{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HTQUPE3DLZMMRWT2QF4PTWZ5RB","short_pith_number":"pith:HTQUPE3D","schema_version":"1.0","canonical_sha256":"3ce14793635e58c8da7a8178f9db3d88755b56814e9b2d4edb7c539c0712d9e9","source":{"kind":"arxiv","id":"2606.10156","version":1},"attestation_state":"computed","paper":{"title":"$\\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Bharath Sivaram Narasimhan, Karthik R Narasimhan","submitted_at":"2026-06-08T20:35:45Z","abstract_excerpt":"As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benchmarks often rely on \"LLM-as-a-judge\" evaluations, which introduce subjectivity, high costs and inconsistency. We present $\\tau$-Rec, a benchmark for agentic recommender systems that replaces subjective evaluation with verifiable rewards and a reveal-tagged elicitation (RTE) mechanism that controls how task constraints surface during dialogue. By testing agents against structured catalog predicates and employing a pass^k reliability metric, $\\tau"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.10156","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-08T20:35:45Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"65b653e616eba17ddbe626d905da4b56b346cb22a6899942be11700d32acaafb","abstract_canon_sha256":"bf51cf5749f868c13101da6d041d5a95d9e2933b4c7bb252b5dd412aa896b837"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:57.007831Z","signature_b64":"WuRhboYDMr2pgUbGJeLQt/IRe/ga3VFOdLhlD09QOsTKfyr8mlBkY+OVljSBAVZ7aEOQ29iH3Ynca84X+6PLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ce14793635e58c8da7a8178f9db3d88755b56814e9b2d4edb7c539c0712d9e9","last_reissued_at":"2026-06-10T01:08:57.006928Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:57.006928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$\\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Bharath Sivaram Narasimhan, Karthik R Narasimhan","submitted_at":"2026-06-08T20:35:45Z","abstract_excerpt":"As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benchmarks often rely on \"LLM-as-a-judge\" evaluations, which introduce subjectivity, high costs and inconsistency. We present $\\tau$-Rec, a benchmark for agentic recommender systems that replaces subjective evaluation with verifiable rewards and a reveal-tagged elicitation (RTE) mechanism that controls how task constraints surface during dialogue. By testing agents against structured catalog predicates and employing a pass^k reliability metric, $\\tau"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10156","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/2606.10156/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":"2606.10156","created_at":"2026-06-10T01:08:57.007083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10156v1","created_at":"2026-06-10T01:08:57.007083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10156","created_at":"2026-06-10T01:08:57.007083+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTQUPE3DLZMM","created_at":"2026-06-10T01:08:57.007083+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTQUPE3DLZMMRWT2","created_at":"2026-06-10T01:08:57.007083+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTQUPE3D","created_at":"2026-06-10T01:08:57.007083+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/HTQUPE3DLZMMRWT2QF4PTWZ5RB","json":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB.json","graph_json":"https://pith.science/api/pith-number/HTQUPE3DLZMMRWT2QF4PTWZ5RB/graph.json","events_json":"https://pith.science/api/pith-number/HTQUPE3DLZMMRWT2QF4PTWZ5RB/events.json","paper":"https://pith.science/paper/HTQUPE3D"},"agent_actions":{"view_html":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB","download_json":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB.json","view_paper":"https://pith.science/paper/HTQUPE3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10156&json=true","fetch_graph":"https://pith.science/api/pith-number/HTQUPE3DLZMMRWT2QF4PTWZ5RB/graph.json","fetch_events":"https://pith.science/api/pith-number/HTQUPE3DLZMMRWT2QF4PTWZ5RB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB/action/storage_attestation","attest_author":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB/action/author_attestation","sign_citation":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB/action/citation_signature","submit_replication":"https://pith.science/pith/HTQUPE3DLZMMRWT2QF4PTWZ5RB/action/replication_record"}},"created_at":"2026-06-10T01:08:57.007083+00:00","updated_at":"2026-06-10T01:08:57.007083+00:00"}