{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QLDZW3NNJFSWVAXYLAGUA6QKQ5","short_pith_number":"pith:QLDZW3NN","schema_version":"1.0","canonical_sha256":"82c79b6dad49656a82f8580d407a0a876ce53cd57a12156284faea5ca638e398","source":{"kind":"arxiv","id":"2408.00114","version":2},"attestation_state":"computed","paper":{"title":"Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bing Yin, Binxuan Huang, Haoming Jiang, Jingfeng Yang, Kewei Cheng, Ruirui Li, Shiyang Li, Xian Li, Yifan Gao, Yizhou Sun, Zheng Li, Zhengyang Wang","submitted_at":"2024-07-31T18:47:11Z","abstract_excerpt":"Reasoning encompasses two typical types: deductive reasoning and inductive reasoning. Despite extensive research into the reasoning capabilities of Large Language Models (LLMs), most studies have failed to rigorously differentiate between inductive and deductive reasoning, leading to a blending of the two. This raises an essential question: In LLM reasoning, which poses a greater challenge - deductive or inductive reasoning? While the deductive reasoning capabilities of LLMs, (i.e. their capacity to follow instructions in reasoning tasks), have received considerable attention, their abilities "},"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":"2408.00114","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-31T18:47:11Z","cross_cats_sorted":[],"title_canon_sha256":"0f9b5a169de68ef382af4e4e1168e944997b19ab656dce708ece8712b17fd21f","abstract_canon_sha256":"a524b1eedb667e39fc50041e343f86c31151c1e343a51f2155f65c1e09463fb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:56.078905Z","signature_b64":"WoFFGJ+nBm/CYXmPS7nrvy8PllUu5LofCxfICCzDo3+mYqle3gIytTdD70wX++gC4NhwX3r7O2ydkLg94Sc+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82c79b6dad49656a82f8580d407a0a876ce53cd57a12156284faea5ca638e398","last_reissued_at":"2026-07-05T08:52:56.078474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:56.078474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bing Yin, Binxuan Huang, Haoming Jiang, Jingfeng Yang, Kewei Cheng, Ruirui Li, Shiyang Li, Xian Li, Yifan Gao, Yizhou Sun, Zheng Li, Zhengyang Wang","submitted_at":"2024-07-31T18:47:11Z","abstract_excerpt":"Reasoning encompasses two typical types: deductive reasoning and inductive reasoning. Despite extensive research into the reasoning capabilities of Large Language Models (LLMs), most studies have failed to rigorously differentiate between inductive and deductive reasoning, leading to a blending of the two. This raises an essential question: In LLM reasoning, which poses a greater challenge - deductive or inductive reasoning? While the deductive reasoning capabilities of LLMs, (i.e. their capacity to follow instructions in reasoning tasks), have received considerable attention, their abilities "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00114","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/2408.00114/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":"2408.00114","created_at":"2026-07-05T08:52:56.078530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00114v2","created_at":"2026-07-05T08:52:56.078530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00114","created_at":"2026-07-05T08:52:56.078530+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLDZW3NNJFSW","created_at":"2026-07-05T08:52:56.078530+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLDZW3NNJFSWVAXY","created_at":"2026-07-05T08:52:56.078530+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLDZW3NN","created_at":"2026-07-05T08:52:56.078530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08028","citing_title":"Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02378","citing_title":"Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5","json":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5.json","graph_json":"https://pith.science/api/pith-number/QLDZW3NNJFSWVAXYLAGUA6QKQ5/graph.json","events_json":"https://pith.science/api/pith-number/QLDZW3NNJFSWVAXYLAGUA6QKQ5/events.json","paper":"https://pith.science/paper/QLDZW3NN"},"agent_actions":{"view_html":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5","download_json":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5.json","view_paper":"https://pith.science/paper/QLDZW3NN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00114&json=true","fetch_graph":"https://pith.science/api/pith-number/QLDZW3NNJFSWVAXYLAGUA6QKQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/QLDZW3NNJFSWVAXYLAGUA6QKQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5/action/storage_attestation","attest_author":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5/action/author_attestation","sign_citation":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5/action/citation_signature","submit_replication":"https://pith.science/pith/QLDZW3NNJFSWVAXYLAGUA6QKQ5/action/replication_record"}},"created_at":"2026-07-05T08:52:56.078530+00:00","updated_at":"2026-07-05T08:52:56.078530+00:00"}