{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WCNJNCLN4GQ6ADJZLVQESAXF35","short_pith_number":"pith:WCNJNCLN","schema_version":"1.0","canonical_sha256":"b09a96896de1a1e00d395d604902e5df508490c10b04335ce12e8b097aca5d49","source":{"kind":"arxiv","id":"2505.02665","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Zhou, Junsong Li, Junyi Wang, Liang He, Min Zhang, Qianjun Pan, Qin Chen, Shilian Chen, Wenkai Ji, Yulan Wu, Yuyang Ding","submitted_at":"2025-05-05T14:14:59Z","abstract_excerpt":"This survey explores recent advancements in reasoning large language models (LLMs) designed to mimic \"slow thinking\" - a reasoning process inspired by human cognition, as described in Kahneman's Thinking, Fast and Slow. These models, like OpenAI's o1, focus on scaling computational resources dynamically during complex tasks, such as math reasoning, visual reasoning, medical diagnosis, and multi-agent debates. We present the development of reasoning LLMs and list their key technologies. By synthesizing over 100 studies, it charts a path toward LLMs that combine human-like deep thinking with sca"},"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":"2505.02665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-05T14:14:59Z","cross_cats_sorted":[],"title_canon_sha256":"b087610a515f1730048c80dfdf4b757aa24ffbd42ae0abc821d8293b8bebfb76","abstract_canon_sha256":"33ed58885edafeb026c8ba984daf3744cbd131cda2589fab5d17b89c47fccab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:07.734340Z","signature_b64":"76CcvMPpa6wBDX3Pbbcu9FGRBd27Vk7wqsBdTEL8LqJSiI9RrWHYAPS0LOO3TIyCb58vANek/76vUsI9twO0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b09a96896de1a1e00d395d604902e5df508490c10b04335ce12e8b097aca5d49","last_reissued_at":"2026-07-05T11:00:07.733818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:07.733818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Zhou, Junsong Li, Junyi Wang, Liang He, Min Zhang, Qianjun Pan, Qin Chen, Shilian Chen, Wenkai Ji, Yulan Wu, Yuyang Ding","submitted_at":"2025-05-05T14:14:59Z","abstract_excerpt":"This survey explores recent advancements in reasoning large language models (LLMs) designed to mimic \"slow thinking\" - a reasoning process inspired by human cognition, as described in Kahneman's Thinking, Fast and Slow. These models, like OpenAI's o1, focus on scaling computational resources dynamically during complex tasks, such as math reasoning, visual reasoning, medical diagnosis, and multi-agent debates. We present the development of reasoning LLMs and list their key technologies. By synthesizing over 100 studies, it charts a path toward LLMs that combine human-like deep thinking with sca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02665","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/2505.02665/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":"2505.02665","created_at":"2026-07-05T11:00:07.733878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02665v2","created_at":"2026-07-05T11:00:07.733878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02665","created_at":"2026-07-05T11:00:07.733878+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCNJNCLN4GQ6","created_at":"2026-07-05T11:00:07.733878+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCNJNCLN4GQ6ADJZ","created_at":"2026-07-05T11:00:07.733878+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCNJNCLN","created_at":"2026-07-05T11:00:07.733878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08196","citing_title":"A First-Principles Theory of Slow Thinking and Active Perception","ref_index":122,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04402","citing_title":"Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04402","citing_title":"Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21260","citing_title":"On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35","json":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35.json","graph_json":"https://pith.science/api/pith-number/WCNJNCLN4GQ6ADJZLVQESAXF35/graph.json","events_json":"https://pith.science/api/pith-number/WCNJNCLN4GQ6ADJZLVQESAXF35/events.json","paper":"https://pith.science/paper/WCNJNCLN"},"agent_actions":{"view_html":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35","download_json":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35.json","view_paper":"https://pith.science/paper/WCNJNCLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02665&json=true","fetch_graph":"https://pith.science/api/pith-number/WCNJNCLN4GQ6ADJZLVQESAXF35/graph.json","fetch_events":"https://pith.science/api/pith-number/WCNJNCLN4GQ6ADJZLVQESAXF35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35/action/storage_attestation","attest_author":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35/action/author_attestation","sign_citation":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35/action/citation_signature","submit_replication":"https://pith.science/pith/WCNJNCLN4GQ6ADJZLVQESAXF35/action/replication_record"}},"created_at":"2026-07-05T11:00:07.733878+00:00","updated_at":"2026-07-05T11:00:07.733878+00:00"}