{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6753TV2L6O5QATOIBANFUC6ENK","short_pith_number":"pith:6753TV2L","canonical_record":{"source":{"id":"2212.09184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-18T22:34:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca56ee8c638c623ed9aab0b7cfccde85988ef985c14294b333487fdbcda3d430","abstract_canon_sha256":"d622e2b11321c4a3107c565307d42c4a3ee77897482b1d69ee9a100bbeb8e7ee"},"schema_version":"1.0"},"canonical_sha256":"f7fbb9d74bf3bb004dc8081a5a0bc46a988c382d3ba571f5559e81f2f715c7b4","source":{"kind":"arxiv","id":"2212.09184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09184","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09184v1","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09184","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"6753TV2L6O5Q","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"6753TV2L6O5QATOI","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"6753TV2L","created_at":"2026-07-05T05:26:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6753TV2L6O5QATOIBANFUC6ENK","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-18T22:34:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca56ee8c638c623ed9aab0b7cfccde85988ef985c14294b333487fdbcda3d430","abstract_canon_sha256":"d622e2b11321c4a3107c565307d42c4a3ee77897482b1d69ee9a100bbeb8e7ee"},"schema_version":"1.0"},"canonical_sha256":"f7fbb9d74bf3bb004dc8081a5a0bc46a988c382d3ba571f5559e81f2f715c7b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:19.044168Z","signature_b64":"wcIeDtTA2uMgsRAJ0rH1bVW749xBeWtMaobIenTsIbZ8SjQb+nurkUa8rr9NG2XN8K0l1Vw+ebjxoNJbrNQ2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7fbb9d74bf3bb004dc8081a5a0bc46a988c382d3ba571f5559e81f2f715c7b4","last_reissued_at":"2026-07-05T05:26:19.043716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:19.043716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09184","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:26:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"103j9z/pWOO/S+B5AKyi/YExrjvNzpvohKnyY/zEVjk+0yH6HHKmZ/fQ5Ga8zMf+EH1SSOewIX5X3iRoOBj6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:25:56.619565Z"},"content_sha256":"bba2dea9ae18515281ca846488eeaa64a0c995ea8ffb36f4976dfb8d6ddf9bf2","schema_version":"1.0","event_id":"sha256:bba2dea9ae18515281ca846488eeaa64a0c995ea8ffb36f4976dfb8d6ddf9bf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6753TV2L6O5QATOIBANFUC6ENK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faithful Heteroscedastic Regression with Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Stirn, David A. Knowles, Hans-Hermann Wessels, Laura Pereira, Megan Schertzer, Neville E. Sanjana","submitted_at":"2022-12-18T22:34:42Z","abstract_excerpt":"Heteroscedastic regression models a Gaussian variable's mean and variance as a function of covariates. Parametric methods that employ neural networks for these parameter maps can capture complex relationships in the data. Yet, optimizing network parameters via log likelihood gradients can yield suboptimal mean and uncalibrated variance estimates. Current solutions side-step this optimization problem with surrogate objectives or Bayesian treatments. Instead, we make two simple modifications to optimization. Notably, their combination produces a heteroscedastic model with mean estimates that are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09184","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/2212.09184/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":"2026-07-05T05:26:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDC0zo4/QM9eiiwY/lTvZoVKGGdotd3ceBp7mQhm0BvKy7kp/T1x12ywLz67/NjVwTF/emX79tbW0K6IbkowAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:25:56.620513Z"},"content_sha256":"30996fd75be8fb2377d6ee04937493acdcbaaec3b664905ebeaea8fb6d301a36","schema_version":"1.0","event_id":"sha256:30996fd75be8fb2377d6ee04937493acdcbaaec3b664905ebeaea8fb6d301a36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6753TV2L6O5QATOIBANFUC6ENK/bundle.json","state_url":"https://pith.science/pith/6753TV2L6O5QATOIBANFUC6ENK