{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HT6QQ4TB7OGKVKI3UABOZZ4U73","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":"cfb29c4c262a64da1fc4447bc450c0e8515de1da77deb8084ab5abebae19d345","cross_cats_sorted":["cs.AI","cs.CL","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-09T02:47:11Z","title_canon_sha256":"4825a5bfdbb40bf4dd097eeeca06730d89bbabdeed7b64dcc922037f5fc7c59f"},"schema_version":"1.0","source":{"id":"2403.07008","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07008","created_at":"2026-06-02T02:04:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07008v3","created_at":"2026-06-02T02:04:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07008","created_at":"2026-06-02T02:04:03Z"},{"alias_kind":"pith_short_12","alias_value":"HT6QQ4TB7OGK","created_at":"2026-06-02T02:04:03Z"},{"alias_kind":"pith_short_16","alias_value":"HT6QQ4TB7OGKVKI3","created_at":"2026-06-02T02:04:03Z"},{"alias_kind":"pith_short_8","alias_value":"HT6QQ4TB","created_at":"2026-06-02T02:04:03Z"}],"graph_snapshots":[{"event_id":"sha256:0a1ccd53584b3b4f754fa74617051d080d0b07ebd9a75add03f25ca49d868e62","target":"graph","created_at":"2026-06-02T02:04:03Z","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/2403.07008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process called autoevaluation. We suggest efficient and statistically principled algorithms for this purpose that improve sample efficiency while remaining unbiased. These algorithms increase the effective human-labeled sample size by up to 50% on experiments with GPT-4.","authors_text":"Anastasios N. Angelopoulos, Jitendra Malik, Michael I. Jordan, Nir Yosef, Pierre Boyeau","cross_cats":["cs.AI","cs.CL","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-09T02:47:11Z","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07008","kind":"arxiv","version":3},"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":"sha256:9473725617ca36008066e05f2fca9baa731595fb2c0a67071c26f1994642cdb4","target":"record","created_at":"2026-06-02T02:04:03Z","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":"cfb29c4c262a64da1fc4447bc450c0e8515de1da77deb8084ab5abebae19d345","cross_cats_sorted":["cs.AI","cs.CL","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-09T02:47:11Z","title_canon_sha256":"4825a5bfdbb40bf4dd097eeeca06730d89bbabdeed7b64dcc922037f5fc7c59f"},"schema_version":"1.0","source":{"id":"2403.07008","kind":"arxiv","version":3}},"canonical_sha256":"3cfd087261fb8caaa91ba002ece794fec1c1fd4490c05decc7f17e6b34f67585","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cfd087261fb8caaa91ba002ece794fec1c1fd4490c05decc7f17e6b34f67585","first_computed_at":"2026-06-02T02:04:03.965445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:03.965445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xyEHSvVB2uYZqTFA3dBpIPs53pyVMQk9/uUDCyXYWhcePMU2GM1dxe5GGwQEGOSDZyYd75yAuJRGrHF5BznjCA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:03.965864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07008","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9473725617ca36008066e05f2fca9baa731595fb2c0a67071c26f1994642cdb4","sha256:0a1ccd53584b3b4f754fa74617051d080d0b07ebd9a75add03f25ca49d868e62"],"state_sha256":"e1430ca5551a03c6355bd28a0d157a6f466df14aa7ebab3f1e1f7a93616b3472"}