{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:27R2OM7A2OFS3CEEHTATCM5V2K","short_pith_number":"pith:27R2OM7A","schema_version":"1.0","canonical_sha256":"d7e3a733e0d38b2d88843cc13133b5d2806513b9a595c539a62309a1d9445d4d","source":{"kind":"arxiv","id":"2605.18805","version":1},"attestation_state":"computed","paper":{"title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexandre Gilotte, Benjamin Heymann, Flavian Vasile, Imad Aouali, Otmane Sakhi","submitted_at":"2026-05-11T18:55:32Z","abstract_excerpt":"LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduce this setting to reranking small shortlisted candidate sets or judge reports mainly by semantic plausibility. We introduce Recommendation Atlas (Agentic Tool-Level Assessment for Shopping), or RecoAtlas, a benchmark and toolkit for evaluating shopping agents with behavior-grounded metrics. RecoAtlas complements held-out interaction metrics with learned utility proxies for relevance, complementarity, and diversity de"},"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":"2605.18805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-11T18:55:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c1cd727338e927faaa639c8ceecdd31e09178a869ea440e8071572e995bea05a","abstract_canon_sha256":"9542864926575183eef130bbdd874d99d9d3ad06d4d33d26b2f0e5fe203d2c00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:23.407886Z","signature_b64":"Eju+YsoKMAAxt2sMo5P/jWwc3XoysvjlFe/FxP7UMcC0HWzDfVRW1SxCd/mWvjbNZ3RZD5aztNEV9tH1MGIdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7e3a733e0d38b2d88843cc13133b5d2806513b9a595c539a62309a1d9445d4d","last_reissued_at":"2026-05-20T00:06:23.407074Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:23.407074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Alexandre Gilotte, Benjamin Heymann, Flavian Vasile, Imad Aouali, Otmane Sakhi","submitted_at":"2026-05-11T18:55:32Z","abstract_excerpt":"LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduce this setting to reranking small shortlisted candidate sets or judge reports mainly by semantic plausibility. We introduce Recommendation Atlas (Agentic Tool-Level Assessment for Shopping), or RecoAtlas, a benchmark and toolkit for evaluating shopping agents with behavior-grounded metrics. RecoAtlas complements held-out interaction metrics with learned utility proxies for relevance, complementarity, and diversity de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18805","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/2605.18805/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":"2605.18805","created_at":"2026-05-20T00:06:23.407201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18805v1","created_at":"2026-05-20T00:06:23.407201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18805","created_at":"2026-05-20T00:06:23.407201+00:00"},{"alias_kind":"pith_short_12","alias_value":"27R2OM7A2OFS","created_at":"2026-05-20T00:06:23.407201+00:00"},{"alias_kind":"pith_short_16","alias_value":"27R2OM7A2OFS3CEE","created_at":"2026-05-20T00:06:23.407201+00:00"},{"alias_kind":"pith_short_8","alias_value":"27R2OM7A","created_at":"2026-05-20T00:06:23.407201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K","json":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K.json","graph_json":"https://pith.science/api/pith-number/27R2OM7A2OFS3CEEHTATCM5V2K/graph.json","events_json":"https://pith.science/api/pith-number/27R2OM7A2OFS3CEEHTATCM5V2K/events.json","paper":"https://pith.science/paper/27R2OM7A"},"agent_actions":{"view_html":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K","download_json":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K.json","view_paper":"https://pith.science/paper/27R2OM7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18805&json=true","fetch_graph":"https://pith.science/api/pith-number/27R2OM7A2OFS3CEEHTATCM5V2K/graph.json","fetch_events":"https://pith.science/api/pith-number/27R2OM7A2OFS3CEEHTATCM5V2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K/action/storage_attestation","attest_author":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K/action/author_attestation","sign_citation":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K/action/citation_signature","submit_replication":"https://pith.science/pith/27R2OM7A2OFS3CEEHTATCM5V2K/action/replication_record"}},"created_at":"2026-05-20T00:06:23.407201+00:00","updated_at":"2026-05-20T00:06:23.407201+00:00"}