{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QYRL3AMIPS4TIKZYKVTYKRZ7JK","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":"24db657d4034294f9cc24fe950bee499f271591f860fe9e57fb7f52c5238a210","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:10:35Z","title_canon_sha256":"f09d686a8d92069ba859b5704cba2e4b34dc9d97b75066e5a902a46b02334726"},"schema_version":"1.0","source":{"id":"2605.31278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31278","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31278v1","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31278","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"QYRL3AMIPS4T","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"QYRL3AMIPS4TIKZY","created_at":"2026-06-01T01:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"QYRL3AMI","created_at":"2026-06-01T01:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:5a3e530c06879ffb489c81dba30f267c5264b3843cfb51c7ef75c59b03190938","target":"graph","created_at":"2026-06-01T01:04:08Z","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/2605.31278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotation and biased LLM-as-judge proxies. Prediction-powered inference (PPI) combines both into debiased estimates with valid confidence intervals, yet its various methods remain scattered across papers under partial implementations. We introduce GLIDE, an open-source Python library that unifies state-of-the-art PPI estimators (PPI++, Stratified PPI, Predict-Then-Debias and its stratified variants, Active Statistical Inference) and samplers (uniform,","authors_text":"Gr\\'egoire Martinon, Ibrahim Merad, Mohammed Raki","cross_cats":["cs.LG","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:10:35Z","title":"Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31278","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":"sha256:1e2f2158c88a2546a64d3a4f00a1a9e1385679e4b81af56e2f50a70b3fa62df1","target":"record","created_at":"2026-06-01T01:04:08Z","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":"24db657d4034294f9cc24fe950bee499f271591f860fe9e57fb7f52c5238a210","cross_cats_sorted":["cs.LG","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:10:35Z","title_canon_sha256":"f09d686a8d92069ba859b5704cba2e4b34dc9d97b75066e5a902a46b02334726"},"schema_version":"1.0","source":{"id":"2605.31278","kind":"arxiv","version":1}},"canonical_sha256":"8622bd81887cb9342b38556785473f4a9a2e464bb05da0830c8c49bafcb59b20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8622bd81887cb9342b38556785473f4a9a2e464bb05da0830c8c49bafcb59b20","first_computed_at":"2026-06-01T01:04:08.428757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:08.428757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"usP+/B1FnChoRaZvUVrD5OTdU/OsjhhWZPK1oHFjyWQIQZvWREDxvg21Sx4sO48b9O9h+/frrYRNzrYBlZEwCQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:08.429771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e2f2158c88a2546a64d3a4f00a1a9e1385679e4b81af56e2f50a70b3fa62df1","sha256:5a3e530c06879ffb489c81dba30f267c5264b3843cfb51c7ef75c59b03190938"],"state_sha256":"07e8a414ae896f854f0d2d1a06b9c397fe2a245d95462a2ec915d69bedb74ccf"}