{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SG3ZEW4WWFDV6EXGRTFFO6O2NG","short_pith_number":"pith:SG3ZEW4W","schema_version":"1.0","canonical_sha256":"91b7925b96b1475f12e68cca5779da698d0b4719fb08fe1cd52fdb69bc40fafb","source":{"kind":"arxiv","id":"2404.05221","version":2},"attestation_state":"computed","paper":{"title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adithya Samavedhi, Haodi Ma, Haotian Luo, Qiyue Gao, Shibo Hao, Shuhua Xie, Tianyang Liu, Xinyuan Wang, Xiyan Shao, Yi Gu, Zhen Wang, Zhiting Hu","submitted_at":"2024-04-08T06:35:09Z","abstract_excerpt":"Generating accurate step-by-step reasoning is essential for Large Language Models (LLMs) to address complex problems and enhance robustness and interpretability. Despite the flux of research on developing advanced reasoning approaches, systematically analyzing the diverse LLMs and reasoning strategies in generating reasoning chains remains a significant challenge. The difficulties stem from the lack of two key elements: (1) an automatic method for evaluating the generated reasoning chains on different tasks, and (2) a unified formalism and implementation of the diverse reasoning approaches for"},"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":"2404.05221","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T06:35:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0397b0ddcf10e5936014a6756e10783fb6e5bd1756f698cf19902ab1cc79d8c4","abstract_canon_sha256":"46705b07f6b57a3692b18b9c67e334d7ffcd7df22a84916dc383cf666c7241d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:09.854415Z","signature_b64":"kvfA0k3c9cZlVzrWPtTgPVlcR+vWjIrPpZ0Fv4vmuvet9ctoT51G9MOMcPQ31+64aI7uxlf/T0pSNquEoVOlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91b7925b96b1475f12e68cca5779da698d0b4719fb08fe1cd52fdb69bc40fafb","last_reissued_at":"2026-07-05T08:54:09.853834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:09.853834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adithya Samavedhi, Haodi Ma, Haotian Luo, Qiyue Gao, Shibo Hao, Shuhua Xie, Tianyang Liu, Xinyuan Wang, Xiyan Shao, Yi Gu, Zhen Wang, Zhiting Hu","submitted_at":"2024-04-08T06:35:09Z","abstract_excerpt":"Generating accurate step-by-step reasoning is essential for Large Language Models (LLMs) to address complex problems and enhance robustness and interpretability. Despite the flux of research on developing advanced reasoning approaches, systematically analyzing the diverse LLMs and reasoning strategies in generating reasoning chains remains a significant challenge. The difficulties stem from the lack of two key elements: (1) an automatic method for evaluating the generated reasoning chains on different tasks, and (2) a unified formalism and implementation of the diverse reasoning approaches for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05221","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/2404.05221/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":"2404.05221","created_at":"2026-07-05T08:54:09.853893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05221v2","created_at":"2026-07-05T08:54:09.853893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05221","created_at":"2026-07-05T08:54:09.853893+00:00"},{"alias_kind":"pith_short_12","alias_value":"SG3ZEW4WWFDV","created_at":"2026-07-05T08:54:09.853893+00:00"},{"alias_kind":"pith_short_16","alias_value":"SG3ZEW4WWFDV6EXG","created_at":"2026-07-05T08:54:09.853893+00:00"},{"alias_kind":"pith_short_8","alias_value":"SG3ZEW4W","created_at":"2026-07-05T08:54:09.853893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10279","citing_title":"Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31010","citing_title":"MoG: Mixture of Experts for Graph-based Retrieval-Augmented Generation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27397","citing_title":"SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Game","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23773","citing_title":"General Agentic Planning Through Simulative Reasoning with World Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03540","citing_title":"Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04476","citing_title":"Vision-aligned Latent Reasoning for Multi-modal Large Language Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06769","citing_title":"Training Large Language Models to Reason in a Continuous Latent Space","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG","json":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG.json","graph_json":"https://pith.science/api/pith-number/SG3ZEW4WWFDV6EXGRTFFO6O2NG/graph.json","events_json":"https://pith.science/api/pith-number/SG3ZEW4WWFDV6EXGRTFFO6O2NG/events.json","paper":"https://pith.science/paper/SG3ZEW4W"},"agent_actions":{"view_html":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG","download_json":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG.json","view_paper":"https://pith.science/paper/SG3ZEW4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05221&json=true","fetch_graph":"https://pith.science/api/pith-number/SG3ZEW4WWFDV6EXGRTFFO6O2NG/graph.json","fetch_events":"https://pith.science/api/pith-number/SG3ZEW4WWFDV6EXGRTFFO6O2NG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG/action/storage_attestation","attest_author":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG/action/author_attestation","sign_citation":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG/action/citation_signature","submit_replication":"https://pith.science/pith/SG3ZEW4WWFDV6EXGRTFFO6O2NG/action/replication_record"}},"created_at":"2026-07-05T08:54:09.853893+00:00","updated_at":"2026-07-05T08:54:09.853893+00:00"}