{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZWWTVVHBHUXYV526DDOGTICMQJ","short_pith_number":"pith:ZWWTVVHB","schema_version":"1.0","canonical_sha256":"cdad3ad4e13d2f8af75e18dc69a04c825fe35dbea43d0d1de3cf4a78f3b221c6","source":{"kind":"arxiv","id":"2407.01009","version":1},"attestation_state":"computed","paper":{"title":"DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Haizhou Li, Hongwei Wang, Jiabao Pan, Yan Zhang, Zuozhu Liu","submitted_at":"2024-07-01T06:45:13Z","abstract_excerpt":"Large language models (LLMs) have demonstrated emergent capabilities across diverse reasoning tasks via popular Chains-of-Thought (COT) prompting. However, such a simple and fast COT approach often encounters limitations in dealing with complicated problems, while a thorough method, which considers multiple reasoning pathways and verifies each step carefully, results in slower inference. This paper addresses the challenge of enabling LLMs to autonomously select between fast and slow inference methods, thereby optimizing both efficiency and effectiveness. We introduce a dynamic decision-making "},"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":"2407.01009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T06:45:13Z","cross_cats_sorted":[],"title_canon_sha256":"52c44ce4dc3e5425837ee8d5523eea7e3fbe290c8fcb6f6fd2a470e4f65d5435","abstract_canon_sha256":"e99f666b8a086f478c1624e40c739fc77d8c9d1a8dc21acd483aeb6bb5e92700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:41.517125Z","signature_b64":"rU8K2toG4aFWL1GbFzPQQ52bx75wP+s304FTjwn0xtvEFe6OpRtobC6Z4Nj7MnxlhU/Hp8kma4J+9OKPkP+ACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdad3ad4e13d2f8af75e18dc69a04c825fe35dbea43d0d1de3cf4a78f3b221c6","last_reissued_at":"2026-07-05T08:38:41.516693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:41.516693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Haizhou Li, Hongwei Wang, Jiabao Pan, Yan Zhang, Zuozhu Liu","submitted_at":"2024-07-01T06:45:13Z","abstract_excerpt":"Large language models (LLMs) have demonstrated emergent capabilities across diverse reasoning tasks via popular Chains-of-Thought (COT) prompting. However, such a simple and fast COT approach often encounters limitations in dealing with complicated problems, while a thorough method, which considers multiple reasoning pathways and verifies each step carefully, results in slower inference. This paper addresses the challenge of enabling LLMs to autonomously select between fast and slow inference methods, thereby optimizing both efficiency and effectiveness. We introduce a dynamic decision-making "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01009","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/2407.01009/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":"2407.01009","created_at":"2026-07-05T08:38:41.516752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01009v1","created_at":"2026-07-05T08:38:41.516752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01009","created_at":"2026-07-05T08:38:41.516752+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWWTVVHBHUXY","created_at":"2026-07-05T08:38:41.516752+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWWTVVHBHUXYV526","created_at":"2026-07-05T08:38:41.516752+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWWTVVHB","created_at":"2026-07-05T08:38:41.516752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.05605","citing_title":"ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ","json":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ.json","graph_json":"https://pith.science/api/pith-number/ZWWTVVHBHUXYV526DDOGTICMQJ/graph.json","events_json":"https://pith.science/api/pith-number/ZWWTVVHBHUXYV526DDOGTICMQJ/events.json","paper":"https://pith.science/paper/ZWWTVVHB"},"agent_actions":{"view_html":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ","download_json":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ.json","view_paper":"https://pith.science/paper/ZWWTVVHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01009&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWWTVVHBHUXYV526DDOGTICMQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWWTVVHBHUXYV526DDOGTICMQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZWWTVVHBHUXYV526DDOGTICMQJ/action/replication_record"}},"created_at":"2026-07-05T08:38:41.516752+00:00","updated_at":"2026-07-05T08:38:41.516752+00:00"}