{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W6L2XJAJCRVGZFTQITF6QDBLOF","short_pith_number":"pith:W6L2XJAJ","schema_version":"1.0","canonical_sha256":"b797aba409146a6c967044cbe80c2b7141bb06e565fddea137aec97366dd35ca","source":{"kind":"arxiv","id":"2406.03248","version":2},"attestation_state":"computed","paper":{"title":"Large Language Models as Evaluators for Recommendation Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bowen Sun, Jiayin Wang, Min Zhang, Peijie Sun, Weizhi Ma, Xiaoyu Zhang, Yishan Li","submitted_at":"2024-06-05T13:23:23Z","abstract_excerpt":"The explainability of recommender systems has attracted significant attention in academia and industry. Many efforts have been made for explainable recommendations, yet evaluating the quality of the explanations remains a challenging and unresolved issue. In recent years, leveraging LLMs as evaluators presents a promising avenue in Natural Language Processing tasks (e.g., sentiment classification, information extraction), as they perform strong capabilities in instruction following and common-sense reasoning. However, evaluating recommendation explanatory texts is different from these NLG task"},"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":"2406.03248","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-05T13:23:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"db45f67d1ea1c95b5abd820862595a6a487feb8a20fac0fefc5be1ad1c78edbc","abstract_canon_sha256":"5f6219af643251777798d2a5bc16e56f7f5959a0a7b5be4815f91959fbe1426c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:12.064665Z","signature_b64":"VLMgRalm2TL/gcbq29lOSZYVxy4VmguWAYOXCsJ0ykwuDQAph2ptno6CaKN1sHfT8vl1Z2yospHy0am+PfGBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b797aba409146a6c967044cbe80c2b7141bb06e565fddea137aec97366dd35ca","last_reissued_at":"2026-07-05T08:28:12.064219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:12.064219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models as Evaluators for Recommendation Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bowen Sun, Jiayin Wang, Min Zhang, Peijie Sun, Weizhi Ma, Xiaoyu Zhang, Yishan Li","submitted_at":"2024-06-05T13:23:23Z","abstract_excerpt":"The explainability of recommender systems has attracted significant attention in academia and industry. Many efforts have been made for explainable recommendations, yet evaluating the quality of the explanations remains a challenging and unresolved issue. In recent years, leveraging LLMs as evaluators presents a promising avenue in Natural Language Processing tasks (e.g., sentiment classification, information extraction), as they perform strong capabilities in instruction following and common-sense reasoning. However, evaluating recommendation explanatory texts is different from these NLG task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03248","kind":"arxiv","version":2},"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/2406.03248/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":"2406.03248","created_at":"2026-07-05T08:28:12.064274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03248v2","created_at":"2026-07-05T08:28:12.064274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03248","created_at":"2026-07-05T08:28:12.064274+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6L2XJAJCRVG","created_at":"2026-07-05T08:28:12.064274+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6L2XJAJCRVGZFTQ","created_at":"2026-07-05T08:28:12.064274+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6L2XJAJ","created_at":"2026-07-05T08:28:12.064274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11068","citing_title":"RecSys Arena: Pair-wise Recommender System Evaluation with Large Language Models","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF","json":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF.json","graph_json":"https://pith.science/api/pith-number/W6L2XJAJCRVGZFTQITF6QDBLOF/graph.json","events_json":"https://pith.science/api/pith-number/W6L2XJAJCRVGZFTQITF6QDBLOF/events.json","paper":"https://pith.science/paper/W6L2XJAJ"},"agent_actions":{"view_html":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF","download_json":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF.json","view_paper":"https://pith.science/paper/W6L2XJAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03248&json=true","fetch_graph":"https://pith.science/api/pith-number/W6L2XJAJCRVGZFTQITF6QDBLOF/graph.json","fetch_events":"https://pith.science/api/pith-number/W6L2XJAJCRVGZFTQITF6QDBLOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF/action/storage_attestation","attest_author":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF/action/author_attestation","sign_citation":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF/action/citation_signature","submit_replication":"https://pith.science/pith/W6L2XJAJCRVGZFTQITF6QDBLOF/action/replication_record"}},"created_at":"2026-07-05T08:28:12.064274+00:00","updated_at":"2026-07-05T08:28:12.064274+00:00"}