{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4F2FWASCOQZUJWICTVSUG36LUC","short_pith_number":"pith:4F2FWASC","schema_version":"1.0","canonical_sha256":"e1745b0242743344d9029d65436fcba0b00905c2b131e3c4ba15dec9aedeadc2","source":{"kind":"arxiv","id":"2311.09682","version":4},"attestation_state":"computed","paper":{"title":"MacGyver: Are Large Language Models Creative Problem Solvers?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhilasha Ravichander, Faeze Brahman, Lianhui Qin, Nanyun Peng, Raja Marjieh, Ronan Le Bras, Thomas L. Griffiths, Yejin Choi, Yufei Tian","submitted_at":"2023-11-16T08:52:27Z","abstract_excerpt":"We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting. To this end, we create MACGYVER, an automatically generated dataset consisting of over 1,600 real-world problems deliberately designed to trigger innovative usage of objects and necessitate out-of-the-box thinking. We then present our collection to both LLMs and humans to compare and contrast their problem-solving abilities. MACGYVER is challenging for both groups, but in unique and complementary ways. For instance, humans excel in tasks they are familiar with but struggle with domain-specific k"},"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":"2311.09682","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T08:52:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70395720768a745ebabfff7277c71f3d6a848fad743ad7c42d5bb98002bf0443","abstract_canon_sha256":"85ca4c4ad6018e611e6bfaa057b932377c40f3b45ccc44beb5ade69e555d4233"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:33.682415Z","signature_b64":"8RC2LHsoWUcOEgGp2L94UCw+RXPUAGcN28vYk9p6PF15aF+XKJnoJUggmbw7J0oocypLbv1uDigH2noNnibKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1745b0242743344d9029d65436fcba0b00905c2b131e3c4ba15dec9aedeadc2","last_reissued_at":"2026-07-05T10:18:33.681912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:33.681912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MacGyver: Are Large Language Models Creative Problem Solvers?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhilasha Ravichander, Faeze Brahman, Lianhui Qin, Nanyun Peng, Raja Marjieh, Ronan Le Bras, Thomas L. Griffiths, Yejin Choi, Yufei Tian","submitted_at":"2023-11-16T08:52:27Z","abstract_excerpt":"We explore the creative problem-solving capabilities of modern LLMs in a novel constrained setting. To this end, we create MACGYVER, an automatically generated dataset consisting of over 1,600 real-world problems deliberately designed to trigger innovative usage of objects and necessitate out-of-the-box thinking. We then present our collection to both LLMs and humans to compare and contrast their problem-solving abilities. MACGYVER is challenging for both groups, but in unique and complementary ways. For instance, humans excel in tasks they are familiar with but struggle with domain-specific k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09682","kind":"arxiv","version":4},"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/2311.09682/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":"2311.09682","created_at":"2026-07-05T10:18:33.681971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09682v4","created_at":"2026-07-05T10:18:33.681971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09682","created_at":"2026-07-05T10:18:33.681971+00:00"},{"alias_kind":"pith_short_12","alias_value":"4F2FWASCOQZU","created_at":"2026-07-05T10:18:33.681971+00:00"},{"alias_kind":"pith_short_16","alias_value":"4F2FWASCOQZUJWIC","created_at":"2026-07-05T10:18:33.681971+00:00"},{"alias_kind":"pith_short_8","alias_value":"4F2FWASC","created_at":"2026-07-05T10:18:33.681971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC","json":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC.json","graph_json":"https://pith.science/api/pith-number/4F2FWASCOQZUJWICTVSUG36LUC/graph.json","events_json":"https://pith.science/api/pith-number/4F2FWASCOQZUJWICTVSUG36LUC/events.json","paper":"https://pith.science/paper/4F2FWASC"},"agent_actions":{"view_html":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC","download_json":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC.json","view_paper":"https://pith.science/paper/4F2FWASC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09682&json=true","fetch_graph":"https://pith.science/api/pith-number/4F2FWASCOQZUJWICTVSUG36LUC/graph.json","fetch_events":"https://pith.science/api/pith-number/4F2FWASCOQZUJWICTVSUG36LUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC/action/storage_attestation","attest_author":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC/action/author_attestation","sign_citation":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC/action/citation_signature","submit_replication":"https://pith.science/pith/4F2FWASCOQZUJWICTVSUG36LUC/action/replication_record"}},"created_at":"2026-07-05T10:18:33.681971+00:00","updated_at":"2026-07-05T10:18:33.681971+00:00"}