{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CVE72TNW6CWJX3LCLCEYJ5M3NX","short_pith_number":"pith:CVE72TNW","schema_version":"1.0","canonical_sha256":"1549fd4db6f0ac9bed62588984f59b6df73db83e6628ba4b6992189b83a9fb6f","source":{"kind":"arxiv","id":"2503.13447","version":1},"attestation_state":"computed","paper":{"title":"MetaScale: Test-Time Scaling with Evolving Meta-Thoughts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fei Wang, Hoifung Poon, James Y. Huang, Muhao Chen, Nan Xu, Qin Liu, Sheng Zhang, Wenxuan Zhou","submitted_at":"2025-03-17T17:59:54Z","abstract_excerpt":"One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a given task. Existing approaches impose fixed cognitive structures that enhance performance in specific tasks but lack adaptability across diverse scenarios. To address this limitation, we introduce METASCALE, a test-time scaling framework based on meta-thoughts -- adaptive thinking strategies tailored to each task. METASCALE initializes a pool of candidate met"},"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":"2503.13447","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T17:59:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d3192bbfa37d0c3b979efd486105c49c1b155f0b4c06acaa8c3c2948fc205446","abstract_canon_sha256":"7a7188350d4230b9aa6256a1b553c70890037d39064670e96491881f67b1ebea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:00.940560Z","signature_b64":"5yG3NKST3X+TOfgUaVO7rIbWSGeCFChdfpwRE5qCA03VVfIx4cfX3G0co4j6Fo5duL1rgtF12psyxEelxWzABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1549fd4db6f0ac9bed62588984f59b6df73db83e6628ba4b6992189b83a9fb6f","last_reissued_at":"2026-07-05T10:33:00.939997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:00.939997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaScale: Test-Time Scaling with Evolving Meta-Thoughts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fei Wang, Hoifung Poon, James Y. Huang, Muhao Chen, Nan Xu, Qin Liu, Sheng Zhang, Wenxuan Zhou","submitted_at":"2025-03-17T17:59:54Z","abstract_excerpt":"One critical challenge for large language models (LLMs) for making complex reasoning is their reliance on matching reasoning patterns from training data, instead of proactively selecting the most appropriate cognitive strategy to solve a given task. Existing approaches impose fixed cognitive structures that enhance performance in specific tasks but lack adaptability across diverse scenarios. To address this limitation, we introduce METASCALE, a test-time scaling framework based on meta-thoughts -- adaptive thinking strategies tailored to each task. METASCALE initializes a pool of candidate met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13447","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/2503.13447/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":"2503.13447","created_at":"2026-07-05T10:33:00.940059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13447v1","created_at":"2026-07-05T10:33:00.940059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13447","created_at":"2026-07-05T10:33:00.940059+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVE72TNW6CWJ","created_at":"2026-07-05T10:33:00.940059+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVE72TNW6CWJX3LC","created_at":"2026-07-05T10:33:00.940059+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVE72TNW","created_at":"2026-07-05T10:33:00.940059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21005","citing_title":"Building Agent Harnesses for Scientific Curation from Multimodal Sources","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17399","citing_title":"Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX","json":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX.json","graph_json":"https://pith.science/api/pith-number/CVE72TNW6CWJX3LCLCEYJ5M3NX/graph.json","events_json":"https://pith.science/api/pith-number/CVE72TNW6CWJX3LCLCEYJ5M3NX/events.json","paper":"https://pith.science/paper/CVE72TNW"},"agent_actions":{"view_html":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX","download_json":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX.json","view_paper":"https://pith.science/paper/CVE72TNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13447&json=true","fetch_graph":"https://pith.science/api/pith-number/CVE72TNW6CWJX3LCLCEYJ5M3NX/graph.json","fetch_events":"https://pith.science/api/pith-number/CVE72TNW6CWJX3LCLCEYJ5M3NX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX/action/storage_attestation","attest_author":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX/action/author_attestation","sign_citation":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX/action/citation_signature","submit_replication":"https://pith.science/pith/CVE72TNW6CWJX3LCLCEYJ5M3NX/action/replication_record"}},"created_at":"2026-07-05T10:33:00.940059+00:00","updated_at":"2026-07-05T10:33:00.940059+00:00"}