz3CGXlzIQWcrwKSpC/pqsynmCJnoRBtv2iIb6I0QIIUi+bK96mb+Bt7gg3eYXOSNKe2lhEClQdtwAw3sfHiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:06.088554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d2bdf4c4323ccf6516c2da46ebb310ec564d8be01bf63a68ed4568cc86fa004","sha256:0ff8d8a2119628f7db4fac5582eca29b9a2ec7223ded9fdb4619399678dbfeb3"],"state_sha256":"fc2cbfa1df8bbabaf740d93257d84e77c5dcb508360308aafb2859db376e5a94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1ymtJT18ZUuB03ZrL9Gc+bLWcNTFTqLR3xO0V9Tx+4WLt+Kt1sR7qA0ad6GjUKF9P/fdqb9jaZxMMGoSHnTAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:51:34.081119Z","bundle_sha256":"e8bb7f1d086eceee6185f032df68c1ca6ebd248417c66e507991f8f3023da119"}}