{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B63JKGFNKW5VHFBFTGHPX4FPSN","short_pith_number":"pith:B63JKGFN","schema_version":"1.0","canonical_sha256":"0fb69518ad55bb539425998efbf0af935db7591f261db0046eeca6731dbe7bbb","source":{"kind":"arxiv","id":"2308.16118","version":2},"attestation_state":"computed","paper":{"title":"Response: Emergent analogical reasoning in large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Damian Hodel, Jevin West","submitted_at":"2023-08-30T16:17:26Z","abstract_excerpt":"In their recent Nature Human Behaviour paper, \"Emergent analogical reasoning in large language models,\" (Webb, Holyoak, and Lu, 2023) the authors argue that \"large language models such as GPT-3 have acquired an emergent ability to find zero-shot solutions to a broad range of analogy problems.\" In this response, we provide counterexamples of the letter string analogies. In our tests, GPT-3 fails to solve simplest variations of the original tasks, whereas human performance remains consistently high across all modified versions. Zero-shot reasoning is an extraordinary claim that requires extraord"},"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":"2308.16118","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-30T16:17:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"26520d5683e2c273997fc69dfa11182f6dfa99fe6245fdf24126b58ee66d9a84","abstract_canon_sha256":"d52822bad5c924ccf0485c826c850294befa02b231e4f13e156a6e90f001e956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:00.841714Z","signature_b64":"+T2hfjQL5Qe3oFdvoBwARKO6NpyjiMjJMnSrjJwMMCh0ShOb6KNvH7/Amj8St6kN8SDTe19dp70gpRwBP8uRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fb69518ad55bb539425998efbf0af935db7591f261db0046eeca6731dbe7bbb","last_reissued_at":"2026-07-05T08:14:00.841071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:00.841071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Response: Emergent analogical reasoning in large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Damian Hodel, Jevin West","submitted_at":"2023-08-30T16:17:26Z","abstract_excerpt":"In their recent Nature Human Behaviour paper, \"Emergent analogical reasoning in large language models,\" (Webb, Holyoak, and Lu, 2023) the authors argue that \"large language models such as GPT-3 have acquired an emergent ability to find zero-shot solutions to a broad range of analogy problems.\" In this response, we provide counterexamples of the letter string analogies. In our tests, GPT-3 fails to solve simplest variations of the original tasks, whereas human performance remains consistently high across all modified versions. Zero-shot reasoning is an extraordinary claim that requires extraord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16118","kind":"arxiv","version":2},"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/2308.16118/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":"2308.16118","created_at":"2026-07-05T08:14:00.841219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16118v2","created_at":"2026-07-05T08:14:00.841219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16118","created_at":"2026-07-05T08:14:00.841219+00:00"},{"alias_kind":"pith_short_12","alias_value":"B63JKGFNKW5V","created_at":"2026-07-05T08:14:00.841219+00:00"},{"alias_kind":"pith_short_16","alias_value":"B63JKGFNKW5VHFBF","created_at":"2026-07-05T08:14:00.841219+00:00"},{"alias_kind":"pith_short_8","alias_value":"B63JKGFN","created_at":"2026-07-05T08:14:00.841219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01359","citing_title":"Structural Ranking of the Cognitive Plausibility of Computational Models of Analogy and Metaphors with the Minimal Cognitive Grid","ref_index":210,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN","json":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN.json","graph_json":"https://pith.science/api/pith-number/B63JKGFNKW5VHFBFTGHPX4FPSN/graph.json","events_json":"https://pith.science/api/pith-number/B63JKGFNKW5VHFBFTGHPX4FPSN/events.json","paper":"https://pith.science/paper/B63JKGFN"},"agent_actions":{"view_html":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN","download_json":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN.json","view_paper":"https://pith.science/paper/B63JKGFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16118&json=true","fetch_graph":"https://pith.science/api/pith-number/B63JKGFNKW5VHFBFTGHPX4FPSN/graph.json","fetch_events":"https://pith.science/api/pith-number/B63JKGFNKW5VHFBFTGHPX4FPSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN/action/storage_attestation","attest_author":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN/action/author_attestation","sign_citation":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN/action/citation_signature","submit_replication":"https://pith.science/pith/B63JKGFNKW5VHFBFTGHPX4FPSN/action/replication_record"}},"created_at":"2026-07-05T08:14:00.841219+00:00","updated_at":"2026-07-05T08:14:00.841219+00:00"}