{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HTQUPE3DLZMMRWT2QF4PTWZ5RB","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":"bf51cf5749f868c13101da6d041d5a95d9e2933b4c7bb252b5dd412aa896b837","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-08T20:35:45Z","title_canon_sha256":"65b653e616eba17ddbe626d905da4b56b346cb22a6899942be11700d32acaafb"},"schema_version":"1.0","source":{"id":"2606.10156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10156","created_at":"2026-06-10T01:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10156v1","created_at":"2026-06-10T01:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10156","created_at":"2026-06-10T01:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"HTQUPE3DLZMM","created_at":"2026-06-10T01:08:57Z"},{"alias_kind":"pith_short_16","alias_value":"HTQUPE3DLZMMRWT2","created_at":"2026-06-10T01:08:57Z"},{"alias_kind":"pith_short_8","alias_value":"HTQUPE3D","created_at":"2026-06-10T01:08:57Z"}],"graph_snapshots":[{"event_id":"sha256:d3ea54350374fd07bbe90c6cf84566794057b0be9b45418992ca6c69d84e1584","target":"graph","created_at":"2026-06-10T01:08:57Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.10156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, $\\tau","authors_text":"Bharath Sivaram Narasimhan, Karthik R Narasimhan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-08T20:35:45Z","title":"$\\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10156","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0035a63ee2abf114c2d4cb86ebe99a670be4e5e424d3b4061f9707bfe90e1411","target":"record","created_at":"2026-06-10T01:08:57Z","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":"bf51cf5749f868c13101da6d041d5a95d9e2933b4c7bb252b5dd412aa896b837","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-08T20:35:45Z","title_canon_sha256":"65b653e616eba17ddbe626d905da4b56b346cb22a6899942be11700d32acaafb"},"schema_version":"1.0","source":{"id":"2606.10156","kind":"arxiv","version":1}},"canonical_sha256":"3ce14793635e58c8da7a8178f9db3d88755b56814e9b2d4edb7c539c0712d9e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ce14793635e58c8da7a8178f9db3d88755b56814e9b2d4edb7c539c0712d9e9","first_computed_at":"2026-06-10T01:08:57.006928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:08:57.006928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WuRhboYDMr2pgUbGJeLQt/IRe/ga3VFOdLhlD09QOsTKfyr8mlBkY+OVljSBAVZ7aEOQ29iH3Ynca84X+6PLBg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:08:57.007831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0035a63ee2abf114c2d4cb86ebe99a670be4e5e424d3b4061f9707bfe90e1411","sha256:d3ea54350374fd07bbe90c6cf84566794057b0be9b45418992ca6c69d84e1584"],"state_sha256":"6360d3a62269f51e233714352ffc777498db54571beb40f4e6dff253ec5aa02e"}