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6753TV2L6O5QATOIBANFUC6ENK/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":"2026-08-03T19:25:56Z","links":{"resolver":"https://pith.science/pith/6753TV2L6O5QATOIBANFUC6ENK","bundle":"https://pith.science/pith/6753TV2L6O5QATOIBANFUC6ENK/bundle.json","state":"https://pith.science/pith/6753TV2L6O5QATOIBANFUC6ENK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6753TV2L6O5QATOIBANFUC6ENK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6753TV2L6O5QATOIBANFUC6ENK","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":"d622e2b11321c4a3107c565307d42c4a3ee77897482b1d69ee9a100bbeb8e7ee","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-18T22:34:42Z","title_canon_sha256":"ca56ee8c638c623ed9aab0b7cfccde85988ef985c14294b333487fdbcda3d430"},"schema_version":"1.0","source":{"id":"2212.09184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09184","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09184v1","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09184","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"6753TV2L6O5Q","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"6753TV2L6O5QATOI","created_at":"2026-07-05T05:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"6753TV2L","created_at":"2026-07-05T05:26:19Z"}],"graph_snapshots":[{"event_id":"sha256:30996fd75be8fb2377d6ee04937493acdcbaaec3b664905ebeaea8fb6d301a36","target":"graph","created_at":"2026-07-05T05:26:19Z","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/2212.09184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Heteroscedastic regression models a Gaussian variable's mean and variance as a function of covariates. Parametric methods that employ neural networks for these parameter maps can capture complex relationships in the data. Yet, optimizing network parameters via log likelihood gradients can yield suboptimal mean and uncalibrated variance estimates. Current solutions side-step this optimization problem with surrogate objectives or Bayesian treatments. Instead, we make two simple modifications to optimization. Notably, their combination produces a heteroscedastic model with mean estimates that are","authors_text":"Andrew Stirn, David A. Knowles, Hans-Hermann Wessels, Laura Pereira, Megan Schertzer, Neville E. Sanjana","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-18T22:34:42Z","title":"Faithful Heteroscedastic Regression with Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09184","kind":"arxiv","version":1},"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:bba2dea9ae18515281ca846488eeaa64a0c995ea8ffb36f4976dfb8d6ddf9bf2","target":"record","created_at":"2026-07-05T05:26:19Z","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":"d622e2b11321c4a3107c565307d42c4a3ee77897482b1d69ee9a100bbeb8e7ee","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-18T22:34:42Z","title_canon_sha256":"ca56ee8c638c623ed9aab0b7cfccde85988ef985c14294b333487fdbcda3d430"},"schema_version":"1.0","source":{"id":"2212.09184","kind":"arxiv","version":1}},"canonical_sha256":"f7fbb9d74bf3bb004dc8081a5a0bc46a988c382d3ba571f5559e81f2f715c7b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7fbb9d74bf3bb004dc8081a5a0bc46a988c382d3ba571f5559e81f2f715c7b4","first_computed_at":"2026-07-05T05:26:19.043716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:19.043716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wcIeDtTA2uMgsRAJ0rH1bVW749xBeWtMaobIenTsIbZ8SjQb+nurkUa8rr9NG2XN8K0l1Vw+ebjxoNJbrNQ2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:19.044168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bba2dea9ae18515281ca846488eeaa64a0c995ea8ffb36f4976dfb8d6ddf9bf2","sha256:30996fd75be8fb2377d6ee04937493acdcbaaec3b664905ebeaea8fb6d301a36"],"state_sha256":"5a0479d0a3674c78cafba21ce1fae07ef0e448379102a727e2cb032703d853b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M6hiKOJKSxjjwC+bu2/Ph6HalUgdyBDDKABmPyK40fqHyghn9RPPVrVwViRYzR8M7PGTC6Vt7QouZy7KYewADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:25:56.627442Z","bundle_sha256":"bcf083c0d4f10ac07b301464251ea0816cbee17648ea3c1d3f3eb5de0b50353f"}}