{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5I7LATQLXM4EPT6N5J4ENU57XF","short_pith_number":"pith:5I7LATQL","canonical_record":{"source":{"id":"2012.08625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:32:03Z","cross_cats_sorted":[],"title_canon_sha256":"4938739a85ac16e22451cf18a57bd8790db956c3e662141bae6accaa9d5b27e9","abstract_canon_sha256":"0b9bc396d9b7268f6a217545a98c9bd7a11ee16b857e520cc359dfb9c667b587"},"schema_version":"1.0"},"canonical_sha256":"ea3eb04e0bbb3847cfcdea7846d3bfb949c6522c69d76449944059c5d2dfd3ee","source":{"kind":"arxiv","id":"2012.08625","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08625","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08625v1","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08625","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"5I7LATQLXM4E","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"5I7LATQLXM4EPT6N","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"5I7LATQL","created_at":"2026-07-05T02:00:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5I7LATQLXM4EPT6N5J4ENU57XF","target":"record","payload":{"canonical_record":{"source":{"id":"2012.08625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:32:03Z","cross_cats_sorted":[],"title_canon_sha256":"4938739a85ac16e22451cf18a57bd8790db956c3e662141bae6accaa9d5b27e9","abstract_canon_sha256":"0b9bc396d9b7268f6a217545a98c9bd7a11ee16b857e520cc359dfb9c667b587"},"schema_version":"1.0"},"canonical_sha256":"ea3eb04e0bbb3847cfcdea7846d3bfb949c6522c69d76449944059c5d2dfd3ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:01.446743Z","signature_b64":"5XELMJXiev8Sf69IJu/p+7YhzbWjkE5N8IKNB2agrtw4sBIXqhLSxNurWu06EOmpshqHb4m/dqYZ9dSTVZSpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea3eb04e0bbb3847cfcdea7846d3bfb949c6522c69d76449944059c5d2dfd3ee","last_reissued_at":"2026-07-05T02:00:01.446305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:01.446305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.08625","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":"2026-07-05T02:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"llCsmQSBLopW6ceXJiYSyccjZdN8vR3dS0MzG8reu5tky35CrI4G8au79JD4khlQEpZelb/pt/uyjF9/xXCeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:27:04.964580Z"},"content_sha256":"55729522981ae4a9e756158251ccdd3d588e852535c2ce061a700ae531cada3f","schema_version":"1.0","event_id":"sha256:55729522981ae4a9e756158251ccdd3d588e852535c2ce061a700ae531cada3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5I7LATQLXM4EPT6N5J4ENU57XF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Prediction Intervals for Model Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anupama Murthi, Benjamin Elder, Jiri Navratil, Matthew Arnold","submitted_at":"2020-12-15T21:32:03Z","abstract_excerpt":"Understanding model performance on unlabeled data is a fundamental challenge of developing, deploying, and maintaining AI systems. Model performance is typically evaluated using test sets or periodic manual quality assessments, both of which require laborious manual data labeling. Automated performance prediction techniques aim to mitigate this burden, but potential inaccuracy and a lack of trust in their predictions has prevented their widespread adoption. We address this core problem of performance prediction uncertainty with a method to compute prediction intervals for model performance. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08625","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/2012.08625/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":"2026-07-05T02:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3kOseR6+yRoHo1XXYcj4kGEJ509u1Joec7dDk3AJVovwJSG+j7Z3Bv7F2ZdIWYAkXw1yCQzRGJET24wZYtxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:27:04.964950Z"},"content_sha256":"6a8e1ced17d23b3e899b7e7f680f80f8bd80fb84c07cc4bdf7b0467dce8648ae","schema_version":"1.0","event_id":"sha256:6a8e1ced17d23b3e899b7e7f680f80f8bd80fb84c07cc4bdf7b0467dce8648ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5I7LATQLXM4EPT6N5J4ENU57XF/bundle.json","state_url":"https://pith.science/pith/5I7LATQLXM4EPT6N5J4