{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KOO3ODKEDWZT5DF4IGS45HJ5AT","short_pith_number":"pith:KOO3ODKE","schema_version":"1.0","canonical_sha256":"539db70d441db33e8cbc41a5ce9d3d04d0b8f79a2b7b69821ef062d76af84e2d","source":{"kind":"arxiv","id":"2506.04611","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunerh Cho, Ho-Lam Chung, Hsiao-Ying Huang, Jian-Ren Lin, Teng-Yun Hsiao, Yun-Nung Chen, Zhang Ziwei","submitted_at":"2025-06-05T04:02:17Z","abstract_excerpt":"Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based, search-based, and trajectory optimization strategies. We observe that reasoning-optimized models often produce less diverse outputs, which limits TTS effectiveness. To address this, we propose ADAPT (A Diversity Aware Prefix fine-Tuning), a lightweight method that applies prefix tuning with a diversity-focused data strategy. Experiments on mathematical reasoning tasks "},"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":"2506.04611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T04:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"ea1191a73900e0abd5e341a2273a590743146591c12e363a0a9fb34400b45a76","abstract_canon_sha256":"2a2cbf4ae0d39bfb5427b91a7a5a5067b4f55dfbbcb1367367bd053c70df030b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:17.836607Z","signature_b64":"RNJ8zh4P/Lt5tnFpQzfOfF469XSP/67mfPY2hwt5pf7D715Wk3YM69F0VP6UFpK0UZM7tqDdqEtP58oyCQNHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"539db70d441db33e8cbc41a5ce9d3d04d0b8f79a2b7b69821ef062d76af84e2d","last_reissued_at":"2026-07-05T11:16:17.835993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:17.835993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunerh Cho, Ho-Lam Chung, Hsiao-Ying Huang, Jian-Ren Lin, Teng-Yun Hsiao, Yun-Nung Chen, Zhang Ziwei","submitted_at":"2025-06-05T04:02:17Z","abstract_excerpt":"Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based, search-based, and trajectory optimization strategies. We observe that reasoning-optimized models often produce less diverse outputs, which limits TTS effectiveness. To address this, we propose ADAPT (A Diversity Aware Prefix fine-Tuning), a lightweight method that applies prefix tuning with a diversity-focused data strategy. Experiments on mathematical reasoning tasks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04611","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/2506.04611/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":"2506.04611","created_at":"2026-07-05T11:16:17.836068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04611v1","created_at":"2026-07-05T11:16:17.836068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04611","created_at":"2026-07-05T11:16:17.836068+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOO3ODKEDWZT","created_at":"2026-07-05T11:16:17.836068+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOO3ODKEDWZT5DF4","created_at":"2026-07-05T11:16:17.836068+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOO3ODKE","created_at":"2026-07-05T11:16:17.836068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06262","citing_title":"From Exposure to Internalization: Dual-Stream Calibration for In-context Clinical Reasoning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT","json":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT.json","graph_json":"https://pith.science/api/pith-number/KOO3ODKEDWZT5DF4IGS45HJ5AT/graph.json","events_json":"https://pith.science/api/pith-number/KOO3ODKEDWZT5DF4IGS45HJ5AT/events.json","paper":"https://pith.science/paper/KOO3ODKE"},"agent_actions":{"view_html":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT","download_json":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT.json","view_paper":"https://pith.science/paper/KOO3ODKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04611&json=true","fetch_graph":"https://pith.science/api/pith-number/KOO3ODKEDWZT5DF4IGS45HJ5AT/graph.json","fetch_events":"https://pith.science/api/pith-number/KOO3ODKEDWZT5DF4IGS45HJ5AT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT/action/storage_attestation","attest_author":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT/action/author_attestation","sign_citation":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT/action/citation_signature","submit_replication":"https://pith.science/pith/KOO3ODKEDWZT5DF4IGS45HJ5AT/action/replication_record"}},"created_at":"2026-07-05T11:16:17.836068+00:00","updated_at":"2026-07-05T11:16:17.836068+00:00"}