{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3U4JM6P357BFTNOWATNO65NNFL","short_pith_number":"pith:3U4JM6P3","schema_version":"1.0","canonical_sha256":"dd389679fbefc259b5d604daef75ad2ae7eb74cfb43f74b1b854798b52fb86d0","source":{"kind":"arxiv","id":"2508.05512","version":1},"attestation_state":"computed","paper":{"title":"RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Abdelrahman Abdallah, Adam Jatowt, Bhawna Piryani, Jamshid Mozafari, Mahmoud Abdalla, Mohammed Ali","submitted_at":"2025-08-07T15:46:53Z","abstract_excerpt":"Evaluating the quality of retrieval-augmented generation (RAG) and document reranking systems remains challenging due to the lack of scalable, user-centric, and multi-perspective evaluation tools. We introduce RankArena, a unified platform for comparing and analysing the performance of retrieval pipelines, rerankers, and RAG systems using structured human and LLM-based feedback as well as for collecting such feedback. RankArena supports multiple evaluation modes: direct reranking visualisation, blind pairwise comparisons with human or LLM voting, supervised manual document annotation, and end-"},"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":"2508.05512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-07T15:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"fdb71668818d1af5c842113192177dcdbed8da61c533f68a692a22e7f19fa568","abstract_canon_sha256":"bb4ba6dc0e00ff411922432a7a888d4ce29935d74eb34768b1bec2317128e425"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:14.602497Z","signature_b64":"huFCIDcuzmYaajHRk5cAAXxw99MVCfcTnFB5QfuLV7L4TRy8dzaHw/yFORQ/+FB4ffB1EZk8242j3EZGpzulBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd389679fbefc259b5d604daef75ad2ae7eb74cfb43f74b1b854798b52fb86d0","last_reissued_at":"2026-07-05T11:50:14.602065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:14.602065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Abdelrahman Abdallah, Adam Jatowt, Bhawna Piryani, Jamshid Mozafari, Mahmoud Abdalla, Mohammed Ali","submitted_at":"2025-08-07T15:46:53Z","abstract_excerpt":"Evaluating the quality of retrieval-augmented generation (RAG) and document reranking systems remains challenging due to the lack of scalable, user-centric, and multi-perspective evaluation tools. We introduce RankArena, a unified platform for comparing and analysing the performance of retrieval pipelines, rerankers, and RAG systems using structured human and LLM-based feedback as well as for collecting such feedback. RankArena supports multiple evaluation modes: direct reranking visualisation, blind pairwise comparisons with human or LLM voting, supervised manual document annotation, and end-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05512","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/2508.05512/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":"2508.05512","created_at":"2026-07-05T11:50:14.602121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05512v1","created_at":"2026-07-05T11:50:14.602121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05512","created_at":"2026-07-05T11:50:14.602121+00:00"},{"alias_kind":"pith_short_12","alias_value":"3U4JM6P357BF","created_at":"2026-07-05T11:50:14.602121+00:00"},{"alias_kind":"pith_short_16","alias_value":"3U4JM6P357BFTNOW","created_at":"2026-07-05T11:50:14.602121+00:00"},{"alias_kind":"pith_short_8","alias_value":"3U4JM6P3","created_at":"2026-07-05T11:50:14.602121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16757","citing_title":"How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL","json":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL.json","graph_json":"https://pith.science/api/pith-number/3U4JM6P357BFTNOWATNO65NNFL/graph.json","events_json":"https://pith.science/api/pith-number/3U4JM6P357BFTNOWATNO65NNFL/events.json","paper":"https://pith.science/paper/3U4JM6P3"},"agent_actions":{"view_html":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL","download_json":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL.json","view_paper":"https://pith.science/paper/3U4JM6P3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05512&json=true","fetch_graph":"https://pith.science/api/pith-number/3U4JM6P357BFTNOWATNO65NNFL/graph.json","fetch_events":"https://pith.science/api/pith-number/3U4JM6P357BFTNOWATNO65NNFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL/action/storage_attestation","attest_author":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL/action/author_attestation","sign_citation":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL/action/citation_signature","submit_replication":"https://pith.science/pith/3U4JM6P357BFTNOWATNO65NNFL/action/replication_record"}},"created_at":"2026-07-05T11:50:14.602121+00:00","updated_at":"2026-07-05T11:50:14.602121+00:00"}