{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AHGE6C64Z7WXV4BDZLFQZN5SVC","short_pith_number":"pith:AHGE6C64","schema_version":"1.0","canonical_sha256":"01cc4f0bdccfed7af023cacb0cb7b2a8bdb243892888bde1a3f9b3e00aa7bfd6","source":{"kind":"arxiv","id":"2602.07840","version":3},"attestation_state":"computed","paper":{"title":"SAGE: Scalable AI Governance & Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Abhinav Gupta, Abraham Cabangbang, Andrew Kirk, Baofen Zheng, Benjamin Le, Igor Lapchuk, Jianqiang Shen, Jiewen Huang, Jingwei Wu, Kevin Rosenberg, Mathew Teoh, Nick Stern, Raghavan Muthuregunathan, Satej Milind Wagle, Thomas Kwan, Wenjing Zhang, Wenqiong Liu, Xiang Li, Xueying Lu, Zhe Zhang","submitted_at":"2026-02-08T06:42:50Z","abstract_excerpt":"Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present \\textbf{SAGE} (Scalable AI Governance \\& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration"},"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":"2602.07840","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-02-08T06:42:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0a476acea3e9d95191223f2717d81e7880874fe96fd45976e00d0bfd8959c965","abstract_canon_sha256":"f07ec5b0080cec90baa30d5e01adf53eb5c23758f2b9b6f5390998dd2d171779"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:45.521305Z","signature_b64":"YSjhsn4B5373gRPKA76iYCKPUpRZ3ii+KBy2X+WUneevSwlX3PQzfcycgGKuOQlUtknzL63bv1lpoAnTVuHEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01cc4f0bdccfed7af023cacb0cb7b2a8bdb243892888bde1a3f9b3e00aa7bfd6","last_reissued_at":"2026-06-05T00:13:45.520810Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:45.520810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAGE: Scalable AI Governance & Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Abhinav Gupta, Abraham Cabangbang, Andrew Kirk, Baofen Zheng, Benjamin Le, Igor Lapchuk, Jianqiang Shen, Jiewen Huang, Jingwei Wu, Kevin Rosenberg, Mathew Teoh, Nick Stern, Raghavan Muthuregunathan, Satej Milind Wagle, Thomas Kwan, Wenjing Zhang, Wenqiong Liu, Xiang Li, Xueying Lu, Zhe Zhang","submitted_at":"2026-02-08T06:42:50Z","abstract_excerpt":"Evaluating relevance in large-scale search systems is fundamentally constrained by the governance gap between nuanced, resource-constrained human oversight and the high-throughput requirements of production systems. While traditional approaches rely on engagement proxies or sparse manual review, these methods often fail to capture the full scope of high-impact relevance failures. We present \\textbf{SAGE} (Scalable AI Governance \\& Evaluation), a framework that operationalizes high-quality human product judgment as a scalable evaluation signal. At the core of SAGE is a bidirectional calibration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07840","kind":"arxiv","version":3},"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/2602.07840/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":"2602.07840","created_at":"2026-06-05T00:13:45.520871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.07840v3","created_at":"2026-06-05T00:13:45.520871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07840","created_at":"2026-06-05T00:13:45.520871+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHGE6C64Z7WX","created_at":"2026-06-05T00:13:45.520871+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHGE6C64Z7WXV4BD","created_at":"2026-06-05T00:13:45.520871+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHGE6C64","created_at":"2026-06-05T00:13:45.520871+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/AHGE6C64Z7WXV4BDZLFQZN5SVC","json":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC.json","graph_json":"https://pith.science/api/pith-number/AHGE6C64Z7WXV4BDZLFQZN5SVC/graph.json","events_json":"https://pith.science/api/pith-number/AHGE6C64Z7WXV4BDZLFQZN5SVC/events.json","paper":"https://pith.science/paper/AHGE6C64"},"agent_actions":{"view_html":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC","download_json":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC.json","view_paper":"https://pith.science/paper/AHGE6C64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.07840&json=true","fetch_graph":"https://pith.science/api/pith-number/AHGE6C64Z7WXV4BDZLFQZN5SVC/graph.json","fetch_events":"https://pith.science/api/pith-number/AHGE6C64Z7WXV4BDZLFQZN5SVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC/action/storage_attestation","attest_author":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC/action/author_attestation","sign_citation":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC/action/citation_signature","submit_replication":"https://pith.science/pith/AHGE6C64Z7WXV4BDZLFQZN5SVC/action/replication_record"}},"created_at":"2026-06-05T00:13:45.520871+00:00","updated_at":"2026-06-05T00:13:45.520871+00:00"}