{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HK6UW7WLIA455GH7UPDK3CAMOR","short_pith_number":"pith:HK6UW7WL","canonical_record":{"source":{"id":"1902.01080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-04T08:39:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4b11f8e24593fe6fd330352eb742a5712c309a280cf27ca46a3c13f28447c28c","abstract_canon_sha256":"056dc8d83aec85ceeb7d1d2ee63dfa3c0a355a6180ee614a70025ade3bbbf9ac"},"schema_version":"1.0"},"canonical_sha256":"3abd4b7ecb4039de98ffa3c6ad880c7479fe31bdd5d2f1e66a6d5ae330360c96","source":{"kind":"arxiv","id":"1902.01080","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01080","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01080v2","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01080","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"HK6UW7WLIA45","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"HK6UW7WLIA455GH7","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"HK6UW7WL","created_at":"2026-07-05T00:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HK6UW7WLIA455GH7UPDK3CAMOR","target":"record","payload":{"canonical_record":{"source":{"id":"1902.01080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-04T08:39:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4b11f8e24593fe6fd330352eb742a5712c309a280cf27ca46a3c13f28447c28c","abstract_canon_sha256":"056dc8d83aec85ceeb7d1d2ee63dfa3c0a355a6180ee614a70025ade3bbbf9ac"},"schema_version":"1.0"},"canonical_sha256":"3abd4b7ecb4039de98ffa3c6ad880c7479fe31bdd5d2f1e66a6d5ae330360c96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:46.323046Z","signature_b64":"mEKx2Owfw5dhuslfU2ZUcd8q2fvOW95ZUBoa2tXju+UUOUO01Uwz6OgB3pokWpa+OWtUBhCwRpQBafjlxMoeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3abd4b7ecb4039de98ffa3c6ad880c7479fe31bdd5d2f1e66a6d5ae330360c96","last_reissued_at":"2026-07-05T00:28:46.322532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:46.322532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.01080","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":"2026-07-05T00:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0BEmX6iJF8l7xYMu3XDMTs91FnRu1eo6dLnFwCZFxW6/mON0B80ILNueRW8mPJPllJxh+6xW49cUnb6MWqoRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:00:26.717803Z"},"content_sha256":"b46912dc085a35a2ba0bed93662063bd203d619d3be799e3b9cc5ea369c298b1","schema_version":"1.0","event_id":"sha256:b46912dc085a35a2ba0bed93662063bd203d619d3be799e3b9cc5ea369c298b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HK6UW7WLIA455GH7UPDK3CAMOR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Predictive Uncertainty Quantification with Compound Density Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Agustinus Kristiadi, Asja Fischer, Sina D\\\"aubener","submitted_at":"2019-02-04T08:39:06Z","abstract_excerpt":"Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are one of the most popular approaches to uncertainty quantification. On the other hand, it was recently shown that ensembles of NNs, which belong to the class of mixture models, can be used to quantify prediction uncertainty. In this paper, we build upon these two approaches. First, we increase the mixture model's flexibility by replacing the fixed mixing weights by an adaptive, input-dependent distribution (specifying "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01080","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/1902.01080/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":"2026-07-05T00:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErRAytmqzGGRS+EVcYUVW4YaR3JIMlwcNHjEkGg1zpbASJaasvhEFJScKNH0QmPIWtFQB74z7lmjcNtSjTfSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:00:26.719016Z"},"content_sha256":"02c08f427bba1ec3f51420121287f82a396d352b687bc9e1459ddae40c8586d5","schema_version":"1.0","event_id":"sha256:02c08f427bba1ec3f51420121287f82a396d352b687bc9e1459ddae40c8586d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HK6UW7WLIA455GH7UPDK3CAMOR/bundle.json","state_url":"https://pith.science/pith/HK6UW7WLIA455GH7UPDK3CAMOR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HK6UW7WLIA455GH7UPDK3CAMOR/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":"2026-08-13T08:00:26Z","links":{"resolver":"https://pith.science/pith/HK6UW7WLIA455GH7UPDK3CAMOR","bundle":"https://pith.science/pith/HK6UW7WLIA455GH7UPDK3CAMOR/bundle.json","state":"https://pith.science/pith/HK6UW7WLIA455GH7UPDK3CAMOR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HK6UW7WLIA455GH7UPDK3CAMOR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HK6UW7WLIA455GH7UPDK3CAMOR","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":"056dc8d83aec85ceeb7d1d2ee63dfa3c0a355a6180ee614a70025ade3bbbf9ac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-04T08:39:06Z","title_canon_sha256":"4b11f8e24593fe6fd330352eb742a5712c309a280cf27ca46a3c13f28447c28c"},"schema_version":"1.0","source":{"id":"1902.01080","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.01080","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.01080v2","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01080","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"HK6UW7WLIA45","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"HK6UW7WLIA455GH7","created_at":"2026-07-05T00:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"HK6UW7WL","created_at":"2026-07-05T00:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:02c08f427bba1ec3f51420121287f82a396d352b687bc9e1459ddae40c8586d5","target":"graph","created_at":"2026-07-05T00:28:46Z","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/1902.01080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are one of the most popular approaches to uncertainty quantification. On the other hand, it was recently shown that ensembles of NNs, which belong to the class of mixture models, can be used to quantify prediction uncertainty. In this paper, we build upon these two approaches. First, we increase the mixture model's flexibility by replacing the fixed mixing weights by an adaptive, input-dependent distribution (specifying ","authors_text":"Agustinus Kristiadi, Asja Fischer, Sina D\\\"aubener","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-04T08:39:06Z","title":"Predictive Uncertainty Quantification with Compound Density Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01080","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:b46912dc085a35a2ba0bed93662063bd203d619d3be799e3b9cc5ea369c298b1","target":"record","created_at":"2026-07-05T00:28:46Z","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":"056dc8d83aec85ceeb7d1d2ee63dfa3c0a355a6180ee614a70025ade3bbbf9ac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-04T08:39:06Z","title_canon_sha256":"4b11f8e24593fe6fd330352eb742a5712c309a280cf27ca46a3c13f28447c28c"},"schema_version":"1.0","source":{"id":"1902.01080","kind":"arxiv","version":2}},"canonical_sha256":"3abd4b7ecb4039de98ffa3c6ad880c7479fe31bdd5d2f1e66a6d5ae330360c96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3abd4b7ecb4039de98ffa3c6ad880c7479fe31bdd5d2f1e66a6d5ae330360c96","first_computed_at":"2026-07-05T00:28:46.322532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:46.322532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mEKx2Owfw5dhuslfU2ZUcd8q2fvOW95ZUBoa2tXju+UUOUO01Uwz6OgB3pokWpa+OWtUBhCwRpQBafjlxMoeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:46.323046Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.01080","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b46912dc085a35a2ba0bed93662063bd203d619d3be799e3b9cc5ea369c298b1","sha256:02c08f427bba1ec3f51420121287f82a396d352b687bc9e1459ddae40c8586d5"],"state_sha256":"f4db141ea40d625a8eea77e88de1f3a2245868dbe5c6fbfcf2154e35a5e5a784"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i8y8/MUvYk64PVZSsmCF8uXc+9nMa9w5Qr1YOGRGyuyCNWitaJRDOt/vYQRX54H3AGL4bTAlGoM6+BK2d8WyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:00:26.726045Z","bundle_sha256":"9490ec4867f96f1e413fe9826c0bbdcde34b06251b3f7d0cf40b14c7264b9553"}}