{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EF2UR5CY7S2SJPCWGVQJKVFNKW","short_pith_number":"pith:EF2UR5CY","schema_version":"1.0","canonical_sha256":"217548f458fcb524bc5635609554ad55b96d7d87942e3ed50356e7fc6bafc1c4","source":{"kind":"arxiv","id":"2410.01246","version":1},"attestation_state":"computed","paper":{"title":"AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hisashi Kashima, Jiyi Li, Koh Takeuchi, Xiaotian Lu","submitted_at":"2024-10-02T05:22:07Z","abstract_excerpt":"Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to"},"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":"2410.01246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T05:22:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18081cf4aca45ef5a67c2fee5e6573f77abc2047032731c2feaa6c1cd67dd2d1","abstract_canon_sha256":"3cc4a57fc7aeda66591d81755780869311785a3f93319b78f73d150695dfcc74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:45.257720Z","signature_b64":"GvlqOW1I73nvQWpWzkUZ9s3YB3OXL945UbEypwCpwC7+7PHcUoAM8WxSPKqNmCm3zPjwAxlr2JoGoZOBdVB6Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217548f458fcb524bc5635609554ad55b96d7d87942e3ed50356e7fc6bafc1c4","last_reissued_at":"2026-07-05T09:14:45.257322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:45.257322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hisashi Kashima, Jiyi Li, Koh Takeuchi, Xiaotian Lu","submitted_at":"2024-10-02T05:22:07Z","abstract_excerpt":"Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlike close-ended questions with definitive answers. While large language models (LLMs) have demonstrated strong capabilities across various tasks, they exhibit relatively weaker performance in evaluating answers to open-ended questions. In this study, we propose a method that leverages LLMs and the analytic hierarchy process (AHP) to assess answers to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01246","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/2410.01246/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":"2410.01246","created_at":"2026-07-05T09:14:45.257376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01246v1","created_at":"2026-07-05T09:14:45.257376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01246","created_at":"2026-07-05T09:14:45.257376+00:00"},{"alias_kind":"pith_short_12","alias_value":"EF2UR5CY7S2S","created_at":"2026-07-05T09:14:45.257376+00:00"},{"alias_kind":"pith_short_16","alias_value":"EF2UR5CY7S2SJPCW","created_at":"2026-07-05T09:14:45.257376+00:00"},{"alias_kind":"pith_short_8","alias_value":"EF2UR5CY","created_at":"2026-07-05T09:14:45.257376+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/EF2UR5CY7S2SJPCWGVQJKVFNKW","json":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW.json","graph_json":"https://pith.science/api/pith-number/EF2UR5CY7S2SJPCWGVQJKVFNKW/graph.json","events_json":"https://pith.science/api/pith-number/EF2UR5CY7S2SJPCWGVQJKVFNKW/events.json","paper":"https://pith.science/paper/EF2UR5CY"},"agent_actions":{"view_html":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW","download_json":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW.json","view_paper":"https://pith.science/paper/EF2UR5CY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01246&json=true","fetch_graph":"https://pith.science/api/pith-number/EF2UR5CY7S2SJPCWGVQJKVFNKW/graph.json","fetch_events":"https://pith.science/api/pith-number/EF2UR5CY7S2SJPCWGVQJKVFNKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/action/storage_attestation","attest_author":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/action/author_attestation","sign_citation":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/action/citation_signature","submit_replication":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/action/replication_record"}},"created_at":"2026-07-05T09:14:45.257376+00:00","updated_at":"2026-07-05T09:14:45.257376+00:00"}