{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y2SNHPSK5KEEG627OD6IEOCQXC","short_pith_number":"pith:Y2SNHPSK","schema_version":"1.0","canonical_sha256":"c6a4d3be4aea88437b5f70fc823850b8bfab37f153d5af7f4ef59c626f8a68fa","source":{"kind":"arxiv","id":"2508.19903","version":1},"attestation_state":"computed","paper":{"title":"Logical Reasoning with Outcome Reward Models for Test-Time Scaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Ramya Keerthy Thatikonda, Wray Buntine","submitted_at":"2025-08-27T14:08:43Z","abstract_excerpt":"Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with dedicated outcome or process reward models has opened up new avenues to enhance LLMs performance in complex reasoning tasks, this space is under-explored in deductive logical reasoning. We present a set of Outcome Reward Models (ORMs) for deductive reasoning. To train the ORMs we mainly generate data using Chain-of-Thought (CoT) with single and multiple samples. Ad"},"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":"2508.19903","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-27T14:08:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a16a33b59fe62d67a506967427b03976f8c78cb088fa75ca0b2c17424fe29219","abstract_canon_sha256":"c3d7c73cb8a7a1eeb310589661aff65195742c2aad6586586f1da1cf47d685d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:19.648090Z","signature_b64":"6sBETPIy9B5b3Sq1PqWCiz5AOaYnejTE/jKcDy2pQgfOgO++ul7IN4dVgtjkCCRu6G69ebH/OMlZdc/vZ9vgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6a4d3be4aea88437b5f70fc823850b8bfab37f153d5af7f4ef59c626f8a68fa","last_reissued_at":"2026-07-05T12:00:19.647640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:19.647640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Logical Reasoning with Outcome Reward Models for Test-Time Scaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ehsan Shareghi, Ramya Keerthy Thatikonda, Wray Buntine","submitted_at":"2025-08-27T14:08:43Z","abstract_excerpt":"Logical reasoning is a critical benchmark for evaluating the capabilities of large language models (LLMs), as it reflects their ability to derive valid conclusions from given premises. While the combination of test-time scaling with dedicated outcome or process reward models has opened up new avenues to enhance LLMs performance in complex reasoning tasks, this space is under-explored in deductive logical reasoning. We present a set of Outcome Reward Models (ORMs) for deductive reasoning. To train the ORMs we mainly generate data using Chain-of-Thought (CoT) with single and multiple samples. Ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19903","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/2508.19903/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":"2508.19903","created_at":"2026-07-05T12:00:19.647701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19903v1","created_at":"2026-07-05T12:00:19.647701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19903","created_at":"2026-07-05T12:00:19.647701+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y2SNHPSK5KEE","created_at":"2026-07-05T12:00:19.647701+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y2SNHPSK5KEEG627","created_at":"2026-07-05T12:00:19.647701+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y2SNHPSK","created_at":"2026-07-05T12:00:19.647701+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/Y2SNHPSK5KEEG627OD6IEOCQXC","json":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC.json","graph_json":"https://pith.science/api/pith-number/Y2SNHPSK5KEEG627OD6IEOCQXC/graph.json","events_json":"https://pith.science/api/pith-number/Y2SNHPSK5KEEG627OD6IEOCQXC/events.json","paper":"https://pith.science/paper/Y2SNHPSK"},"agent_actions":{"view_html":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC","download_json":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC.json","view_paper":"https://pith.science/paper/Y2SNHPSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19903&json=true","fetch_graph":"https://pith.science/api/pith-number/Y2SNHPSK5KEEG627OD6IEOCQXC/graph.json","fetch_events":"https://pith.science/api/pith-number/Y2SNHPSK5KEEG627OD6IEOCQXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC/action/storage_attestation","attest_author":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC/action/author_attestation","sign_citation":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC/action/citation_signature","submit_replication":"https://pith.science/pith/Y2SNHPSK5KEEG627OD6IEOCQXC/action/replication_record"}},"created_at":"2026-07-05T12:00:19.647701+00:00","updated_at":"2026-07-05T12:00:19.647701+00:00"}