{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GRDN3UBCUQJZHDOZ2Q72M76GWJ","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":"cf0e9290db000169f64f70bc1287df52063ce741bbfcda95cbef0230c14465c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T19:04:15Z","title_canon_sha256":"a710fdfbee02931933c57b58fcfdd2ea06c5c0ecbd9b65f2a8c2ae37e91c738d"},"schema_version":"1.0","source":{"id":"2412.13268","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13268","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13268v1","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13268","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"pith_short_12","alias_value":"GRDN3UBCUQJZ","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"pith_short_16","alias_value":"GRDN3UBCUQJZHDOZ","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"pith_short_8","alias_value":"GRDN3UBC","created_at":"2026-07-05T09:50:58Z"}],"graph_snapshots":[{"event_id":"sha256:8b78352201b9a7ce76cc57255e629b76d5e11e594c82f764772bb21e73371d45","target":"graph","created_at":"2026-07-05T09:50:58Z","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/2412.13268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effective training and evaluation of retrieval systems require a substantial amount of relevance judgments, which are traditionally collected from human assessors -- a process that is both costly and time-consuming. Large Language Models (LLMs) have shown promise in generating relevance labels for search tasks, offering a potential alternative to manual assessments. Current approaches often rely on a single LLM, such as GPT-4, which, despite being effective, are expensive and prone to intra-model biases that can favour systems leveraging similar models. In this work, we introduce JudgeBlen","authors_text":"Bhaskar Mitra, Emine Yilmaz, Hossein A. Rahmani, Nick Craswell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T19:04:15Z","title":"JudgeBlender: Ensembling Judgments for Automatic Relevance Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13268","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":"sha256:921c8218223eef005ab94d69b522a337a00e937cdf9fcbdb32bb0bae3f75e63b","target":"record","created_at":"2026-07-05T09:50:58Z","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":"cf0e9290db000169f64f70bc1287df52063ce741bbfcda95cbef0230c14465c4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T19:04:15Z","title_canon_sha256":"a710fdfbee02931933c57b58fcfdd2ea06c5c0ecbd9b65f2a8c2ae37e91c738d"},"schema_version":"1.0","source":{"id":"2412.13268","kind":"arxiv","version":1}},"canonical_sha256":"3446ddd022a413938dd9d43fa67fc6b2425062a45e7bedb31bce719e4c673663","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3446ddd022a413938dd9d43fa67fc6b2425062a45e7bedb31bce719e4c673663","first_computed_at":"2026-07-05T09:50:58.930138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:58.930138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EyDxtqndnT685qH86JO5B5rQC21ZVBxFPidoy9ThsFukRnTduRSav2XKxL6RG0Ap1UaEc97Mg6gr3t3D1uGaBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:58.930633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13268","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:921c8218223eef005ab94d69b522a337a00e937cdf9fcbdb32bb0bae3f75e63b","sha256:8b78352201b9a7ce76cc57255e629b76d5e11e594c82f764772bb21e73371d45"],"state_sha256":"df62c1527ddcf7262ea2f69ec583b505ab5b452d4032b12a0d1f2cd522340ec0"}