{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GWEUPL5XHIN2BI7PXNNGNYAXQ4","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":"64c87e1d9fd05edfad2dce99ffbd4484134f0c80ef1998735089a61834409946","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-16T18:17:19Z","title_canon_sha256":"6dd9af01595d793c478d75b69240c1f02278560e299b54f8482357d19cd90a2e"},"schema_version":"1.0","source":{"id":"2504.12408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12408","created_at":"2026-07-05T10:50:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12408v1","created_at":"2026-07-05T10:50:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12408","created_at":"2026-07-05T10:50:15Z"},{"alias_kind":"pith_short_12","alias_value":"GWEUPL5XHIN2","created_at":"2026-07-05T10:50:15Z"},{"alias_kind":"pith_short_16","alias_value":"GWEUPL5XHIN2BI7P","created_at":"2026-07-05T10:50:15Z"},{"alias_kind":"pith_short_8","alias_value":"GWEUPL5X","created_at":"2026-07-05T10:50:15Z"}],"graph_snapshots":[{"event_id":"sha256:01876061674b66dda1568df0be3d466b91b05168ce83864528a31bcefc4727e9","target":"graph","created_at":"2026-07-05T10:50:15Z","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/2504.12408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly used to automate relevance judgments for information retrieval (IR) tasks, often demonstrating agreement with human labels that approaches inter-human agreement. To assess the robustness and reliability of LLM-based relevance judgments, we systematically investigate impact of prompt sensitivity on the task. We collected prompts for relevance assessment from 15 human experts and 15 LLMs across three tasks~ -- ~binary, graded, and pairwise~ -- ~yielding 90 prompts in total. After filtering out unusable prompts from three humans and three LLMs, we emp","authors_text":"Charles L. A . Clarke, Negar Arabzadeh","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-16T18:17:19Z","title":"A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12408","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":"sha256:9c4a93fb598756423a8cb64c904cd093ab02410fab9d8dc990c1fe1b8c1979f9","target":"record","created_at":"2026-07-05T10:50:15Z","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":"64c87e1d9fd05edfad2dce99ffbd4484134f0c80ef1998735089a61834409946","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-16T18:17:19Z","title_canon_sha256":"6dd9af01595d793c478d75b69240c1f02278560e299b54f8482357d19cd90a2e"},"schema_version":"1.0","source":{"id":"2504.12408","kind":"arxiv","version":1}},"canonical_sha256":"358947afb73a1ba0a3efbb5a66e017872efdd64417110e60c3f90676668ae64b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"358947afb73a1ba0a3efbb5a66e017872efdd64417110e60c3f90676668ae64b","first_computed_at":"2026-07-05T10:50:15.917419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:15.917419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yb5rKnTHS8R6ChJdH66nq2zOOByFjJkcA/crWLyWYCPV6CGGvUiHPT+XgUq8XABIG759+D4QhoABLrgprtSjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:15.917908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c4a93fb598756423a8cb64c904cd093ab02410fab9d8dc990c1fe1b8c1979f9","sha256:01876061674b66dda1568df0be3d466b91b05168ce83864528a31bcefc4727e9"],"state_sha256":"a8be44eb58fde6021704be2b983b1572af7553eb23236dcafa5fcd59c05ae96e"}