{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MBSRGZZSTKBNHSNYIVYWCU6NIX","short_pith_number":"pith:MBSRGZZS","canonical_record":{"source":{"id":"1905.10634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-25T17:07:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f674666db15fa3821774c8c3a2fbcc6831e3e5cbe4c5d45c777a7976e5a3f86","abstract_canon_sha256":"a65bc6647150898f443a198ecf1f0bc425e76511d743e681663e87bbced85203"},"schema_version":"1.0"},"canonical_sha256":"60651367329a82d3c9b845716153cd45c61c5927ceed5021aeb4a1cfa60ae4e2","source":{"kind":"arxiv","id":"1905.10634","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10634","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10634v2","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10634","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"pith_short_12","alias_value":"MBSRGZZSTKBN","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"pith_short_16","alias_value":"MBSRGZZSTKBNHSNY","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"pith_short_8","alias_value":"MBSRGZZS","created_at":"2026-07-05T00:43:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MBSRGZZSTKBNHSNYIVYWCU6NIX","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-25T17:07:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f674666db15fa3821774c8c3a2fbcc6831e3e5cbe4c5d45c777a7976e5a3f86","abstract_canon_sha256":"a65bc6647150898f443a198ecf1f0bc425e76511d743e681663e87bbced85203"},"schema_version":"1.0"},"canonical_sha256":"60651367329a82d3c9b845716153cd45c61c5927ceed5021aeb4a1cfa60ae4e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:01.206958Z","signature_b64":"D2Q+/w/M4CZJwKbfIZfIZ4TF0/H5IcyFUTDVKVb/tf8/PglmsKLuyZ3n6ZQbRo2QwDM6C/02b5XXgo1QCJypCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60651367329a82d3c9b845716153cd45c61c5927ceed5021aeb4a1cfa60ae4e2","last_reissued_at":"2026-07-05T00:43:01.206532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:01.206532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10634","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":"2026-07-05T00:43:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9jB1p3EX46yuX3X6imGkrK/wZqCaN+7bRpWH+Eqw/barD+pBX6CGZSxMcWTe6nL6mCPpQlztWHLPzJYPeAd7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:29:33.587989Z"},"content_sha256":"939a4a94cd24250af8ad78dfc47ecd1e93daae376ec0270bd3fff5a3ded45737","schema_version":"1.0","event_id":"sha256:939a4a94cd24250af8ad78dfc47ecd1e93daae376ec0270bd3fff5a3ded45737"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MBSRGZZSTKBNHSNYIVYWCU6NIX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive, Distribution-Free Prediction Intervals for Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Danijel Kivaranovic, Hannes Leeb, Kory D. Johnson","submitted_at":"2019-05-25T17:07:33Z","abstract_excerpt":"The machine learning literature contains several constructions for prediction intervals that are intuitively reasonable but ultimately ad-hoc in that they do not come with provable performance guarantees. We present methods from the statistics literature that can be used efficiently with neural networks under minimal assumptions with guaranteed performance. We propose a neural network that outputs three values instead of a single point estimate and optimizes a loss function motivated by the standard quantile regression loss. We provide two prediction interval methods with finite sample coverag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10634","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/1905.10634/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":"2026-07-05T00:43:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"unKAeXxudY+nHvVIhU6W0WzF8abg3xOS+tSf+K0rln6clAahuUKTC/hSEnWHusIj5tLnD0XNjNEE+sFM5dpICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T19:29:33.590086Z"},"content_sha256":"d8b9c8e9b69ea2daf60d277d8bc815fa82baa5aa75485115fd93d5bc5db7c38a","schema_version":"1.0","event_id":"sha256:d8b9c8e9b69ea2daf60d277d8bc815fa82baa5aa75485115fd93d5bc5db7c38a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBSRGZZSTKBNHSNYIVYWCU6NIX/bundle.json","state_url":"https://pith.science/pith/MBSRGZZSTKBNHSNYIVYWCU6NIX