{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EF2UR5CY7S2SJPCWGVQJKVFNKW","short_pith_number":"pith:EF2UR5CY","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"},"canonical_sha256":"217548f458fcb524bc5635609554ad55b96d7d87942e3ed50356e7fc6bafc1c4","source":{"kind":"arxiv","id":"2410.01246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01246","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01246v1","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01246","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"EF2UR5CY7S2S","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"EF2UR5CY7S2SJPCW","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"EF2UR5CY","created_at":"2026-07-05T09:14:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EF2UR5CY7S2SJPCWGVQJKVFNKW","target":"record","payload":{"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"},"canonical_sha256":"217548f458fcb524bc5635609554ad55b96d7d87942e3ed50356e7fc6bafc1c4","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"},"source_kind":"arxiv","source_id":"2410.01246","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qkKNC87mxRVEI5ovwLn8ru6Ma+K/dn8pI0Di+LMxNNb66IwGy8gjmlCpTU45ew9fW4JP+gd3eX74O3lkD+AYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T09:53:33.637081Z"},"content_sha256":"1693c8bd57d6e768324f5083f4ea678a49bbc287289e9c908f5fdda25eeb2ed5","schema_version":"1.0","event_id":"sha256:1693c8bd57d6e768324f5083f4ea678a49bbc287289e9c908f5fdda25eeb2ed5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EF2UR5CY7S2SJPCWGVQJKVFNKW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4yyefz5Xky08gGdjMLTyKr3Q1zEOHfz+Sdx5x30ZLYsADfKDkjVf5rKp//Dr8cXbSDOtrm7uADB9up/xMomCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T09:53:33.637577Z"},"content_sha256":"2d292b0b31e0ada749abf5bfd35d66dcd669d0f6f5fc72062d46fa9381c77131","schema_version":"1.0","event_id":"sha256:2d292b0b31e0ada749abf5bfd35d66dcd669d0f6f5fc72062d46fa9381c77131"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/bundle.json","state_url":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T09:53:33Z","links":{"resolver":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW","bundle":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/bundle.json","state":"https://pith.science/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EF2UR5CY7S2SJPCWGVQJKVFNKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EF2UR5CY7S2SJPCWGVQJKVFNKW","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":"3cc4a57fc7aeda66591d81755780869311785a3f93319b78f73d150695dfcc74","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T05:22:07Z","title_canon_sha256":"18081cf4aca45ef5a67c2fee5e6573f77abc2047032731c2feaa6c1cd67dd2d1"},"schema_version":"1.0","source":{"id":"2410.01246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01246","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01246v1","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01246","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"EF2UR5CY7S2S","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"EF2UR5CY7S2SJPCW","created_at":"2026-07-05T09:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"EF2UR5CY","created_at":"2026-07-05T09:14:45Z"}],"graph_snapshots":[{"event_id":"sha256:2d292b0b31e0ada749abf5bfd35d66dcd669d0f6f5fc72062d46fa9381c77131","target":"graph","created_at":"2026-07-05T09:14:45Z","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/2410.01246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hisashi Kashima, Jiyi Li, Koh Takeuchi, Xiaotian Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T05:22:07Z","title":"AHP-Powered LLM Reasoning for Multi-Criteria Evaluation of Open-Ended Responses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01246","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":"sha256:1693c8bd57d6e768324f5083f4ea678a49bbc287289e9c908f5fdda25eeb2ed5","target":"record","created_at":"2026-07-05T09:14:45Z","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":"3cc4a57fc7aeda66591d81755780869311785a3f93319b78f73d150695dfcc74","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T05:22:07Z","title_canon_sha256":"18081cf4aca45ef5a67c2fee5e6573f77abc2047032731c2feaa6c1cd67dd2d1"},"schema_version":"1.0","source":{"id":"2410.01246","kind":"arxiv","version":1}},"canonical_sha256":"217548f458fcb524bc5635609554ad55b96d7d87942e3ed50356e7fc6bafc1c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"217548f458fcb524bc5635609554ad55b96d7d87942e3ed50356e7fc6bafc1c4","first_computed_at":"2026-07-05T09:14:45.257322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:45.257322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GvlqOW1I73nvQWpWzkUZ9s3YB3OXL945UbEypwCpwC7+7PHcUoAM8WxSPKqNmCm3zPjwAxlr2JoGoZOBdVB6Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:45.257720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1693c8bd57d6e768324f5083f4ea678a49bbc287289e9c908f5fdda25eeb2ed5","sha256:2d292b0b31e0ada749abf5bfd35d66dcd669d0f6f5fc72062d46fa9381c77131"],"state_sha256":"33b7b6b22bcf15a9e2ef87d91abcc123514d06af11ea5b1a765431cb7b304794"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSaryDOwnmRgs9e/JbHnsXxIuW7OjfM57TJKU+qHHsGMFo56Lfu63Z4tDYCp8bfWfj3m9XEgBar3lOU1RuUWDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T09:53:33.641615Z","bundle_sha256":"cbfc4e708ec5b03734f8f8c9caf934e88404c8dc54f2ce17dc62887cce4fad60"}}