{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WIWIYJTQEGJ4NF2ANEUCO22OXF","short_pith_number":"pith:WIWIYJTQ","schema_version":"1.0","canonical_sha256":"b22c8c26702193c697406928276b4eb9634ab736997daa1418887a6768ff4f4e","source":{"kind":"arxiv","id":"2406.12255","version":1},"attestation_state":"computed","paper":{"title":"A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Di Wang, Hongru Xiao, Liang Liu, Lijie Hu, Mengdi Li, Muhammad Asif Ali, Pan Zhou, Shu Yang, Xin Chen","submitted_at":"2024-06-18T04:07:13Z","abstract_excerpt":"Chain-of-Thought (CoT) holds a significant place in augmenting the reasoning performance for large language models (LLMs). While some studies focus on improving CoT accuracy through methods like retrieval enhancement, yet a rigorous explanation for why CoT achieves such success remains unclear. In this paper, we analyze CoT methods under two different settings by asking the following questions: (1) For zero-shot CoT, why does prompting the model with \"let's think step by step\" significantly impact its outputs? (2) For few-shot CoT, why does providing examples before questioning the model could"},"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":"2406.12255","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T04:07:13Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"67fce3dbaa2ad39a3fd3b0f804bf038e9284ad5a6aa5fd435fdf894d460ffa84","abstract_canon_sha256":"7fecb88d77a486079976622fdbb08c0eb813ccdfde010e28a79d3309c453dc31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:43.428881Z","signature_b64":"mEfYWSBX51O0cUxI9ZsXRjyVeL4hPlTh8NuFVL/lh3cIPyxT9xO+cdwZ16vKor5rCIk8XsqyNH6tR7WxGo1ADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b22c8c26702193c697406928276b4eb9634ab736997daa1418887a6768ff4f4e","last_reissued_at":"2026-07-05T08:33:43.428434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:43.428434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Di Wang, Hongru Xiao, Liang Liu, Lijie Hu, Mengdi Li, Muhammad Asif Ali, Pan Zhou, Shu Yang, Xin Chen","submitted_at":"2024-06-18T04:07:13Z","abstract_excerpt":"Chain-of-Thought (CoT) holds a significant place in augmenting the reasoning performance for large language models (LLMs). While some studies focus on improving CoT accuracy through methods like retrieval enhancement, yet a rigorous explanation for why CoT achieves such success remains unclear. In this paper, we analyze CoT methods under two different settings by asking the following questions: (1) For zero-shot CoT, why does prompting the model with \"let's think step by step\" significantly impact its outputs? (2) For few-shot CoT, why does providing examples before questioning the model could"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12255","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/2406.12255/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":"2406.12255","created_at":"2026-07-05T08:33:43.428491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12255v1","created_at":"2026-07-05T08:33:43.428491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12255","created_at":"2026-07-05T08:33:43.428491+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIWIYJTQEGJ4","created_at":"2026-07-05T08:33:43.428491+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIWIYJTQEGJ4NF2A","created_at":"2026-07-05T08:33:43.428491+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIWIYJTQ","created_at":"2026-07-05T08:33:43.428491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05286","citing_title":"Stable Vision Concept Transformers for Medical Diagnosis","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF","json":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF.json","graph_json":"https://pith.science/api/pith-number/WIWIYJTQEGJ4NF2ANEUCO22OXF/graph.json","events_json":"https://pith.science/api/pith-number/WIWIYJTQEGJ4NF2ANEUCO22OXF/events.json","paper":"https://pith.science/paper/WIWIYJTQ"},"agent_actions":{"view_html":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF","download_json":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF.json","view_paper":"https://pith.science/paper/WIWIYJTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12255&json=true","fetch_graph":"https://pith.science/api/pith-number/WIWIYJTQEGJ4NF2ANEUCO22OXF/graph.json","fetch_events":"https://pith.science/api/pith-number/WIWIYJTQEGJ4NF2ANEUCO22OXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF/action/storage_attestation","attest_author":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF/action/author_attestation","sign_citation":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF/action/citation_signature","submit_replication":"https://pith.science/pith/WIWIYJTQEGJ4NF2ANEUCO22OXF/action/replication_record"}},"created_at":"2026-07-05T08:33:43.428491+00:00","updated_at":"2026-07-05T08:33:43.428491+00:00"}