{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KHJXCQTWCPS5WFJHDQQO5LKZVZ","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":"a507788aa97b6e93727a42fbf89b78e5abd309a9e32e0cbcc8b7d4da281ed0ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-11T21:48:54Z","title_canon_sha256":"dc65462e862e8c7759524695a1abe0420fdebe9bef9e8a773a728ca47fb34c6e"},"schema_version":"1.0","source":{"id":"2404.08137","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08137","created_at":"2026-07-05T10:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08137v3","created_at":"2026-07-05T10:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08137","created_at":"2026-07-05T10:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"KHJXCQTWCPS5","created_at":"2026-07-05T10:07:01Z"},{"alias_kind":"pith_short_16","alias_value":"KHJXCQTWCPS5WFJH","created_at":"2026-07-05T10:07:01Z"},{"alias_kind":"pith_short_8","alias_value":"KHJXCQTW","created_at":"2026-07-05T10:07:01Z"}],"graph_snapshots":[{"event_id":"sha256:860194aa8582e20268ed64230eaa166da805a0ccd50c8c7cfdd4a11223ce3f76","target":"graph","created_at":"2026-07-05T10:07:01Z","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/2404.08137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this chapter, we consider generative information retrieval evaluation from two distinct but interrelated perspectives. First, large language models (LLMs) themselves are rapidly becoming tools for evaluation, with current research indicating that LLMs may be superior to crowdsource workers and other paid assessors on basic relevance judgement tasks. We review past and ongoing related research, including speculation on the future of shared task initiatives, such as TREC, and a discussion on the continuing need for human assessments. Second, we consider the evaluation of emerging LLM-based ge","authors_text":"Charles L. A. Clarke, Mark Sanderson, Marwah Alaofi, Negar Arabzadeh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-11T21:48:54Z","title":"Generative Information Retrieval Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08137","kind":"arxiv","version":3},"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":"sha256:60f7a92b264db489cf6bd2d5818c52892929688f48241186e0652b2aed52792d","target":"record","created_at":"2026-07-05T10:07:01Z","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":"a507788aa97b6e93727a42fbf89b78e5abd309a9e32e0cbcc8b7d4da281ed0ed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-04-11T21:48:54Z","title_canon_sha256":"dc65462e862e8c7759524695a1abe0420fdebe9bef9e8a773a728ca47fb34c6e"},"schema_version":"1.0","source":{"id":"2404.08137","kind":"arxiv","version":3}},"canonical_sha256":"51d371427613e5db15271c20eead59ae7cdf7b8b4250f777c2ee3176b06c9c9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51d371427613e5db15271c20eead59ae7cdf7b8b4250f777c2ee3176b06c9c9e","first_computed_at":"2026-07-05T10:07:01.150961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:01.150961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqfqO+nz6Bkqcz6MtpVyKMOx+rR/N6xdq1pJv/xIEf0739SARAZ7lk/wOv+HhILWmCf3FPF4MlNbYdk09ue1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:01.151388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08137","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60f7a92b264db489cf6bd2d5818c52892929688f48241186e0652b2aed52792d","sha256:860194aa8582e20268ed64230eaa166da805a0ccd50c8c7cfdd4a11223ce3f76"],"state_sha256":"1198de6db85e34e13bfa53d43970ac3b74f93aafef28d6a99deaefb493c9a808"}