{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DB255CSZHZHCXNYG6UUK2KUZY2","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":"dfc1121d4a3736b2a290ef6daadda0295399bc9ad08e638aa5e5a6ab9f840c53","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T19:56:10Z","title_canon_sha256":"db5e460a06649e09ff6d1f8f37d6d135ef88e8547f71ab3ff01e3e7d3e5eb144"},"schema_version":"1.0","source":{"id":"2305.13455","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13455","created_at":"2026-07-05T07:15:55Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13455v3","created_at":"2026-07-05T07:15:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13455","created_at":"2026-07-05T07:15:55Z"},{"alias_kind":"pith_short_12","alias_value":"DB255CSZHZHC","created_at":"2026-07-05T07:15:55Z"},{"alias_kind":"pith_short_16","alias_value":"DB255CSZHZHCXNYG","created_at":"2026-07-05T07:15:55Z"},{"alias_kind":"pith_short_8","alias_value":"DB255CSZ","created_at":"2026-07-05T07:15:55Z"}],"graph_snapshots":[{"event_id":"sha256:7d12dbea5b1972872ee69bac3c7ab6169a6ff8bd90c379be1aea999b5ceb63a5","target":"graph","created_at":"2026-07-05T07:15:55Z","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/2305.13455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has proposed a methodology for the systematic evaluation of \"Situated Language Understanding Agents\"-agents that operate in rich linguistic and non-linguistic contexts-through testing them in carefully constructed interactive settings. Other recent work has argued that Large Language Models (LLMs), if suitably set up, can be understood as (simulators of) such agents. A connection suggests itself, which this paper explores: Can LLMs be evaluated meaningfully by exposing them to constrained game-like settings that are built to challenge specific capabilities? As a proof of concept, t","authors_text":"Brielen Madureira, David Schlangen, Jana G\\\"otze, Kranti Chalamalasetti, Philipp Sadler, Sherzod Hakimov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T19:56:10Z","title":"Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13455","kind":"arxiv","version":3},"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:a3342340e151000b8d04eee3d4a9c111cb41bde1bf80fc4df46db6591390eafd","target":"record","created_at":"2026-07-05T07:15:55Z","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":"dfc1121d4a3736b2a290ef6daadda0295399bc9ad08e638aa5e5a6ab9f840c53","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T19:56:10Z","title_canon_sha256":"db5e460a06649e09ff6d1f8f37d6d135ef88e8547f71ab3ff01e3e7d3e5eb144"},"schema_version":"1.0","source":{"id":"2305.13455","kind":"arxiv","version":3}},"canonical_sha256":"1875de8a593e4e2bb706f528ad2a99c6968562dfe9377b8a6334e1cb0f4fba43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1875de8a593e4e2bb706f528ad2a99c6968562dfe9377b8a6334e1cb0f4fba43","first_computed_at":"2026-07-05T07:15:55.307668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:15:55.307668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jDy1aD/FnplN6pdyNcxHzw59LsvXa+10iscZYyh9hjKLPCxVi760L4YQMIPGp0zz9mxts4VGm72rd0x/A9qmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:15:55.308194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13455","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3342340e151000b8d04eee3d4a9c111cb41bde1bf80fc4df46db6591390eafd","sha256:7d12dbea5b1972872ee69bac3c7ab6169a6ff8bd90c379be1aea999b5ceb63a5"],"state_sha256":"3f33dd09f73e0f9f160696f832094d3e17a535459157f2fbdf031536dbc2602b"}