{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3YNXB6NUWSBC5UJLGFPLFDEYGL","short_pith_number":"pith:3YNXB6NU","schema_version":"1.0","canonical_sha256":"de1b70f9b4b4822ed12b315eb28c9832d2e5abb6d916c31db8566df68117e981","source":{"kind":"arxiv","id":"2505.24225","version":1},"attestation_state":"computed","paper":{"title":"Reasoning Can Hurt the Inductive Abilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haibo Jin, Haohan Wang, Man Luo, Peiyan Zhang","submitted_at":"2025-05-30T05:24:21Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable progress across domains, yet their ability to perform inductive reasoning - inferring latent rules from sparse examples - remains limited. It is often assumed that chain-of-thought (CoT) prompting, as used in Large Reasoning Models (LRMs), enhances such reasoning. We investigate this assumption with creating four controlled, diagnostic game-based tasks - chess, Texas Hold'em, dice games, and blackjack - with hidden human-defined rules. We find that CoT reasoning can degrade inductive performance, with LRMs often underperforming their non-reaso"},"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":"2505.24225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T05:24:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c214ef2526031ab5466b3455ba9866f43e0032749ede21bbc9642443dfc8ec6d","abstract_canon_sha256":"8ecf7bdcac7c78ed9be3ae3be509f661e4b50e3fd4d298cfb5c630ec19f07a4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:44.559582Z","signature_b64":"OHGhcWOhtXfMfAVjQgtEbirqJOBiP58syrEqyJ3j3kY24VMwxSk1rThX1Z63g9SFP0Xplqnl6PQAR4i7TzdZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de1b70f9b4b4822ed12b315eb28c9832d2e5abb6d916c31db8566df68117e981","last_reissued_at":"2026-07-05T11:12:44.559041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:44.559041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Can Hurt the Inductive Abilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haibo Jin, Haohan Wang, Man Luo, Peiyan Zhang","submitted_at":"2025-05-30T05:24:21Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable progress across domains, yet their ability to perform inductive reasoning - inferring latent rules from sparse examples - remains limited. It is often assumed that chain-of-thought (CoT) prompting, as used in Large Reasoning Models (LRMs), enhances such reasoning. We investigate this assumption with creating four controlled, diagnostic game-based tasks - chess, Texas Hold'em, dice games, and blackjack - with hidden human-defined rules. We find that CoT reasoning can degrade inductive performance, with LRMs often underperforming their non-reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24225","kind":"arxiv","version":1},"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/2505.24225/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":"2505.24225","created_at":"2026-07-05T11:12:44.559101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24225v1","created_at":"2026-07-05T11:12:44.559101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24225","created_at":"2026-07-05T11:12:44.559101+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YNXB6NUWSBC","created_at":"2026-07-05T11:12:44.559101+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YNXB6NUWSBC5UJL","created_at":"2026-07-05T11:12:44.559101+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YNXB6NU","created_at":"2026-07-05T11:12:44.559101+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/3YNXB6NUWSBC5UJLGFPLFDEYGL","json":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL.json","graph_json":"https://pith.science/api/pith-number/3YNXB6NUWSBC5UJLGFPLFDEYGL/graph.json","events_json":"https://pith.science/api/pith-number/3YNXB6NUWSBC5UJLGFPLFDEYGL/events.json","paper":"https://pith.science/paper/3YNXB6NU"},"agent_actions":{"view_html":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL","download_json":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL.json","view_paper":"https://pith.science/paper/3YNXB6NU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24225&json=true","fetch_graph":"https://pith.science/api/pith-number/3YNXB6NUWSBC5UJLGFPLFDEYGL/graph.json","fetch_events":"https://pith.science/api/pith-number/3YNXB6NUWSBC5UJLGFPLFDEYGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL/action/storage_attestation","attest_author":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL/action/author_attestation","sign_citation":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL/action/citation_signature","submit_replication":"https://pith.science/pith/3YNXB6NUWSBC5UJLGFPLFDEYGL/action/replication_record"}},"created_at":"2026-07-05T11:12:44.559101+00:00","updated_at":"2026-07-05T11:12:44.559101+00:00"}