{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C47ZYFPARR32UQNSKGZ3IHNFOJ","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":"43871112a84f9a43fdf0785af076041bc46eeb1106f59c35b380bba5beeeca7e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:10:32Z","title_canon_sha256":"9fd09e089493f3fd1d04edad63bf2461c5cf3a3a30360d00db9daa206f03ec08"},"schema_version":"1.0","source":{"id":"2406.11012","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11012","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11012v7","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11012","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"C47ZYFPARR32","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"C47ZYFPARR32UQNS","created_at":"2026-07-05T09:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"C47ZYFPA","created_at":"2026-07-05T09:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:93d685d9221e5159baed8b742ac4fcd4d7ac2cfc54058b208c42d47b0353ee33","target":"graph","created_at":"2026-07-05T09:19:59Z","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/2406.11012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The New York Times Connections game has emerged as a popular and challenging pursuit for word puzzle enthusiasts. We collect 438 Connections games to evaluate the performance of state-of-the-art large language models (LLMs) against expert and novice human players. Our results show that even the best performing LLM, Claude 3.5 Sonnet, which has otherwise shown impressive reasoning abilities on a wide variety of benchmarks, can only fully solve 18% of the games. Novice and expert players perform better than Claude 3.5 Sonnet, with expert human players significantly outperforming it. We create a ","authors_text":"Anushka Kulkarni, Mariam Mustafa, Prisha Samadarshi, Raven Rothkopf, Smaranda Muresan, Tuhin Chakrabarty","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:10:32Z","title":"Connecting the Dots: Evaluating Abstract Reasoning Capabilities of LLMs Using the New York Times Connections Word Game"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11012","kind":"arxiv","version":7},"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":"sha256:85e6f435fb8ea5cf6fbe026b9c9fda68730a2b4c5a229082492a4a56918c4ef5","target":"record","created_at":"2026-07-05T09:19:59Z","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":"43871112a84f9a43fdf0785af076041bc46eeb1106f59c35b380bba5beeeca7e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:10:32Z","title_canon_sha256":"9fd09e089493f3fd1d04edad63bf2461c5cf3a3a30360d00db9daa206f03ec08"},"schema_version":"1.0","source":{"id":"2406.11012","kind":"arxiv","version":7}},"canonical_sha256":"173f9c15e08c77aa41b251b3b41da5725bfd9476f87a1adf7c2c78366180290b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"173f9c15e08c77aa41b251b3b41da5725bfd9476f87a1adf7c2c78366180290b","first_computed_at":"2026-07-05T09:19:59.420791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:59.420791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ME9ofaMf9mK1jQagwTEecMcjOeWPWexTao+O4P/AoDjZOrOXd8oePx4gAfHcGC54qb2FKrm4vIUDO5To69BfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:59.421231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11012","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85e6f435fb8ea5cf6fbe026b9c9fda68730a2b4c5a229082492a4a56918c4ef5","sha256:93d685d9221e5159baed8b742ac4fcd4d7ac2cfc54058b208c42d47b0353ee33"],"state_sha256":"bf0b394f3b69a5e311239fd9eee2d5afe91620c1c4c574c69394652f2428a2cf"}