{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MPNVQBWFJOWEC2GQWHOWXEWDU3","short_pith_number":"pith:MPNVQBWF","schema_version":"1.0","canonical_sha256":"63db5806c54bac4168d0b1dd6b92c3a6d1cecb60ba39be4e846932c52f19c7cd","source":{"kind":"arxiv","id":"2510.06052","version":2},"attestation_state":"computed","paper":{"title":"MixReasoning: Switching Modes to Think","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Gongfan Fang, Haiquan Lu, Qi Li, Xinchao Wang, Xinyin Ma","submitted_at":"2025-10-07T15:46:34Z","abstract_excerpt":"Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to t"},"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":"2510.06052","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-07T15:46:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d9f22f34a983d8657b3c69cd055b1990e5cb1dc9758179e5699084c096ace6d5","abstract_canon_sha256":"8d82b1306a410b078875a1e60216fcd25cfca54236f8aca202451c7363944638"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:10.773835Z","signature_b64":"OfDZ+AC24e6kEGBCBhtIOBmC1Vz9XfLGFnevaa+IWjDN8G85D6sUhWymPX8A3WkEwsVubQAG7B0N1rUckSi4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63db5806c54bac4168d0b1dd6b92c3a6d1cecb60ba39be4e846932c52f19c7cd","last_reissued_at":"2026-06-09T02:07:10.772849Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:10.772849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MixReasoning: Switching Modes to Think","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Gongfan Fang, Haiquan Lu, Qi Li, Xinchao Wang, Xinyin Ma","submitted_at":"2025-10-07T15:46:34Z","abstract_excerpt":"Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step introduces substantial redundancy, as sub-problems vary widely in difficulty and complexity: a small number of pivotal steps are genuinely challenging and decisive for the final answer, while many others only involve straightforward revisions or simple computations. Therefore, a natural idea is to endow reasoning models with the ability to adaptively respond to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.06052","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/2510.06052/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":"2510.06052","created_at":"2026-06-09T02:07:10.772989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.06052v2","created_at":"2026-06-09T02:07:10.772989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.06052","created_at":"2026-06-09T02:07:10.772989+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPNVQBWFJOWE","created_at":"2026-06-09T02:07:10.772989+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPNVQBWFJOWEC2GQ","created_at":"2026-06-09T02:07:10.772989+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPNVQBWF","created_at":"2026-06-09T02:07:10.772989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20315","citing_title":"Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3","json":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3.json","graph_json":"https://pith.science/api/pith-number/MPNVQBWFJOWEC2GQWHOWXEWDU3/graph.json","events_json":"https://pith.science/api/pith-number/MPNVQBWFJOWEC2GQWHOWXEWDU3/events.json","paper":"https://pith.science/paper/MPNVQBWF"},"agent_actions":{"view_html":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3","download_json":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3.json","view_paper":"https://pith.science/paper/MPNVQBWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.06052&json=true","fetch_graph":"https://pith.science/api/pith-number/MPNVQBWFJOWEC2GQWHOWXEWDU3/graph.json","fetch_events":"https://pith.science/api/pith-number/MPNVQBWFJOWEC2GQWHOWXEWDU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3/action/storage_attestation","attest_author":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3/action/author_attestation","sign_citation":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3/action/citation_signature","submit_replication":"https://pith.science/pith/MPNVQBWFJOWEC2GQWHOWXEWDU3/action/replication_record"}},"created_at":"2026-06-09T02:07:10.772989+00:00","updated_at":"2026-06-09T02:07:10.772989+00:00"}