{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QP225GXENRVBVBJGUHQFXJNEWS","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":"558882d3d367efbbb21b9371e6dddd3cee0bbeae45f9a6d87bec22b4d0531da8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-01-26T05:01:00Z","title_canon_sha256":"d616394f1d1f770c0259af61f2f80dc5dcf925c841022a772aa911cd95c5eb32"},"schema_version":"1.0","source":{"id":"2604.09549","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09549","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09549v2","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09549","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"QP225GXENRVB","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"QP225GXENRVBVBJG","created_at":"2026-06-02T02:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"QP225GXE","created_at":"2026-06-02T02:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:0e28310806b0ca59abe1985c74d493052e4f99462d9c44522d5d7825dfd95155","target":"graph","created_at":"2026-06-02T02:04:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments across domains show our method generates interactions more closely aligned with human behavior than prior work. We further validate our approach through offline A/B testing correlation and show that RS parameters optimized using ContextSim yield improved real-world engagement."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM agents with generated life scenarios and enforced consistency at action and trajectory levels accurately capture the contextual factors shaping genuine human decision-making."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ContextSim generates more human-aligned user interactions for recommender systems via context-aware life simulation and consistency enforcement, yielding parameters that improve real-world engagement."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ContextSim anchors LLM agents in daily life scenarios to simulate contextual user interactions for more reliable recommender evaluation."}],"snapshot_sha256":"4f4675b8ef9b5036543cc209dec82b79d07504ffc6292c15f800a31b8e93401d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"aaf9c87efedc17671c1d565f69e963c59495c71f46906e7a3cbf9880b817ea42"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.09549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recommender systems are central to online services, enabling users to navigate through massive amounts of content across various domains. However, their evaluation remains challenging due to the disconnect between offline metrics and online performance. The emergence of Large Language Model-powered agents offers a promising solution, yet existing studies model users in isolation, neglecting the contextual factors such as time, location, and needs, which fundamentally shape human decision-making. In this paper, we introduce ContextSim, an LLM agent framework that simulates believable user proxi","authors_text":"Gian Maria Marconi, Narimasa Watanabe, Nicolas Bougie, Xiaotong Ye","cross_cats":["cs.AI"],"headline":"ContextSim anchors LLM agents in daily life scenarios to simulate contextual user interactions for more reliable recommender evaluation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-01-26T05:01:00Z","title":"Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.09549","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T11:19:07.831542Z","id":"1f0b9fb8-a026-4e07-8cf2-3fab5030e527","model_set":{"reader":"grok-4.3"},"one_line_summary":"ContextSim generates more human-aligned user interactions for recommender systems via context-aware life simulation and consistency enforcement, yielding parameters that improve real-world engagement.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ContextSim anchors LLM agents in daily life scenarios to simulate contextual user interactions for more reliable recommender evaluation.","strongest_claim":"Experiments across domains show our method generates interactions more closely aligned with human behavior than prior work. We further validate our approach through offline A/B testing correlation and show that RS parameters optimized using ContextSim yield improved real-world engagement.","weakest_assumption":"That LLM agents with generated life scenarios and enforced consistency at action and trajectory levels accurately capture the contextual factors shaping genuine human decision-making."}},"verdict_id":"1f0b9fb8-a026-4e07-8cf2-3fab5030e527"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fc166b436c03b7e9b234836b7efb39f8792892d1beba5b9f027108ad82ad58c7","target":"record","created_at":"2026-06-02T02:04:52Z","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":"558882d3d367efbbb21b9371e6dddd3cee0bbeae45f9a6d87bec22b4d0531da8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-01-26T05:01:00Z","title_canon_sha256":"d616394f1d1f770c0259af61f2f80dc5dcf925c841022a772aa911cd95c5eb32"},"schema_version":"1.0","source":{"id":"2604.09549","kind":"arxiv","version":2}},"canonical_sha256":"83f5ae9ae46c6a1a8526a1e05ba5a4b49fd4e123a6186430b70a105de0e0083c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83f5ae9ae46c6a1a8526a1e05ba5a4b49fd4e123a6186430b70a105de0e0083c","first_computed_at":"2026-06-02T02:04:52.938344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:52.938344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CPyrhid0Fzi9pyuQ5jOEyiXcPN/lrT/kiNY7kAXwWphlP9loowdSFDdIea56FuAi2kFu+l7syV1wRjskX68nCw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:52.938745Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.09549","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc166b436c03b7e9b234836b7efb39f8792892d1beba5b9f027108ad82ad58c7","sha256:0e28310806b0ca59abe1985c74d493052e4f99462d9c44522d5d7825dfd95155"],"state_sha256":"33458e5ba836c6b83fda44ccfc955d6c4824b7222725d1c06269c85907c96b2f"}