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBSRGZZSTKBNHSNYIVYWCU6NIX/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":"2026-08-19T19:29:33Z","links":{"resolver":"https://pith.science/pith/MBSRGZZSTKBNHSNYIVYWCU6NIX","bundle":"https://pith.science/pith/MBSRGZZSTKBNHSNYIVYWCU6NIX/bundle.json","state":"https://pith.science/pith/MBSRGZZSTKBNHSNYIVYWCU6NIX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBSRGZZSTKBNHSNYIVYWCU6NIX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MBSRGZZSTKBNHSNYIVYWCU6NIX","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":"a65bc6647150898f443a198ecf1f0bc425e76511d743e681663e87bbced85203","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-25T17:07:33Z","title_canon_sha256":"8f674666db15fa3821774c8c3a2fbcc6831e3e5cbe4c5d45c777a7976e5a3f86"},"schema_version":"1.0","source":{"id":"1905.10634","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10634","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10634v2","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10634","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"pith_short_12","alias_value":"MBSRGZZSTKBN","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"pith_short_16","alias_value":"MBSRGZZSTKBNHSNY","created_at":"2026-07-05T00:43:01Z"},{"alias_kind":"pith_short_8","alias_value":"MBSRGZZS","created_at":"2026-07-05T00:43:01Z"}],"graph_snapshots":[{"event_id":"sha256:d8b9c8e9b69ea2daf60d277d8bc815fa82baa5aa75485115fd93d5bc5db7c38a","target":"graph","created_at":"2026-07-05T00:43:01Z","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/1905.10634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The machine learning literature contains several constructions for prediction intervals that are intuitively reasonable but ultimately ad-hoc in that they do not come with provable performance guarantees. We present methods from the statistics literature that can be used efficiently with neural networks under minimal assumptions with guaranteed performance. We propose a neural network that outputs three values instead of a single point estimate and optimizes a loss function motivated by the standard quantile regression loss. We provide two prediction interval methods with finite sample coverag","authors_text":"Danijel Kivaranovic, Hannes Leeb, Kory D. Johnson","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-25T17:07:33Z","title":"Adaptive, Distribution-Free Prediction Intervals for Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10634","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":"sha256:939a4a94cd24250af8ad78dfc47ecd1e93daae376ec0270bd3fff5a3ded45737","target":"record","created_at":"2026-07-05T00:43:01Z","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":"a65bc6647150898f443a198ecf1f0bc425e76511d743e681663e87bbced85203","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-25T17:07:33Z","title_canon_sha256":"8f674666db15fa3821774c8c3a2fbcc6831e3e5cbe4c5d45c777a7976e5a3f86"},"schema_version":"1.0","source":{"id":"1905.10634","kind":"arxiv","version":2}},"canonical_sha256":"60651367329a82d3c9b845716153cd45c61c5927ceed5021aeb4a1cfa60ae4e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60651367329a82d3c9b845716153cd45c61c5927ceed5021aeb4a1cfa60ae4e2","first_computed_at":"2026-07-05T00:43:01.206532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:01.206532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D2Q+/w/M4CZJwKbfIZfIZ4TF0/H5IcyFUTDVKVb/tf8/PglmsKLuyZ3n6ZQbRo2QwDM6C/02b5XXgo1QCJypCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:01.206958Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10634","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:939a4a94cd24250af8ad78dfc47ecd1e93daae376ec0270bd3fff5a3ded45737","sha256:d8b9c8e9b69ea2daf60d277d8bc815fa82baa5aa75485115fd93d5bc5db7c38a"],"state_sha256":"97572379038129b87d2145f19ce4f58c6eeea8b9c4a2604f230b518ffb498898"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EztzcTEcyRYPW6etu+L2hbsEXQP5szEuHuEz7/GI75M/CrYmIEZ0pahxdlPydTUFyRT7MyGp95Gd4XIIE8IMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T19:29:33.654801Z","bundle_sha256":"8d5c8f2ed36342a677c503b3e57878e00f98f8dd18cb8647c10317c0af50b483"}}