{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3YTUKLY2VB5II7IMZPVNHGJBIU","short_pith_number":"pith:3YTUKLY2","schema_version":"1.0","canonical_sha256":"de27452f1aa87a847d0ccbead399214529c2b665a0516e03de5fda73c3fa0416","source":{"kind":"arxiv","id":"2508.01674","version":2},"attestation_state":"computed","paper":{"title":"CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jiho Kim, Juho Kim, Tae Soo Kim, Yoonah Park, Yoonjoo Lee, Young-Ho Kim","submitted_at":"2025-08-03T09:04:48Z","abstract_excerpt":"Personalization of Large Language Models (LLMs) often assumes users hold static preferences that reflect globally in all tasks. In reality, humans hold dynamic preferences that change depending on the context. As users interact with an LLM in various contexts, they naturally reveal their contextual preferences, which a model must infer and apply in future contexts to ensure alignment. To assess this, we introduce CUPID, a benchmark of 756 human-curated interaction session histories between users and LLM-based chat assistants. In each interaction session, the user provides a request in a specif"},"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":"2508.01674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-03T09:04:48Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"a1ed920c70a24ad29428082055a0cb2b9a36f35656067f3c0669f355f497f371","abstract_canon_sha256":"6269612227343e171c8ddb693095d29a0a06f117937f948bdd6c6fd5b198593e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:58.934924Z","signature_b64":"GG7IqS0EqCrRaz2hLZnrl/Z2DlPoZ883k9ZX5UQsrABTZprwGI1Sn4LhhOcqlVXOFdAS51u/32JW3RXgewh8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de27452f1aa87a847d0ccbead399214529c2b665a0516e03de5fda73c3fa0416","last_reissued_at":"2026-07-05T11:49:58.934416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:58.934416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CUPID: Evaluating Personalized and Contextualized Alignment of LLMs from Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jiho Kim, Juho Kim, Tae Soo Kim, Yoonah Park, Yoonjoo Lee, Young-Ho Kim","submitted_at":"2025-08-03T09:04:48Z","abstract_excerpt":"Personalization of Large Language Models (LLMs) often assumes users hold static preferences that reflect globally in all tasks. In reality, humans hold dynamic preferences that change depending on the context. As users interact with an LLM in various contexts, they naturally reveal their contextual preferences, which a model must infer and apply in future contexts to ensure alignment. To assess this, we introduce CUPID, a benchmark of 756 human-curated interaction session histories between users and LLM-based chat assistants. In each interaction session, the user provides a request in a specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01674","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/2508.01674/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":"2508.01674","created_at":"2026-07-05T11:49:58.934493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01674v2","created_at":"2026-07-05T11:49:58.934493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01674","created_at":"2026-07-05T11:49:58.934493+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YTUKLY2VB5I","created_at":"2026-07-05T11:49:58.934493+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YTUKLY2VB5II7IM","created_at":"2026-07-05T11:49:58.934493+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YTUKLY2","created_at":"2026-07-05T11:49:58.934493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04780","citing_title":"PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16712","citing_title":"Recall Isn't Enough: Bounding Commitments in Personalized Language Systems","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02585","citing_title":"Mitigating LLM biases toward spurious social contexts using direct preference optimization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09996","citing_title":"Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17886","citing_title":"Latent Preference Modeling for Cross-Session Personalized Tool Calling","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10925","citing_title":"From Words to Widgets for Controllable LLM Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06134","citing_title":"MAESTRO: Adapting GUIs and Guiding Navigation with User Preferences in Conversational Agents with GUIs","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU","json":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU.json","graph_json":"https://pith.science/api/pith-number/3YTUKLY2VB5II7IMZPVNHGJBIU/graph.json","events_json":"https://pith.science/api/pith-number/3YTUKLY2VB5II7IMZPVNHGJBIU/events.json","paper":"https://pith.science/paper/3YTUKLY2"},"agent_actions":{"view_html":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU","download_json":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU.json","view_paper":"https://pith.science/paper/3YTUKLY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01674&json=true","fetch_graph":"https://pith.science/api/pith-number/3YTUKLY2VB5II7IMZPVNHGJBIU/graph.json","fetch_events":"https://pith.science/api/pith-number/3YTUKLY2VB5II7IMZPVNHGJBIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU/action/storage_attestation","attest_author":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU/action/author_attestation","sign_citation":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU/action/citation_signature","submit_replication":"https://pith.science/pith/3YTUKLY2VB5II7IMZPVNHGJBIU/action/replication_record"}},"created_at":"2026-07-05T11:49:58.934493+00:00","updated_at":"2026-07-05T11:49:58.934493+00:00"}