{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DB255CSZHZHCXNYG6UUK2KUZY2","short_pith_number":"pith:DB255CSZ","schema_version":"1.0","canonical_sha256":"1875de8a593e4e2bb706f528ad2a99c6968562dfe9377b8a6334e1cb0f4fba43","source":{"kind":"arxiv","id":"2305.13455","version":3},"attestation_state":"computed","paper":{"title":"Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brielen Madureira, David Schlangen, Jana G\\\"otze, Kranti Chalamalasetti, Philipp Sadler, Sherzod Hakimov","submitted_at":"2023-05-22T19:56:10Z","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"},"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":"2305.13455","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T19:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"db5e460a06649e09ff6d1f8f37d6d135ef88e8547f71ab3ff01e3e7d3e5eb144","abstract_canon_sha256":"dfc1121d4a3736b2a290ef6daadda0295399bc9ad08e638aa5e5a6ab9f840c53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:55.308194Z","signature_b64":"jDy1aD/FnplN6pdyNcxHzw59LsvXa+10iscZYyh9hjKLPCxVi760L4YQMIPGp0zz9mxts4VGm72rd0x/A9qmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1875de8a593e4e2bb706f528ad2a99c6968562dfe9377b8a6334e1cb0f4fba43","last_reissued_at":"2026-07-05T07:15:55.307668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:55.307668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brielen Madureira, David Schlangen, Jana G\\\"otze, Kranti Chalamalasetti, Philipp Sadler, Sherzod Hakimov","submitted_at":"2023-05-22T19:56:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13455","kind":"arxiv","version":3},"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/2305.13455/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":"2305.13455","created_at":"2026-07-05T07:15:55.307729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13455v3","created_at":"2026-07-05T07:15:55.307729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13455","created_at":"2026-07-05T07:15:55.307729+00:00"},{"alias_kind":"pith_short_12","alias_value":"DB255CSZHZHC","created_at":"2026-07-05T07:15:55.307729+00:00"},{"alias_kind":"pith_short_16","alias_value":"DB255CSZHZHCXNYG","created_at":"2026-07-05T07:15:55.307729+00:00"},{"alias_kind":"pith_short_8","alias_value":"DB255CSZ","created_at":"2026-07-05T07:15:55.307729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":165,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2","json":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2.json","graph_json":"https://pith.science/api/pith-number/DB255CSZHZHCXNYG6UUK2KUZY2/graph.json","events_json":"https://pith.science/api/pith-number/DB255CSZHZHCXNYG6UUK2KUZY2/events.json","paper":"https://pith.science/paper/DB255CSZ"},"agent_actions":{"view_html":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2","download_json":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2.json","view_paper":"https://pith.science/paper/DB255CSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13455&json=true","fetch_graph":"https://pith.science/api/pith-number/DB255CSZHZHCXNYG6UUK2KUZY2/graph.json","fetch_events":"https://pith.science/api/pith-number/DB255CSZHZHCXNYG6UUK2KUZY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2/action/storage_attestation","attest_author":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2/action/author_attestation","sign_citation":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2/action/citation_signature","submit_replication":"https://pith.science/pith/DB255CSZHZHCXNYG6UUK2KUZY2/action/replication_record"}},"created_at":"2026-07-05T07:15:55.307729+00:00","updated_at":"2026-07-05T07:15:55.307729+00:00"}