{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X2GTUOMRB4V3XVLBZQ2WZIDJOD","short_pith_number":"pith:X2GTUOMR","schema_version":"1.0","canonical_sha256":"be8d3a39910f2bbbd561cc356ca06970cc033010c99c3fe70d4b464ee63e9395","source":{"kind":"arxiv","id":"2412.09078","version":5},"attestation_state":"computed","paper":{"title":"Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanjian Liu, Kai Han, Yehui Tang, Yunhe Wang, Zhenni Bi","submitted_at":"2024-12-12T09:01:18Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable abilities across various language tasks, but solving complex reasoning problems remains a significant challenge. While existing methods, such as Chain-of-Thought (CoT) and Tree-of-Thought (ToT), enhance reasoning by decomposing problems or structuring prompts, they typically perform a single pass of reasoning and may fail to revisit flawed paths, compromising accuracy. To address this limitation, we propose a novel reasoning framework called Forest-of-Thought (FoT), which integrates multiple reasoning trees to leverage collective decisi"},"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":"2412.09078","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T09:01:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a329de9e06605f41117a357fa7aee648c0d60db04e22547b5b8aa12fb55891f","abstract_canon_sha256":"9fb6f767ad37f5089aedea9413f40372bbf6b4a6b90081fdc9303c40ca2f5291"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:40.223632Z","signature_b64":"O9BLnlT4rLmqYuWc2UYx3tpAuG7wgioaFd8DCe8abLMuhluRE2YOCyIfV4ffjA+IzyyNzeyNS9hXZftYoqz3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be8d3a39910f2bbbd561cc356ca06970cc033010c99c3fe70d4b464ee63e9395","last_reissued_at":"2026-07-05T10:42:40.223140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:40.223140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanjian Liu, Kai Han, Yehui Tang, Yunhe Wang, Zhenni Bi","submitted_at":"2024-12-12T09:01:18Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable abilities across various language tasks, but solving complex reasoning problems remains a significant challenge. While existing methods, such as Chain-of-Thought (CoT) and Tree-of-Thought (ToT), enhance reasoning by decomposing problems or structuring prompts, they typically perform a single pass of reasoning and may fail to revisit flawed paths, compromising accuracy. To address this limitation, we propose a novel reasoning framework called Forest-of-Thought (FoT), which integrates multiple reasoning trees to leverage collective decisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09078","kind":"arxiv","version":5},"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/2412.09078/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":"2412.09078","created_at":"2026-07-05T10:42:40.223201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09078v5","created_at":"2026-07-05T10:42:40.223201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09078","created_at":"2026-07-05T10:42:40.223201+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2GTUOMRB4V3","created_at":"2026-07-05T10:42:40.223201+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2GTUOMRB4V3XVLB","created_at":"2026-07-05T10:42:40.223201+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2GTUOMR","created_at":"2026-07-05T10:42:40.223201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22385","citing_title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12402","citing_title":"DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03608","citing_title":"Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10403","citing_title":"KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13332","citing_title":"Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25454","citing_title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08592","citing_title":"Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04942","citing_title":"TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":168,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26644","citing_title":"When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07353","citing_title":"Confidence-Aware Alignment Makes Reasoning LLMs More Reliable","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17353","citing_title":"Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD","json":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD.json","graph_json":"https://pith.science/api/pith-number/X2GTUOMRB4V3XVLBZQ2WZIDJOD/graph.json","events_json":"https://pith.science/api/pith-number/X2GTUOMRB4V3XVLBZQ2WZIDJOD/events.json","paper":"https://pith.science/paper/X2GTUOMR"},"agent_actions":{"view_html":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD","download_json":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD.json","view_paper":"https://pith.science/paper/X2GTUOMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09078&json=true","fetch_graph":"https://pith.science/api/pith-number/X2GTUOMRB4V3XVLBZQ2WZIDJOD/graph.json","fetch_events":"https://pith.science/api/pith-number/X2GTUOMRB4V3XVLBZQ2WZIDJOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD/action/storage_attestation","attest_author":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD/action/author_attestation","sign_citation":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD/action/citation_signature","submit_replication":"https://pith.science/pith/X2GTUOMRB4V3XVLBZQ2WZIDJOD/action/replication_record"}},"created_at":"2026-07-05T10:42:40.223201+00:00","updated_at":"2026-07-05T10:42:40.223201+00:00"}