{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QYRL3AMIPS4TIKZYKVTYKRZ7JK","short_pith_number":"pith:QYRL3AMI","schema_version":"1.0","canonical_sha256":"8622bd81887cb9342b38556785473f4a9a2e464bb05da0830c8c49bafcb59b20","source":{"kind":"arxiv","id":"2605.31278","version":1},"attestation_state":"computed","paper":{"title":"Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"cs.AI","authors_text":"Gr\\'egoire Martinon, Ibrahim Merad, Mohammed Raki","submitted_at":"2026-05-29T13:10:35Z","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,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.31278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-29T13:10:35Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"f09d686a8d92069ba859b5704cba2e4b34dc9d97b75066e5a902a46b02334726","abstract_canon_sha256":"24db657d4034294f9cc24fe950bee499f271591f860fe9e57fb7f52c5238a210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:08.429771Z","signature_b64":"usP+/B1FnChoRaZvUVrD5OTdU/OsjhhWZPK1oHFjyWQIQZvWREDxvg21Sx4sO48b9O9h+/frrYRNzrYBlZEwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8622bd81887cb9342b38556785473f4a9a2e464bb05da0830c8c49bafcb59b20","last_reissued_at":"2026-06-01T01:04:08.428757Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:08.428757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"cs.AI","authors_text":"Gr\\'egoire Martinon, Ibrahim Merad, Mohammed Raki","submitted_at":"2026-05-29T13:10:35Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31278","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/2605.31278/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.31278","created_at":"2026-06-01T01:04:08.428930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31278v1","created_at":"2026-06-01T01:04:08.428930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31278","created_at":"2026-06-01T01:04:08.428930+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYRL3AMIPS4T","created_at":"2026-06-01T01:04:08.428930+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYRL3AMIPS4TIKZY","created_at":"2026-06-01T01:04:08.428930+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYRL3AMI","created_at":"2026-06-01T01:04:08.428930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK","json":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK.json","graph_json":"https://pith.science/api/pith-number/QYRL3AMIPS4TIKZYKVTYKRZ7JK/graph.json","events_json":"https://pith.science/api/pith-number/QYRL3AMIPS4TIKZYKVTYKRZ7JK/events.json","paper":"https://pith.science/paper/QYRL3AMI"},"agent_actions":{"view_html":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK","download_json":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK.json","view_paper":"https://pith.science/paper/QYRL3AMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31278&json=true","fetch_graph":"https://pith.science/api/pith-number/QYRL3AMIPS4TIKZYKVTYKRZ7JK/graph.json","fetch_events":"https://pith.science/api/pith-number/QYRL3AMIPS4TIKZYKVTYKRZ7JK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK/action/storage_attestation","attest_author":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK/action/author_attestation","sign_citation":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK/action/citation_signature","submit_replication":"https://pith.science/pith/QYRL3AMIPS4TIKZYKVTYKRZ7JK/action/replication_record"}},"created_at":"2026-06-01T01:04:08.428930+00:00","updated_at":"2026-06-01T01:04:08.428930+00:00"}