{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S3RENPVURX3DUHBQLUPRBSWSBR","short_pith_number":"pith:S3RENPVU","schema_version":"1.0","canonical_sha256":"96e246beb48df63a1c305d1f10cad20c5d42efc4d83267357770651d36e12a0b","source":{"kind":"arxiv","id":"2508.10142","version":3},"attestation_state":"computed","paper":{"title":"Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhimanyu Goyal, Arian Hosseini, Bahare Fatemi, Jonathan Simon, Kartikeya Badola, Mehran Kazemi, Sara Marie Mc Carthy, Shyam Upadhyay, Tom\\'a\\v{s} Ko\\v{c}isk\\'y, Tsendsuren Munkhdalai","submitted_at":"2025-08-13T19:14:45Z","abstract_excerpt":"Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in most real-world scenarios. This highlights the critical need for developing LLMs that can effectively engage in logically consistent multi-turn dialogue, seek information and reason with incomplete data. To this end, we introduce a novel benchmark comprising a suite of multi-turn tasks each designed to test specific reasoning, interactive dialogue, and information-seeking abilities. These tasks have deterministic scorin"},"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":"2508.10142","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T19:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"9d904512b4330f50ce8fd553cd8163220e4b739f168ce3f40ae3b17c56fff420","abstract_canon_sha256":"eec40a67853f548f905fd297461abd562a27b839238d70384b9bccc1392c16ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:34.785330Z","signature_b64":"kRTvcU/PJZArXgi6+r/sSk8pl0mnwAT/dDgt+TuPjKdCzSTB7NDXk28mcQJk7rHlFtu4GLXWTno7du/fDqRRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96e246beb48df63a1c305d1f10cad20c5d42efc4d83267357770651d36e12a0b","last_reissued_at":"2026-07-05T11:58:34.784838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:34.784838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhimanyu Goyal, Arian Hosseini, Bahare Fatemi, Jonathan Simon, Kartikeya Badola, Mehran Kazemi, Sara Marie Mc Carthy, Shyam Upadhyay, Tom\\'a\\v{s} Ko\\v{c}isk\\'y, Tsendsuren Munkhdalai","submitted_at":"2025-08-13T19:14:45Z","abstract_excerpt":"Large language models (LLMs) excel at solving problems with clear and complete statements, but often struggle with nuanced environments or interactive tasks which are common in most real-world scenarios. This highlights the critical need for developing LLMs that can effectively engage in logically consistent multi-turn dialogue, seek information and reason with incomplete data. To this end, we introduce a novel benchmark comprising a suite of multi-turn tasks each designed to test specific reasoning, interactive dialogue, and information-seeking abilities. These tasks have deterministic scorin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10142","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/2508.10142/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":"2508.10142","created_at":"2026-07-05T11:58:34.784901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10142v3","created_at":"2026-07-05T11:58:34.784901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10142","created_at":"2026-07-05T11:58:34.784901+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3RENPVURX3D","created_at":"2026-07-05T11:58:34.784901+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3RENPVURX3DUHBQ","created_at":"2026-07-05T11:58:34.784901+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3RENPVU","created_at":"2026-07-05T11:58:34.784901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19476","citing_title":"Can In-Context Learning Support Intrinsic Curiosity?","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00103","citing_title":"Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR","json":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR.json","graph_json":"https://pith.science/api/pith-number/S3RENPVURX3DUHBQLUPRBSWSBR/graph.json","events_json":"https://pith.science/api/pith-number/S3RENPVURX3DUHBQLUPRBSWSBR/events.json","paper":"https://pith.science/paper/S3RENPVU"},"agent_actions":{"view_html":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR","download_json":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR.json","view_paper":"https://pith.science/paper/S3RENPVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10142&json=true","fetch_graph":"https://pith.science/api/pith-number/S3RENPVURX3DUHBQLUPRBSWSBR/graph.json","fetch_events":"https://pith.science/api/pith-number/S3RENPVURX3DUHBQLUPRBSWSBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR/action/storage_attestation","attest_author":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR/action/author_attestation","sign_citation":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR/action/citation_signature","submit_replication":"https://pith.science/pith/S3RENPVURX3DUHBQLUPRBSWSBR/action/replication_record"}},"created_at":"2026-07-05T11:58:34.784901+00:00","updated_at":"2026-07-05T11:58:34.784901+00:00"}