{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LRSSYNEFP5FCIZGH7T56V3VQSP","short_pith_number":"pith:LRSSYNEF","schema_version":"1.0","canonical_sha256":"5c652c34857f4a2464c7fcfbeaeeb093e16fbbd633b28fef8dc5e7290da0f3bf","source":{"kind":"arxiv","id":"2509.02350","version":1},"attestation_state":"computed","paper":{"title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengwei Qin, Irwin King, Jiahong Liu, Jindong Li, Li Fan, Menglin Yang, Rex Ying, Yali Fu, Yao Shu","submitted_at":"2025-09-02T14:16:02Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning, where reasoning occurs silently via latent structures without emitting intermediate textual steps. Implicit reasoning brings advantages such as lower generation cost, faster inference, and better alignment with internal computation. Although prior surveys have discussed l"},"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":"2509.02350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-02T14:16:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fdb642a23f486a3e09b63df31c59e350f1096e39e6b1fe76f28c5a445fe37eeb","abstract_canon_sha256":"bb821c98d9c5226e27807ac53ff3580507893fa83cd08b7321b271897c9e9c3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:36.831742Z","signature_b64":"2fFGABHOm31xnYxtdVQEaOH1i8cOAA5tRDhPCAh1XOvoI/t/KrmIEVnzvwJmscz8o6YtdWBBpYfp1BlKWvSdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c652c34857f4a2464c7fcfbeaeeb093e16fbbd633b28fef8dc5e7290da0f3bf","last_reissued_at":"2026-07-05T12:03:36.831193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:36.831193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengwei Qin, Irwin King, Jiahong Liu, Jindong Li, Li Fan, Menglin Yang, Rex Ying, Yali Fu, Yao Shu","submitted_at":"2025-09-02T14:16:02Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decision-making. To support efficient reasoning, recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning, where reasoning occurs silently via latent structures without emitting intermediate textual steps. Implicit reasoning brings advantages such as lower generation cost, faster inference, and better alignment with internal computation. Although prior surveys have discussed l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02350","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/2509.02350/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":"2509.02350","created_at":"2026-07-05T12:03:36.831259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02350v1","created_at":"2026-07-05T12:03:36.831259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02350","created_at":"2026-07-05T12:03:36.831259+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRSSYNEFP5FC","created_at":"2026-07-05T12:03:36.831259+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRSSYNEFP5FCIZGH","created_at":"2026-07-05T12:03:36.831259+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRSSYNEF","created_at":"2026-07-05T12:03:36.831259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24233","citing_title":"Latent Visual States for Efficient Multimodal Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05315","citing_title":"LoRi: Low-Rank Distillation for Implicit Reasoning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31779","citing_title":"Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28639","citing_title":"The Attentional White Bear Effect in Transformer Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2601.18664","citing_title":"S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation","ref_index":18,"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":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20075","citing_title":"CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17866","citing_title":"Latent Abstraction for Retrieval-Augmented Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08299","citing_title":"SeLaR: Selective Latent Reasoning in Large Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21027","citing_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP","json":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP.json","graph_json":"https://pith.science/api/pith-number/LRSSYNEFP5FCIZGH7T56V3VQSP/graph.json","events_json":"https://pith.science/api/pith-number/LRSSYNEFP5FCIZGH7T56V3VQSP/events.json","paper":"https://pith.science/paper/LRSSYNEF"},"agent_actions":{"view_html":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP","download_json":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP.json","view_paper":"https://pith.science/paper/LRSSYNEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02350&json=true","fetch_graph":"https://pith.science/api/pith-number/LRSSYNEFP5FCIZGH7T56V3VQSP/graph.json","fetch_events":"https://pith.science/api/pith-number/LRSSYNEFP5FCIZGH7T56V3VQSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP/action/storage_attestation","attest_author":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP/action/author_attestation","sign_citation":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP/action/citation_signature","submit_replication":"https://pith.science/pith/LRSSYNEFP5FCIZGH7T56V3VQSP/action/replication_record"}},"created_at":"2026-07-05T12:03:36.831259+00:00","updated_at":"2026-07-05T12:03:36.831259+00:00"}