{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EEJP5UEXQ2ECLJTQDP34PYEYWB","short_pith_number":"pith:EEJP5UEX","schema_version":"1.0","canonical_sha256":"2112fed097868825a6701bf7c7e098b053d3fb2f3d07c73682ed5718cc55aa1a","source":{"kind":"arxiv","id":"2405.14075","version":2},"attestation_state":"computed","paper":{"title":"$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengkun Cai, Haoliang Liu, Lei Li, Xu Zhao, Yucheng Du","submitted_at":"2024-05-23T00:40:43Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, especially in complex decision-making scenarios, but their static problem-solving strategies often limit their adaptability to dynamic environments. We explore the enhancement of reasoning capabilities in LLMs through Temperature Tree ($T^2$) prompting via a heuristic algorithm, termed as $T^2$ of Thoughts ($T^2oT$). The primary focus is on enhancing decision-making processes by dynamically adjusting search parameters, especially temperature, to improve accuracy without increasing computational demands. We "},"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":"2405.14075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-23T00:40:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"130a0775b7b922aa5ef282852b6a69f9ea41aca7c7a674f7e06ede0d81068c7b","abstract_canon_sha256":"ca55aebf82261488bde247ebae5ead3ebf42743439bfb2b35999272c448713a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:40.588766Z","signature_b64":"yEhEUuFUTBYG7+cn8pGAse6YBOzYmKKpGIYt4drjUHMWg7yWj+HUlIEQ0CfpVI4+TtO5Ci8XE7OJBo3ZAcmAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2112fed097868825a6701bf7c7e098b053d3fb2f3d07c73682ed5718cc55aa1a","last_reissued_at":"2026-07-05T10:14:40.588251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:40.588251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$T^2$ of Thoughts: Temperature Tree Elicits Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengkun Cai, Haoliang Liu, Lei Li, Xu Zhao, Yucheng Du","submitted_at":"2024-05-23T00:40:43Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools in artificial intelligence, especially in complex decision-making scenarios, but their static problem-solving strategies often limit their adaptability to dynamic environments. We explore the enhancement of reasoning capabilities in LLMs through Temperature Tree ($T^2$) prompting via a heuristic algorithm, termed as $T^2$ of Thoughts ($T^2oT$). The primary focus is on enhancing decision-making processes by dynamically adjusting search parameters, especially temperature, to improve accuracy without increasing computational demands. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14075","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/2405.14075/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":"2405.14075","created_at":"2026-07-05T10:14:40.588310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14075v2","created_at":"2026-07-05T10:14:40.588310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14075","created_at":"2026-07-05T10:14:40.588310+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEJP5UEXQ2EC","created_at":"2026-07-05T10:14:40.588310+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEJP5UEXQ2ECLJTQ","created_at":"2026-07-05T10:14:40.588310+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEJP5UEX","created_at":"2026-07-05T10:14:40.588310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18089","citing_title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","ref_index":133,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB","json":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB.json","graph_json":"https://pith.science/api/pith-number/EEJP5UEXQ2ECLJTQDP34PYEYWB/graph.json","events_json":"https://pith.science/api/pith-number/EEJP5UEXQ2ECLJTQDP34PYEYWB/events.json","paper":"https://pith.science/paper/EEJP5UEX"},"agent_actions":{"view_html":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB","download_json":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB.json","view_paper":"https://pith.science/paper/EEJP5UEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14075&json=true","fetch_graph":"https://pith.science/api/pith-number/EEJP5UEXQ2ECLJTQDP34PYEYWB/graph.json","fetch_events":"https://pith.science/api/pith-number/EEJP5UEXQ2ECLJTQDP34PYEYWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB/action/storage_attestation","attest_author":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB/action/author_attestation","sign_citation":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB/action/citation_signature","submit_replication":"https://pith.science/pith/EEJP5UEXQ2ECLJTQDP34PYEYWB/action/replication_record"}},"created_at":"2026-07-05T10:14:40.588310+00:00","updated_at":"2026-07-05T10:14:40.588310+00:00"}