{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZAS3BS3GDTMNZ5ZXS6R5MEBPDL","short_pith_number":"pith:ZAS3BS3G","schema_version":"1.0","canonical_sha256":"c825b0cb661cd8dcf73797a3d6102f1ac6899c73f3fdfa805efb039924e42294","source":{"kind":"arxiv","id":"2310.08559","version":4},"attestation_state":"computed","paper":{"title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bailin Wang, Chandra Bhagavatula, Linlu Qiu, Liwei Jiang, Melanie Sclar, Nouha Dziri, Valentina Pyatkin, Xiang Ren, Ximing Lu, Yejin Choi, Yoon Kim","submitted_at":"2023-10-12T17:51:10Z","abstract_excerpt":"The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence. Prior work suggests that language models (LMs) often fall short on inductive reasoning, despite achieving impressive success on research benchmarks. In this work, we conduct a systematic study of the inductive reasoning capabilities of LMs through iterative hypothesis refinement, a technique that more closely mirrors the human inductive process than standard input-output prompting. Iterative hypothesis refinement"},"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":"2310.08559","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T17:51:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"385c9513dad506323bf4f2f02194124608fe722dfcce72a08bda3cd89964adf4","abstract_canon_sha256":"76d46be4c8afba9285feb51ab901a14aadad1d7005282057a35cd832bd5f7fe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:41.941372Z","signature_b64":"683ydPGsv6zcs2nWBLX9cWTT1cWDL8Wvt6ucABh+uwuQ4NEX1+885X0gEh7MWvo9n6in7zY8bEVCEo+7OOOsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c825b0cb661cd8dcf73797a3d6102f1ac6899c73f3fdfa805efb039924e42294","last_reissued_at":"2026-07-05T08:21:41.940917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:41.940917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bailin Wang, Chandra Bhagavatula, Linlu Qiu, Liwei Jiang, Melanie Sclar, Nouha Dziri, Valentina Pyatkin, Xiang Ren, Ximing Lu, Yejin Choi, Yoon Kim","submitted_at":"2023-10-12T17:51:10Z","abstract_excerpt":"The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence. Prior work suggests that language models (LMs) often fall short on inductive reasoning, despite achieving impressive success on research benchmarks. In this work, we conduct a systematic study of the inductive reasoning capabilities of LMs through iterative hypothesis refinement, a technique that more closely mirrors the human inductive process than standard input-output prompting. Iterative hypothesis refinement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08559","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/2310.08559/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":"2310.08559","created_at":"2026-07-05T08:21:41.940973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08559v4","created_at":"2026-07-05T08:21:41.940973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08559","created_at":"2026-07-05T08:21:41.940973+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAS3BS3GDTMN","created_at":"2026-07-05T08:21:41.940973+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAS3BS3GDTMNZ5ZX","created_at":"2026-07-05T08:21:41.940973+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAS3BS3G","created_at":"2026-07-05T08:21:41.940973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12412","citing_title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL","json":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL.json","graph_json":"https://pith.science/api/pith-number/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/graph.json","events_json":"https://pith.science/api/pith-number/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/events.json","paper":"https://pith.science/paper/ZAS3BS3G"},"agent_actions":{"view_html":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL","download_json":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL.json","view_paper":"https://pith.science/paper/ZAS3BS3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08559&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/action/storage_attestation","attest_author":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/action/author_attestation","sign_citation":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/action/citation_signature","submit_replication":"https://pith.science/pith/ZAS3BS3GDTMNZ5ZXS6R5MEBPDL/action/replication_record"}},"created_at":"2026-07-05T08:21:41.940973+00:00","updated_at":"2026-07-05T08:21:41.940973+00:00"}