ENU57XF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5I7LATQLXM4EPT6N5J4ENU57XF/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":"2026-07-07T05:27:04Z","links":{"resolver":"https://pith.science/pith/5I7LATQLXM4EPT6N5J4ENU57XF","bundle":"https://pith.science/pith/5I7LATQLXM4EPT6N5J4ENU57XF/bundle.json","state":"https://pith.science/pith/5I7LATQLXM4EPT6N5J4ENU57XF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5I7LATQLXM4EPT6N5J4ENU57XF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5I7LATQLXM4EPT6N5J4ENU57XF","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":"0b9bc396d9b7268f6a217545a98c9bd7a11ee16b857e520cc359dfb9c667b587","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:32:03Z","title_canon_sha256":"4938739a85ac16e22451cf18a57bd8790db956c3e662141bae6accaa9d5b27e9"},"schema_version":"1.0","source":{"id":"2012.08625","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.08625","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2012.08625v1","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.08625","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"5I7LATQLXM4E","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"5I7LATQLXM4EPT6N","created_at":"2026-07-05T02:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"5I7LATQL","created_at":"2026-07-05T02:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:6a8e1ced17d23b3e899b7e7f680f80f8bd80fb84c07cc4bdf7b0467dce8648ae","target":"graph","created_at":"2026-07-05T02:00:01Z","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/2012.08625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding model performance on unlabeled data is a fundamental challenge of developing, deploying, and maintaining AI systems. Model performance is typically evaluated using test sets or periodic manual quality assessments, both of which require laborious manual data labeling. Automated performance prediction techniques aim to mitigate this burden, but potential inaccuracy and a lack of trust in their predictions has prevented their widespread adoption. We address this core problem of performance prediction uncertainty with a method to compute prediction intervals for model performance. Ou","authors_text":"Anupama Murthi, Benjamin Elder, Jiri Navratil, Matthew Arnold","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:32:03Z","title":"Learning Prediction Intervals for Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.08625","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":"sha256:55729522981ae4a9e756158251ccdd3d588e852535c2ce061a700ae531cada3f","target":"record","created_at":"2026-07-05T02:00:01Z","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":"0b9bc396d9b7268f6a217545a98c9bd7a11ee16b857e520cc359dfb9c667b587","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-15T21:32:03Z","title_canon_sha256":"4938739a85ac16e22451cf18a57bd8790db956c3e662141bae6accaa9d5b27e9"},"schema_version":"1.0","source":{"id":"2012.08625","kind":"arxiv","version":1}},"canonical_sha256":"ea3eb04e0bbb3847cfcdea7846d3bfb949c6522c69d76449944059c5d2dfd3ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea3eb04e0bbb3847cfcdea7846d3bfb949c6522c69d76449944059c5d2dfd3ee","first_computed_at":"2026-07-05T02:00:01.446305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:01.446305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5XELMJXiev8Sf69IJu/p+7YhzbWjkE5N8IKNB2agrtw4sBIXqhLSxNurWu06EOmpshqHb4m/dqYZ9dSTVZSpDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:01.446743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.08625","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55729522981ae4a9e756158251ccdd3d588e852535c2ce061a700ae531cada3f","sha256:6a8e1ced17d23b3e899b7e7f680f80f8bd80fb84c07cc4bdf7b0467dce8648ae"],"state_sha256":"dbc947d8621ed063030511d87991c4888f08fe8e809f3e2173559326a41bd994"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rUCEpNp3Uz7qZ/RENgv3zBoIFlsLLpfXXLjdwRCHF4VuYPAxv9SN3sLUdDW1FcV7pL90lrNKPIYPDJs8WissCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:27:04.967248Z","bundle_sha256":"32cdf805065db53ea389ff52c6b31b65d35d37f2efd11f8080a2eb6168486700"}}