{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z6IOVW73BMO6V4QJE3FSAOOBCY","short_pith_number":"pith:Z6IOVW73","canonical_record":{"source":{"id":"2007.08792","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-17T07:32:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"21405baafb749f15381f018c68ef51d812ccaba009a025c990df355ac2015911","abstract_canon_sha256":"fceb28cc8d2848f9a4ab6582459924d951e43eb610cc6580fa403874a222cfec"},"schema_version":"1.0"},"canonical_sha256":"cf90eadbfb0b1deaf20926cb2039c116378d0d5ba5ca3070728e6a9dea98bf24","source":{"kind":"arxiv","id":"2007.08792","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.08792","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2007.08792v4","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08792","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"Z6IOVW73BMO6","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"Z6IOVW73BMO6V4QJ","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"Z6IOVW73","created_at":"2026-07-05T03:35:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z6IOVW73BMO6V4QJE3FSAOOBCY","target":"record","payload":{"canonical_record":{"source":{"id":"2007.08792","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-17T07:32:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"21405baafb749f15381f018c68ef51d812ccaba009a025c990df355ac2015911","abstract_canon_sha256":"fceb28cc8d2848f9a4ab6582459924d951e43eb610cc6580fa403874a222cfec"},"schema_version":"1.0"},"canonical_sha256":"cf90eadbfb0b1deaf20926cb2039c116378d0d5ba5ca3070728e6a9dea98bf24","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:26.014595Z","signature_b64":"PYHnPk+WfDMrL2C0lBzHnr8Zw9sfEUB1fY4WqT8gkWXCAN52eE5VC5A0CAE8o0xktpayBvo4qhtEAXEqaejSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf90eadbfb0b1deaf20926cb2039c116378d0d5ba5ca3070728e6a9dea98bf24","last_reissued_at":"2026-07-05T03:35:26.014139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:26.014139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.08792","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GGKRbMI0aU7blAWlHmDutS2Oa4Y9D3j2JaDihbC/L89HYDSscu7Xm+D1M5BJBPAMETggP6clv9zo8lKFPko1Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:48:37.017135Z"},"content_sha256":"0583d12e4b3f279c77880859f695eb99a978e783a7db51a4861c2fb1d4483358","schema_version":"1.0","event_id":"sha256:0583d12e4b3f279c77880859f695eb99a978e783a7db51a4861c2fb1d4483358"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z6IOVW73BMO6V4QJE3FSAOOBCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty Quantification and Deep Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexandre H. Thiery, Rahul Rahaman","submitted_at":"2020-07-17T07:32:24Z","abstract_excerpt":"Deep Learning methods are known to suffer from calibration issues: they typically produce over-confident estimates. These problems are exacerbated in the low data regime. Although the calibration of probabilistic models is well studied, calibrating extremely over-parametrized models in the low-data regime presents unique challenges. We show that deep-ensembles do not necessarily lead to improved calibration properties. In fact, we show that standard ensembling methods, when used in conjunction with modern techniques such as mixup regularization, can lead to less calibrated models. This text ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08792","kind":"arxiv","version":4},"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/2007.08792/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":"2026-07-05T03:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChxFKLKDZbYKsge+L+R9hOFED5neqbygGdDyM84Zs84aRQzII5SpP160jsZmrHU2R034GycWjhTDqJmI6OJzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:48:37.017426Z"},"content_sha256":"f59f163483b0115539b283425f144174272946697f06b515d48b20793f2b0c03","schema_version":"1.0","event_id":"sha256:f59f163483b0115539b283425f144174272946697f06b515d48b20793f2b0c03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z6IOVW73BMO6V4QJE3FSAOOBCY/bundle.json","state_url":"https://pith.science/pith/Z6IOVW73BMO6V4QJE3FSAOOBCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z6IOVW73BMO6V4QJE3FSAOOBCY/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":"2026-07-31T19:48:37Z","links":{"resolver":"https://pith.science/pith/Z6IOVW73BMO6V4QJE3FSAOOBCY","bundle":"https://pith.science/pith/Z6IOVW73BMO6V4QJE3FSAOOBCY/bundle.json","state":"https://pith.science/pith/Z6IOVW73BMO6V4QJE3FSAOOBCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z6IOVW73BMO6V4QJE3FSAOOBCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z6IOVW73BMO6V4QJE3FSAOOBCY","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":"fceb28cc8d2848f9a4ab6582459924d951e43eb610cc6580fa403874a222cfec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-17T07:32:24Z","title_canon_sha256":"21405baafb749f15381f018c68ef51d812ccaba009a025c990df355ac2015911"},"schema_version":"1.0","source":{"id":"2007.08792","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.08792","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2007.08792v4","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08792","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"Z6IOVW73BMO6","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"Z6IOVW73BMO6V4QJ","created_at":"2026-07-05T03:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"Z6IOVW73","created_at":"2026-07-05T03:35:26Z"}],"graph_snapshots":[{"event_id":"sha256:f59f163483b0115539b283425f144174272946697f06b515d48b20793f2b0c03","target":"graph","created_at":"2026-07-05T03:35:26Z","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/2007.08792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Learning methods are known to suffer from calibration issues: they typically produce over-confident estimates. These problems are exacerbated in the low data regime. Although the calibration of probabilistic models is well studied, calibrating extremely over-parametrized models in the low-data regime presents unique challenges. We show that deep-ensembles do not necessarily lead to improved calibration properties. In fact, we show that standard ensembling methods, when used in conjunction with modern techniques such as mixup regularization, can lead to less calibrated models. This text ex","authors_text":"Alexandre H. Thiery, Rahul Rahaman","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-17T07:32:24Z","title":"Uncertainty Quantification and Deep Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08792","kind":"arxiv","version":4},"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":"sha256:0583d12e4b3f279c77880859f695eb99a978e783a7db51a4861c2fb1d4483358","target":"record","created_at":"2026-07-05T03:35:26Z","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":"fceb28cc8d2848f9a4ab6582459924d951e43eb610cc6580fa403874a222cfec","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-07-17T07:32:24Z","title_canon_sha256":"21405baafb749f15381f018c68ef51d812ccaba009a025c990df355ac2015911"},"schema_version":"1.0","source":{"id":"2007.08792","kind":"arxiv","version":4}},"canonical_sha256":"cf90eadbfb0b1deaf20926cb2039c116378d0d5ba5ca3070728e6a9dea98bf24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf90eadbfb0b1deaf20926cb2039c116378d0d5ba5ca3070728e6a9dea98bf24","first_computed_at":"2026-07-05T03:35:26.014139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:26.014139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PYHnPk+WfDMrL2C0lBzHnr8Zw9sfEUB1fY4WqT8gkWXCAN52eE5VC5A0CAE8o0xktpayBvo4qhtEAXEqaejSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:26.014595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.08792","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0583d12e4b3f279c77880859f695eb99a978e783a7db51a4861c2fb1d4483358","sha256:f59f163483b0115539b283425f144174272946697f06b515d48b20793f2b0c03"],"state_sha256":"30af679674b7c3093cd38014c5bdfc20559f55108b935e543609bd34ec56ce1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ikVtF72yARWu8QIwu4ynApFMbcQP81apu91DTH4aLeiSMY0bg5mZh2T4Mp13gpj2OAoNa4cXTzOv7CAjM1pmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T19:48:37.021951Z","bundle_sha256":"9d1be7662c9e47499f4cf836bbdcf526f03f35d491741b846a404c9eed91cb13"}}