{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UN4EWNYV2JJWOG7D4YW7ALLN6I","short_pith_number":"pith:UN4EWNYV","schema_version":"1.0","canonical_sha256":"a3784b3715d253671be3e62df02d6df22e0f5a42160eff7d446dec96c6b212fa","source":{"kind":"arxiv","id":"2608.05643","version":1},"attestation_state":"computed","paper":{"title":"Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ahsan Bilal, Ali Subhan, Dean F. Hougen, Lena Trigg, Muhammad Ahmed Mohsin, Muhammad Ali, Muhammad Umer","submitted_at":"2026-08-06T06:38:37Z","abstract_excerpt":"Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity. Verifier-based selection offers an alternative, but its performance depends on the calibration of an external reward model. We propose a verifier-free breadth--depth refinement framework that uses test-time compute to both explore and improve candidate solutions. The method samples multiple independent reasoning rollouts, refines each rollout through iterativ"},"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":"2608.05643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T06:38:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0ae4baa4532bb0fcce186423b722f9b0ee12729179c84fafa062b69d3e5755f2","abstract_canon_sha256":"30caed25ae85c9459205d64cb2753eb90d011e9711e3a2b6345bb0a47849479f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:16.592180Z","signature_b64":"JyTEQjtThGJI2qN9xVB0r4u5UnwLPjS+/KNOSqEBp0lopGqOwfkhIr7zejX7NpDFJ3brEtNto6WUxGp/HyoPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3784b3715d253671be3e62df02d6df22e0f5a42160eff7d446dec96c6b212fa","last_reissued_at":"2026-08-07T00:52:16.590445Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:16.590445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ahsan Bilal, Ali Subhan, Dean F. Hougen, Lena Trigg, Muhammad Ahmed Mohsin, Muhammad Ali, Muhammad Umer","submitted_at":"2026-08-06T06:38:37Z","abstract_excerpt":"Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity. Verifier-based selection offers an alternative, but its performance depends on the calibration of an external reward model. We propose a verifier-free breadth--depth refinement framework that uses test-time compute to both explore and improve candidate solutions. The method samples multiple independent reasoning rollouts, refines each rollout through iterativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05643","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/2608.05643/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":"2608.05643","created_at":"2026-08-07T00:52:16.591960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05643v1","created_at":"2026-08-07T00:52:16.591960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05643","created_at":"2026-08-07T00:52:16.591960+00:00"},{"alias_kind":"pith_short_12","alias_value":"UN4EWNYV2JJW","created_at":"2026-08-07T00:52:16.591960+00:00"},{"alias_kind":"pith_short_16","alias_value":"UN4EWNYV2JJWOG7D","created_at":"2026-08-07T00:52:16.591960+00:00"},{"alias_kind":"pith_short_8","alias_value":"UN4EWNYV","created_at":"2026-08-07T00:52:16.591960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I","json":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I.json","graph_json":"https://pith.science/api/pith-number/UN4EWNYV2JJWOG7D4YW7ALLN6I/graph.json","events_json":"https://pith.science/api/pith-number/UN4EWNYV2JJWOG7D4YW7ALLN6I/events.json","paper":"https://pith.science/paper/UN4EWNYV"},"agent_actions":{"view_html":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I","download_json":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I.json","view_paper":"https://pith.science/paper/UN4EWNYV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05643&json=true","fetch_graph":"https://pith.science/api/pith-number/UN4EWNYV2JJWOG7D4YW7ALLN6I/graph.json","fetch_events":"https://pith.science/api/pith-number/UN4EWNYV2JJWOG7D4YW7ALLN6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I/action/storage_attestation","attest_author":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I/action/author_attestation","sign_citation":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I/action/citation_signature","submit_replication":"https://pith.science/pith/UN4EWNYV2JJWOG7D4YW7ALLN6I/action/replication_record"}},"created_at":"2026-08-07T00:52:16.591960+00:00","updated_at":"2026-08-07T00:52:16.591960+00:00"}