{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XBAMEVFFWFM66RNVCFPE3DUWDT","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":"1441bd93385427740e899c963f12a0df7922190c134d1e249dcb4d3946ec8121","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T07:46:01Z","title_canon_sha256":"93ba4150ebc20e06b91ca2cbf50c29e90b8a345f898fc608dc50c4700ea9040b"},"schema_version":"1.0","source":{"id":"2310.05057","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05057","created_at":"2026-07-05T07:11:18Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05057v3","created_at":"2026-07-05T07:11:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05057","created_at":"2026-07-05T07:11:18Z"},{"alias_kind":"pith_short_12","alias_value":"XBAMEVFFWFM6","created_at":"2026-07-05T07:11:18Z"},{"alias_kind":"pith_short_16","alias_value":"XBAMEVFFWFM66RNV","created_at":"2026-07-05T07:11:18Z"},{"alias_kind":"pith_short_8","alias_value":"XBAMEVFF","created_at":"2026-07-05T07:11:18Z"}],"graph_snapshots":[{"event_id":"sha256:5504df1cceed08f070ab8aa6ba95744132cd7ce352c44a981d8e48018f6c49ce","target":"graph","created_at":"2026-07-05T07:11:18Z","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/2310.05057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of language models has inspired the NLP community to attend to tasks that require implicit and complex reasoning, relying on human-like commonsense mechanisms. While such vertical thinking tasks have been relatively popular, lateral thinking puzzles have received little attention. To bridge this gap, we devise BRAINTEASER: a multiple-choice Question Answering task designed to test the model's ability to exhibit lateral thinking and defy default commonsense associations. We design a three-step procedure for creating the first lateral thinking benchmark, consisting of data collection","authors_text":"Filip Ilievski, Kaixin Ma, Yifan Jiang, Zhivar Sourati","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T07:46:01Z","title":"BRAINTEASER: Lateral Thinking Puzzles for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05057","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:f76294fcf66afcbbbece014326b9af8d71026b311df5e60ff847d8add0ceee0f","target":"record","created_at":"2026-07-05T07:11:18Z","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":"1441bd93385427740e899c963f12a0df7922190c134d1e249dcb4d3946ec8121","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T07:46:01Z","title_canon_sha256":"93ba4150ebc20e06b91ca2cbf50c29e90b8a345f898fc608dc50c4700ea9040b"},"schema_version":"1.0","source":{"id":"2310.05057","kind":"arxiv","version":3}},"canonical_sha256":"b840c254a5b159ef45b5115e4d8e961cde7ddac207ff0ce1d5719af9e8569837","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b840c254a5b159ef45b5115e4d8e961cde7ddac207ff0ce1d5719af9e8569837","first_computed_at":"2026-07-05T07:11:18.807439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:18.807439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GzwK4jlV9oLz6EMIrqjFJjk4qhrAJ9V7xp/6jKr6iRSVO0R0mMatQSj7gdFvPgKHOQ2Q80u3HYSUTbZhyIeKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:18.808731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05057","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f76294fcf66afcbbbece014326b9af8d71026b311df5e60ff847d8add0ceee0f","sha256:5504df1cceed08f070ab8aa6ba95744132cd7ce352c44a981d8e48018f6c49ce"],"state_sha256":"ba67a3f4a9381c6733f6b9c0cbff6c1976ff42902cf7c5b23d68ff021f0c00cc"}