{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7VHDWEY5GYSM7OS64TKSN47HCN","short_pith_number":"pith:7VHDWEY5","schema_version":"1.0","canonical_sha256":"fd4e3b131d3624cfba5ee4d526f3e713732a535c3dec342d13529850556b1366","source":{"kind":"arxiv","id":"2608.01810","version":1},"attestation_state":"computed","paper":{"title":"RADAR: Rubric-Aware Dependency and Redundancy Analysis for LLM-as-Judge Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Mashhadi, Divyansh Singh, Reza Davari","submitted_at":"2026-08-03T07:21:32Z","abstract_excerpt":"Rubric-based LLM-as-judge pipelines often assume that evaluation criteria provide independent signals. In practice, however, criteria can be behaviorally coupled: improving one criterion may systematically change scores on another, distorting aggregate scores used in model-release or product-update decisions. We introduce RADAR, a lightweight preflight diagnostic framework for estimating such coupling before large-scale evaluation. Given a rubric, RADAR generates targeted synthetic probes, scores each probe on all criteria, and produces a directional coupling matrix that shows which criteria c"},"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":"2608.01810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T07:21:32Z","cross_cats_sorted":[],"title_canon_sha256":"89e80b8f19347467873718cf4bb2e072809c4f37b28c31560a7ec868f392fcc7","abstract_canon_sha256":"ccbdf2c07b3f7aa70d844832002ae9b7ba7a8f393bfe96d80770bd21b341ffc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:07:13.510505Z","signature_b64":"ggdQW6rrisL3JcSVhFWGNe+lE8OF0uQrSbTgispmsq74qmX8Dsp0zP1ZLhIOUYUg9iaByN0tz5aAcFaxXyxwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd4e3b131d3624cfba5ee4d526f3e713732a535c3dec342d13529850556b1366","last_reissued_at":"2026-08-04T02:07:13.509081Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:07:13.509081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RADAR: Rubric-Aware Dependency and Redundancy Analysis for LLM-as-Judge Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Mashhadi, Divyansh Singh, Reza Davari","submitted_at":"2026-08-03T07:21:32Z","abstract_excerpt":"Rubric-based LLM-as-judge pipelines often assume that evaluation criteria provide independent signals. In practice, however, criteria can be behaviorally coupled: improving one criterion may systematically change scores on another, distorting aggregate scores used in model-release or product-update decisions. We introduce RADAR, a lightweight preflight diagnostic framework for estimating such coupling before large-scale evaluation. Given a rubric, RADAR generates targeted synthetic probes, scores each probe on all criteria, and produces a directional coupling matrix that shows which criteria c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01810","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/2608.01810/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":"2608.01810","created_at":"2026-08-04T02:07:13.510509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01810v1","created_at":"2026-08-04T02:07:13.510509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01810","created_at":"2026-08-04T02:07:13.510509+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VHDWEY5GYSM","created_at":"2026-08-04T02:07:13.510509+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VHDWEY5GYSM7OS6","created_at":"2026-08-04T02:07:13.510509+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VHDWEY5","created_at":"2026-08-04T02:07:13.510509+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/7VHDWEY5GYSM7OS64TKSN47HCN","json":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN.json","graph_json":"https://pith.science/api/pith-number/7VHDWEY5GYSM7OS64TKSN47HCN/graph.json","events_json":"https://pith.science/api/pith-number/7VHDWEY5GYSM7OS64TKSN47HCN/events.json","paper":"https://pith.science/paper/7VHDWEY5"},"agent_actions":{"view_html":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN","download_json":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN.json","view_paper":"https://pith.science/paper/7VHDWEY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01810&json=true","fetch_graph":"https://pith.science/api/pith-number/7VHDWEY5GYSM7OS64TKSN47HCN/graph.json","fetch_events":"https://pith.science/api/pith-number/7VHDWEY5GYSM7OS64TKSN47HCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN/action/storage_attestation","attest_author":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN/action/author_attestation","sign_citation":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN/action/citation_signature","submit_replication":"https://pith.science/pith/7VHDWEY5GYSM7OS64TKSN47HCN/action/replication_record"}},"created_at":"2026-08-04T02:07:13.510509+00:00","updated_at":"2026-08-04T02:07:13.510509+00:00"}