{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WNDIRTJVPFG6FSNPQXZKD3KTJ5","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":"e26c3086aef28347729c5fe16d420eef83420090d2c33d2b188ddacfb06ed779","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-23T03:42:01Z","title_canon_sha256":"a8961e5d71c89c556d04325ea5d317f651cfa66a1ccbf48816f214d7b353ce25"},"schema_version":"1.0","source":{"id":"2109.11126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.11126","created_at":"2026-07-05T03:16:54Z"},{"alias_kind":"arxiv_version","alias_value":"2109.11126v1","created_at":"2026-07-05T03:16:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11126","created_at":"2026-07-05T03:16:54Z"},{"alias_kind":"pith_short_12","alias_value":"WNDIRTJVPFG6","created_at":"2026-07-05T03:16:54Z"},{"alias_kind":"pith_short_16","alias_value":"WNDIRTJVPFG6FSNP","created_at":"2026-07-05T03:16:54Z"},{"alias_kind":"pith_short_8","alias_value":"WNDIRTJV","created_at":"2026-07-05T03:16:54Z"}],"graph_snapshots":[{"event_id":"sha256:45f5ee3c3ac34d4f5ba680de428e16750b7dd4733ea3dbd68a8b888b5313c0c6","target":"graph","created_at":"2026-07-05T03:16:54Z","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/2109.11126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In some problem spaces, the high cost of obtaining ground truth labels necessitates use of lower quality reference datasets. It is difficult to benchmark model performance using these datasets, as evaluation results may be biased. We propose a supplement to using reference labels, which we call an approximate ground truth refinement (AGTR). Using an AGTR, we prove that bounds on specific metrics used to evaluate clustering algorithms and multi-class classifiers can be computed without reference labels. We also introduce a procedure that uses an AGTR to identify inaccurate evaluation results pr","authors_text":"Charles Nicholas, Edward Raff, Robert J. Joyce","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-23T03:42:01Z","title":"A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11126","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":"sha256:757b498ee0a1726ee606e8d7ed2fb667489ae10adff69f8c5b9061f0d0287ab6","target":"record","created_at":"2026-07-05T03:16:54Z","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":"e26c3086aef28347729c5fe16d420eef83420090d2c33d2b188ddacfb06ed779","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-23T03:42:01Z","title_canon_sha256":"a8961e5d71c89c556d04325ea5d317f651cfa66a1ccbf48816f214d7b353ce25"},"schema_version":"1.0","source":{"id":"2109.11126","kind":"arxiv","version":1}},"canonical_sha256":"b34688cd35794de2c9af85f2a1ed534f4dcf2e73fcbfcf624c48d240d4f6dd68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b34688cd35794de2c9af85f2a1ed534f4dcf2e73fcbfcf624c48d240d4f6dd68","first_computed_at":"2026-07-05T03:16:54.908023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:16:54.908023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OZVrZ2s3/ja6+EznINlYH+eryXbv0SXN6UIjkbKEUh9QQodsJ9g/CfctXKM8V2z1afmY7/H3BPqLLSCfqbUqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:16:54.908550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.11126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:757b498ee0a1726ee606e8d7ed2fb667489ae10adff69f8c5b9061f0d0287ab6","sha256:45f5ee3c3ac34d4f5ba680de428e16750b7dd4733ea3dbd68a8b888b5313c0c6"],"state_sha256":"46ae5ca27ffb6fc3c36ffcc1a27c14331c90a797b1f8c500c2d67cd260dc7433"}