{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GP3ME7KHLJ6D4BFL6OEBNIANCD","short_pith_number":"pith:GP3ME7KH","schema_version":"1.0","canonical_sha256":"33f6c27d475a7c3e04abf38816a00d10d96053ff0b6d0b27ed881de0d69453cf","source":{"kind":"arxiv","id":"2506.05936","version":1},"attestation_state":"computed","paper":{"title":"DynamicMind: A Tri-Mode Thinking System for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"James T. Kwok, Jiangyue Yan, Qiushi Huang, Wei Li, Yanbin Wei, Yang Chen, Yu Zhang","submitted_at":"2025-06-06T10:02:13Z","abstract_excerpt":"Modern large language models (LLMs) often struggle to dynamically adapt their reasoning depth to varying task complexities, leading to suboptimal performance or inefficient resource utilization. To address this, we introduce DynamicMind, a novel tri-mode thinking system. DynamicMind empowers LLMs to autonomously select between Fast, Normal, and Slow thinking modes for zero-shot question answering (ZSQA) tasks through cognitive-inspired prompt engineering. Our framework's core innovations include: (1) expanding the established dual-process framework of fast and slow thinking into a tri-mode thi"},"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":"2506.05936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T10:02:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d682ad2d7e0c723a0d5fba0a04c51a3946018cbd07aab3e1f9947dd3b7226d6c","abstract_canon_sha256":"c02b2fe871a6098c3186c0a76008020f88500687c2ed0be36e7019547eaf356b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:13.361918Z","signature_b64":"9anXWarpRHy9zwWCrd98AT6S1y6pNXTFeNmS5obSg3pV/SJubr13Vm6faIgOCtyzrK44GrHOgAIYFV+zp0mvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33f6c27d475a7c3e04abf38816a00d10d96053ff0b6d0b27ed881de0d69453cf","last_reissued_at":"2026-07-05T11:17:13.361436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:13.361436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynamicMind: A Tri-Mode Thinking System for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"James T. Kwok, Jiangyue Yan, Qiushi Huang, Wei Li, Yanbin Wei, Yang Chen, Yu Zhang","submitted_at":"2025-06-06T10:02:13Z","abstract_excerpt":"Modern large language models (LLMs) often struggle to dynamically adapt their reasoning depth to varying task complexities, leading to suboptimal performance or inefficient resource utilization. To address this, we introduce DynamicMind, a novel tri-mode thinking system. DynamicMind empowers LLMs to autonomously select between Fast, Normal, and Slow thinking modes for zero-shot question answering (ZSQA) tasks through cognitive-inspired prompt engineering. Our framework's core innovations include: (1) expanding the established dual-process framework of fast and slow thinking into a tri-mode thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05936","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/2506.05936/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":"2506.05936","created_at":"2026-07-05T11:17:13.361490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05936v1","created_at":"2026-07-05T11:17:13.361490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05936","created_at":"2026-07-05T11:17:13.361490+00:00"},{"alias_kind":"pith_short_12","alias_value":"GP3ME7KHLJ6D","created_at":"2026-07-05T11:17:13.361490+00:00"},{"alias_kind":"pith_short_16","alias_value":"GP3ME7KHLJ6D4BFL","created_at":"2026-07-05T11:17:13.361490+00:00"},{"alias_kind":"pith_short_8","alias_value":"GP3ME7KH","created_at":"2026-07-05T11:17:13.361490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.13332","citing_title":"Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD","json":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD.json","graph_json":"https://pith.science/api/pith-number/GP3ME7KHLJ6D4BFL6OEBNIANCD/graph.json","events_json":"https://pith.science/api/pith-number/GP3ME7KHLJ6D4BFL6OEBNIANCD/events.json","paper":"https://pith.science/paper/GP3ME7KH"},"agent_actions":{"view_html":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD","download_json":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD.json","view_paper":"https://pith.science/paper/GP3ME7KH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05936&json=true","fetch_graph":"https://pith.science/api/pith-number/GP3ME7KHLJ6D4BFL6OEBNIANCD/graph.json","fetch_events":"https://pith.science/api/pith-number/GP3ME7KHLJ6D4BFL6OEBNIANCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD/action/storage_attestation","attest_author":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD/action/author_attestation","sign_citation":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD/action/citation_signature","submit_replication":"https://pith.science/pith/GP3ME7KHLJ6D4BFL6OEBNIANCD/action/replication_record"}},"created_at":"2026-07-05T11:17:13.361490+00:00","updated_at":"2026-07-05T11:17:13.361490+00:00"}