{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S3RENPVURX3DUHBQLUPRBSWSBR","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":"eec40a67853f548f905fd297461abd562a27b839238d70384b9bccc1392c16ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T19:14:45Z","title_canon_sha256":"9d904512b4330f50ce8fd553cd8163220e4b739f168ce3f40ae3b17c56fff420"},"schema_version":"1.0","source":{"id":"2508.10142","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10142","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10142v3","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10142","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"pith_short_12","alias_value":"S3RENPVURX3D","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"pith_short_16","alias_value":"S3RENPVURX3DUHBQ","created_at":"2026-07-05T11:58:34Z"},{"alias_kind":"pith_short_8","alias_value":"S3RENPVU","created_at":"2026-07-05T11:58:34Z"}],"graph_snapshots":[{"event_id":"sha256:401f64b21eafc687a3e58c4d06302ca43424e51e29f0a342e2d0f9cca117dea7","target":"graph","created_at":"2026-07-05T11:58:34Z","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/2508.10142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T19:14:45Z","title":"Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10142","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":"sha256:1e02fd85d90d45929a30a3ba0c835de23d2927526c1b324baac34fc3f8c83b17","target":"record","created_at":"2026-07-05T11:58:34Z","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":"eec40a67853f548f905fd297461abd562a27b839238d70384b9bccc1392c16ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T19:14:45Z","title_canon_sha256":"9d904512b4330f50ce8fd553cd8163220e4b739f168ce3f40ae3b17c56fff420"},"schema_version":"1.0","source":{"id":"2508.10142","kind":"arxiv","version":3}},"canonical_sha256":"96e246beb48df63a1c305d1f10cad20c5d42efc4d83267357770651d36e12a0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96e246beb48df63a1c305d1f10cad20c5d42efc4d83267357770651d36e12a0b","first_computed_at":"2026-07-05T11:58:34.784838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:34.784838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kRTvcU/PJZArXgi6+r/sSk8pl0mnwAT/dDgt+TuPjKdCzSTB7NDXk28mcQJk7rHlFtu4GLXWTno7du/fDqRRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:34.785330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10142","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e02fd85d90d45929a30a3ba0c835de23d2927526c1b324baac34fc3f8c83b17","sha256:401f64b21eafc687a3e58c4d06302ca43424e51e29f0a342e2d0f9cca117dea7"],"state_sha256":"16e9587b74a96786bb0dd5157894762cbb5f01cef38afd98b0b47ddb16bf832f"}