{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XBAMEVFFWFM66RNVCFPE3DUWDT","short_pith_number":"pith:XBAMEVFF","schema_version":"1.0","canonical_sha256":"b840c254a5b159ef45b5115e4d8e961cde7ddac207ff0ce1d5719af9e8569837","source":{"kind":"arxiv","id":"2310.05057","version":3},"attestation_state":"computed","paper":{"title":"BRAINTEASER: Lateral Thinking Puzzles for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ilievski, Kaixin Ma, Yifan Jiang, Zhivar Sourati","submitted_at":"2023-10-08T07:46:01Z","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"},"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":"2310.05057","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-08T07:46:01Z","cross_cats_sorted":[],"title_canon_sha256":"93ba4150ebc20e06b91ca2cbf50c29e90b8a345f898fc608dc50c4700ea9040b","abstract_canon_sha256":"1441bd93385427740e899c963f12a0df7922190c134d1e249dcb4d3946ec8121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:18.808731Z","signature_b64":"GzwK4jlV9oLz6EMIrqjFJjk4qhrAJ9V7xp/6jKr6iRSVO0R0mMatQSj7gdFvPgKHOQ2Q80u3HYSUTbZhyIeKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b840c254a5b159ef45b5115e4d8e961cde7ddac207ff0ce1d5719af9e8569837","last_reissued_at":"2026-07-05T07:11:18.807439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:18.807439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BRAINTEASER: Lateral Thinking Puzzles for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ilievski, Kaixin Ma, Yifan Jiang, Zhivar Sourati","submitted_at":"2023-10-08T07:46:01Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05057","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/2310.05057/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":"2310.05057","created_at":"2026-07-05T07:11:18.807504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05057v3","created_at":"2026-07-05T07:11:18.807504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05057","created_at":"2026-07-05T07:11:18.807504+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBAMEVFFWFM6","created_at":"2026-07-05T07:11:18.807504+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBAMEVFFWFM66RNV","created_at":"2026-07-05T07:11:18.807504+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBAMEVFF","created_at":"2026-07-05T07:11:18.807504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23843","citing_title":"Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning Tasks","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT","json":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT.json","graph_json":"https://pith.science/api/pith-number/XBAMEVFFWFM66RNVCFPE3DUWDT/graph.json","events_json":"https://pith.science/api/pith-number/XBAMEVFFWFM66RNVCFPE3DUWDT/events.json","paper":"https://pith.science/paper/XBAMEVFF"},"agent_actions":{"view_html":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT","download_json":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT.json","view_paper":"https://pith.science/paper/XBAMEVFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05057&json=true","fetch_graph":"https://pith.science/api/pith-number/XBAMEVFFWFM66RNVCFPE3DUWDT/graph.json","fetch_events":"https://pith.science/api/pith-number/XBAMEVFFWFM66RNVCFPE3DUWDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT/action/storage_attestation","attest_author":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT/action/author_attestation","sign_citation":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT/action/citation_signature","submit_replication":"https://pith.science/pith/XBAMEVFFWFM66RNVCFPE3DUWDT/action/replication_record"}},"created_at":"2026-07-05T07:11:18.807504+00:00","updated_at":"2026-07-05T07:11:18.807504+00:00"}