{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7OXKREG2BFXSCKPEXTLDJEQPDP","short_pith_number":"pith:7OXKREG2","schema_version":"1.0","canonical_sha256":"fbaea890da096f2129e4bcd634920f1bde406580c808c63f6ce9027a2952c307","source":{"kind":"arxiv","id":"2505.24863","version":1},"attestation_state":"computed","paper":{"title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Wang, Haoran Geng, Huan Zhang, Jitendra Malik, Junyu Zhang, Peihao Li, Runpei Dong, Saurabh Gupta, Xialin He, Xuying Ning, Yutong Bai","submitted_at":"2025-05-30T17:58:36Z","abstract_excerpt":"This paper presents AlphaOne ($\\alpha$1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. $\\alpha$1 first introduces $\\alpha$ moment, which represents the scaled thinking phase with a universal parameter $\\alpha$. Within this scaled pre-$\\alpha$ moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the $\\alpha$ moment, $\\alpha$1 deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoni"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.24863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T17:58:36Z","cross_cats_sorted":[],"title_canon_sha256":"41394a2b78608a215ffce4955ea0855adaf28c3332130a60f598f967328b2f9a","abstract_canon_sha256":"7b7bb0b0135b74dd534d1f7405ab88e22f606050d548db5f7fe6c0ea4174686c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:58.016569Z","signature_b64":"hCnyp5pzN/CWOKr2tEbYLXLP6UsRegnvgccmtv/nut/QhHvAQZ6Q79Qmfg+ta7Cn/xeDUVtmlrzwk2rVYrHbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbaea890da096f2129e4bcd634920f1bde406580c808c63f6ce9027a2952c307","last_reissued_at":"2026-07-05T11:12:58.016028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:58.016028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Wang, Haoran Geng, Huan Zhang, Jitendra Malik, Junyu Zhang, Peihao Li, Runpei Dong, Saurabh Gupta, Xialin He, Xuying Ning, Yutong Bai","submitted_at":"2025-05-30T17:58:36Z","abstract_excerpt":"This paper presents AlphaOne ($\\alpha$1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. $\\alpha$1 first introduces $\\alpha$ moment, which represents the scaled thinking phase with a universal parameter $\\alpha$. Within this scaled pre-$\\alpha$ moment phase, it dynamically schedules slow thinking transitions by modeling the insertion of reasoning transition tokens as a Bernoulli stochastic process. After the $\\alpha$ moment, $\\alpha$1 deterministically terminates slow thinking with the end-of-thinking token, thereby fostering fast reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24863","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/2505.24863/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":"2505.24863","created_at":"2026-07-05T11:12:58.016090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24863v1","created_at":"2026-07-05T11:12:58.016090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24863","created_at":"2026-07-05T11:12:58.016090+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OXKREG2BFXS","created_at":"2026-07-05T11:12:58.016090+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OXKREG2BFXSCKPE","created_at":"2026-07-05T11:12:58.016090+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OXKREG2","created_at":"2026-07-05T11:12:58.016090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03102","citing_title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15205","citing_title":"Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21743","citing_title":"Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.19669","citing_title":"DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16419","citing_title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06165","citing_title":"Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost","ref_index":226,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP","json":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP.json","graph_json":"https://pith.science/api/pith-number/7OXKREG2BFXSCKPEXTLDJEQPDP/graph.json","events_json":"https://pith.science/api/pith-number/7OXKREG2BFXSCKPEXTLDJEQPDP/events.json","paper":"https://pith.science/paper/7OXKREG2"},"agent_actions":{"view_html":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP","download_json":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP.json","view_paper":"https://pith.science/paper/7OXKREG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24863&json=true","fetch_graph":"https://pith.science/api/pith-number/7OXKREG2BFXSCKPEXTLDJEQPDP/graph.json","fetch_events":"https://pith.science/api/pith-number/7OXKREG2BFXSCKPEXTLDJEQPDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP/action/storage_attestation","attest_author":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP/action/author_attestation","sign_citation":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP/action/citation_signature","submit_replication":"https://pith.science/pith/7OXKREG2BFXSCKPEXTLDJEQPDP/action/replication_record"}},"created_at":"2026-07-05T11:12:58.016090+00:00","updated_at":"2026-07-05T11:12:58.016090+00:00"}