{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MRZLSC72Y54RGGEQ3HOF3EJPKI","short_pith_number":"pith:MRZLSC72","schema_version":"1.0","canonical_sha256":"6472b90bfac779131890d9dc5d912f52079df4a9123ecbfb5b8094894867972b","source":{"kind":"arxiv","id":"2501.12152","version":2},"attestation_state":"computed","paper":{"title":"Contextualizing Recommendation Explanations with LLMs: A User Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Stefan Feuerriegel, Yash Raj Shrestha, Yuanjun Feng","submitted_at":"2025-01-21T14:02:39Z","abstract_excerpt":"Large language models (LLMs) are increasingly prevalent in recommender systems, where LLMs can be used to generate personalized recommendations. Here, we examine how different LLM-generated explanations for movie recommendations affect users' perceptions of cognitive, affective, and utilitarian needs and consumption intentions. In a pre-registered, between-subject online experiment (N=759) and follow-up interviews (N=30), we compare (a) LLM-generated generic explanations, and (b) LLM-generated contextualized explanations. Our findings show that contextualized explanations (i.e., explanations t"},"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":"2501.12152","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2025-01-21T14:02:39Z","cross_cats_sorted":[],"title_canon_sha256":"8babbdd37086c76ab7af418c78142c569c0446432005d7d31f136e0724925a28","abstract_canon_sha256":"648d079873a3a6bea79310acf8539b92456acada872113fc04765c55fb8f3feb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:01.763967Z","signature_b64":"LADMXFMycyB5nsWGDtXfU6W3Kz/d1PQ2/56s/0iMQuqoQXMunU4qj/kFjGqgkr94ej9kzBNA9TYiJwFI/F1aAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6472b90bfac779131890d9dc5d912f52079df4a9123ecbfb5b8094894867972b","last_reissued_at":"2026-07-05T11:56:01.763449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:01.763449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextualizing Recommendation Explanations with LLMs: A User Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Stefan Feuerriegel, Yash Raj Shrestha, Yuanjun Feng","submitted_at":"2025-01-21T14:02:39Z","abstract_excerpt":"Large language models (LLMs) are increasingly prevalent in recommender systems, where LLMs can be used to generate personalized recommendations. Here, we examine how different LLM-generated explanations for movie recommendations affect users' perceptions of cognitive, affective, and utilitarian needs and consumption intentions. In a pre-registered, between-subject online experiment (N=759) and follow-up interviews (N=30), we compare (a) LLM-generated generic explanations, and (b) LLM-generated contextualized explanations. Our findings show that contextualized explanations (i.e., explanations t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12152","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/2501.12152/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":"2501.12152","created_at":"2026-07-05T11:56:01.763508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12152v2","created_at":"2026-07-05T11:56:01.763508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12152","created_at":"2026-07-05T11:56:01.763508+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRZLSC72Y54R","created_at":"2026-07-05T11:56:01.763508+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRZLSC72Y54RGGEQ","created_at":"2026-07-05T11:56:01.763508+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRZLSC72","created_at":"2026-07-05T11:56:01.763508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00669","citing_title":"GARDRec: Decision-Level Graph Grounding for Large Language Model Recommendation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI","json":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI.json","graph_json":"https://pith.science/api/pith-number/MRZLSC72Y54RGGEQ3HOF3EJPKI/graph.json","events_json":"https://pith.science/api/pith-number/MRZLSC72Y54RGGEQ3HOF3EJPKI/events.json","paper":"https://pith.science/paper/MRZLSC72"},"agent_actions":{"view_html":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI","download_json":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI.json","view_paper":"https://pith.science/paper/MRZLSC72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12152&json=true","fetch_graph":"https://pith.science/api/pith-number/MRZLSC72Y54RGGEQ3HOF3EJPKI/graph.json","fetch_events":"https://pith.science/api/pith-number/MRZLSC72Y54RGGEQ3HOF3EJPKI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI/action/storage_attestation","attest_author":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI/action/author_attestation","sign_citation":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI/action/citation_signature","submit_replication":"https://pith.science/pith/MRZLSC72Y54RGGEQ3HOF3EJPKI/action/replication_record"}},"created_at":"2026-07-05T11:56:01.763508+00:00","updated_at":"2026-07-05T11:56:01.763508+00:00"}