{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CUIZS75PZDTRY5MIONRK74364V","short_pith_number":"pith:CUIZS75P","canonical_record":{"source":{"id":"2203.09168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-17T08:46:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"588db8d9ff1005e28206432a296edcf6351471a8035e0fb33012e8417bd85410","abstract_canon_sha256":"ad440f753facea4a0ddbe37dc49237d6d53279b1db942289769d8e5a4da90cdb"},"schema_version":"1.0"},"canonical_sha256":"1511997fafc8e71c75887362aff37ee546f880416159d1945d428ed7d54ebb0b","source":{"kind":"arxiv","id":"2203.09168","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09168","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09168v2","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09168","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"CUIZS75PZDTR","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"CUIZS75PZDTRY5MI","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"CUIZS75P","created_at":"2026-07-05T04:10:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CUIZS75PZDTRY5MIONRK74364V","target":"record","payload":{"canonical_record":{"source":{"id":"2203.09168","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-17T08:46:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"588db8d9ff1005e28206432a296edcf6351471a8035e0fb33012e8417bd85410","abstract_canon_sha256":"ad440f753facea4a0ddbe37dc49237d6d53279b1db942289769d8e5a4da90cdb"},"schema_version":"1.0"},"canonical_sha256":"1511997fafc8e71c75887362aff37ee546f880416159d1945d428ed7d54ebb0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:40.178913Z","signature_b64":"jqPxd6L6fWQqCdpqoQvRAojdHrDI06u/I83aNafbaB95vOiA+zwiRK1pedviDQQCE2Fn+FXeaVT5u2vIfP6/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1511997fafc8e71c75887362aff37ee546f880416159d1945d428ed7d54ebb0b","last_reissued_at":"2026-07-05T04:10:40.178330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:40.178330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.09168","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":"2026-07-05T04:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uf4FbkLS/oI9h+x0H+w25YJsB6ts+37QbylzyCe+iH7QZEUxookCa/r4tb300WsjAQ2zddfyzdI1KeBgB2sBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:52:57.160362Z"},"content_sha256":"cd63b458c5b6c9b60a59ac218d5e814ce631264a11a7f48ddd87bbb4de090670","schema_version":"1.0","event_id":"sha256:cd63b458c5b6c9b60a59ac218d5e814ce631264a11a7f48ddd87bbb4de090670"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CUIZS75PZDTRY5MIONRK74364V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Tavakoli, Dimitrije Antic, Georg Martius, Maximilian Seitzer","submitted_at":"2022-03-17T08:46:17Z","abstract_excerpt":"Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the parameters of a heteroscedastic Gaussian distribution by maximizing the logarithm of the likelihood function under the observed data. In this work, we examine this approach and identify potential hazards associated with the use of log-likelihood in conjunction with gradient-based optimizers. First, we present a synthetic example illustrating how this approach can lead to very poor but stable parameter estimates. Second"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09168","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/2203.09168/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":"2026-07-05T04:10:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zYIonoMJ21sph4UvkhlBA3dBjWcLiYoxnCxQUDDd0Sv7V0Y3wPc7X4CbDYIk/wuiWMD37MpRgG+C7SmCAWLXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:52:57.161320Z"},"content_sha256":"d7f4ee3f1e3662e6ed32123d51165a657bc4968681a93433a541b05a30917b9f","schema_version":"1.0","event_id":"sha256:d7f4ee3f1e3662e6ed32123d51165a657bc4968681a93433a541b05a30917b9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUIZS75PZDTRY5MIONRK74364V/bundle.json","state_url":"https://pith.science/pith/CUIZS75PZDTRY5MIONRK74364V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUIZS75PZDTRY5MIONRK74364V/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":"2026-08-03T15:52:57Z","links":{"resolver":"https://pith.science/pith/CUIZS75PZDTRY5MIONRK74364V","bundle":"https://pith.science/pith/CUIZS75PZDTRY5MIONRK74364V/bundle.json","state":"https://pith.science/pith/CUIZS75PZDTRY5MIONRK74364V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUIZS75PZDTRY5MIONRK74364V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CUIZS75PZDTRY5MIONRK74364V","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":"ad440f753facea4a0ddbe37dc49237d6d53279b1db942289769d8e5a4da90cdb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-17T08:46:17Z","title_canon_sha256":"588db8d9ff1005e28206432a296edcf6351471a8035e0fb33012e8417bd85410"},"schema_version":"1.0","source":{"id":"2203.09168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09168","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09168v2","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09168","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_12","alias_value":"CUIZS75PZDTR","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_16","alias_value":"CUIZS75PZDTRY5MI","created_at":"2026-07-05T04:10:40Z"},{"alias_kind":"pith_short_8","alias_value":"CUIZS75P","created_at":"2026-07-05T04:10:40Z"}],"graph_snapshots":[{"event_id":"sha256:d7f4ee3f1e3662e6ed32123d51165a657bc4968681a93433a541b05a30917b9f","target":"graph","created_at":"2026-07-05T04:10:40Z","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/2203.09168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Capturing aleatoric uncertainty is a critical part of many machine learning systems. In deep learning, a common approach to this end is to train a neural network to estimate the parameters of a heteroscedastic Gaussian distribution by maximizing the logarithm of the likelihood function under the observed data. In this work, we examine this approach and identify potential hazards associated with the use of log-likelihood in conjunction with gradient-based optimizers. First, we present a synthetic example illustrating how this approach can lead to very poor but stable parameter estimates. Second","authors_text":"Arash Tavakoli, Dimitrije Antic, Georg Martius, Maximilian Seitzer","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-17T08:46:17Z","title":"On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09168","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:cd63b458c5b6c9b60a59ac218d5e814ce631264a11a7f48ddd87bbb4de090670","target":"record","created_at":"2026-07-05T04:10:40Z","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":"ad440f753facea4a0ddbe37dc49237d6d53279b1db942289769d8e5a4da90cdb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-17T08:46:17Z","title_canon_sha256":"588db8d9ff1005e28206432a296edcf6351471a8035e0fb33012e8417bd85410"},"schema_version":"1.0","source":{"id":"2203.09168","kind":"arxiv","version":2}},"canonical_sha256":"1511997fafc8e71c75887362aff37ee546f880416159d1945d428ed7d54ebb0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1511997fafc8e71c75887362aff37ee546f880416159d1945d428ed7d54ebb0b","first_computed_at":"2026-07-05T04:10:40.178330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:40.178330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jqPxd6L6fWQqCdpqoQvRAojdHrDI06u/I83aNafbaB95vOiA+zwiRK1pedviDQQCE2Fn+FXeaVT5u2vIfP6/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:40.178913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.09168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd63b458c5b6c9b60a59ac218d5e814ce631264a11a7f48ddd87bbb4de090670","sha256:d7f4ee3f1e3662e6ed32123d51165a657bc4968681a93433a541b05a30917b9f"],"state_sha256":"3d809ae57dc5875a209aa27c4a0fbf8325e5229355957a97162195713e294a01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fTnxVdR2xf/sRPbv6nbzIdy3SH9U+AmkrE/lDGy2qt2TePtUgb7jI7wo9tLcS5FME17C6bSN1g9IFLPCvKWNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:52:57.168772Z","bundle_sha256":"e089a259cd51d4031dee3a51c3d70817e9070347ad1b0f7afa54897a56165b15"}}