{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QPKBCORRG3L7PRUFDZ3T66N527","short_pith_number":"pith:QPKBCORR","schema_version":"1.0","canonical_sha256":"83d4113a3136d7f7c6851e773f79bdd7d9fffc7095e78e5addc925c24f74ec90","source":{"kind":"arxiv","id":"2607.25069","version":1},"attestation_state":"computed","paper":{"title":"DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Sagnik Sinha, Shreyas Shrestha","submitted_at":"2026-07-27T20:59:14Z","abstract_excerpt":"Automated verification of numerical claims is a challenging problem, as it requires both language understanding and quantitative reasoning. This paper describes our system for CLEF 2026 CheckThat! Task 2, which focuses on ranking reasoning traces generated by large language models (LLMs) and predicting a final verdict for numerical claims in English and Arabic. We explore two approaches. The first approach fine-tunes an LLM-based verifier using LoRA to score each reasoning trace independently as a binary classification problem, and selects the final verdict using Best-of-N selection. We furthe"},"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":"2607.25069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T20:59:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d26d47f0ebf502945aa96f6ce7e619d82cf619a21fd900435a60882094aca715","abstract_canon_sha256":"33c6c605e576266ca269a426ccef0d9d734a6702e46b9b048adcc324ea3434c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:00.984688Z","signature_b64":"VVaCpmdjCzTakusMZ+eFMONrYE5rAtppmaQpcbZrwALKFb2SaPCwg/brmFXTt7cSHZPs1BUO8IeosG3L15vgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83d4113a3136d7f7c6851e773f79bdd7d9fffc7095e78e5addc925c24f74ec90","last_reissued_at":"2026-07-29T00:25:00.983861Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:00.983861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DS@GT ARC at CheckThat! 2026: LLM-Based Trace Ranking and Grouped Reward Modeling for Multilingual Numerical Claim Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Sagnik Sinha, Shreyas Shrestha","submitted_at":"2026-07-27T20:59:14Z","abstract_excerpt":"Automated verification of numerical claims is a challenging problem, as it requires both language understanding and quantitative reasoning. This paper describes our system for CLEF 2026 CheckThat! Task 2, which focuses on ranking reasoning traces generated by large language models (LLMs) and predicting a final verdict for numerical claims in English and Arabic. We explore two approaches. The first approach fine-tunes an LLM-based verifier using LoRA to score each reasoning trace independently as a binary classification problem, and selects the final verdict using Best-of-N selection. We furthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25069","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/2607.25069/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":"2607.25069","created_at":"2026-07-29T00:25:00.984285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25069v1","created_at":"2026-07-29T00:25:00.984285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25069","created_at":"2026-07-29T00:25:00.984285+00:00"},{"alias_kind":"pith_short_12","alias_value":"QPKBCORRG3L7","created_at":"2026-07-29T00:25:00.984285+00:00"},{"alias_kind":"pith_short_16","alias_value":"QPKBCORRG3L7PRUF","created_at":"2026-07-29T00:25:00.984285+00:00"},{"alias_kind":"pith_short_8","alias_value":"QPKBCORR","created_at":"2026-07-29T00:25:00.984285+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/QPKBCORRG3L7PRUFDZ3T66N527","json":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527.json","graph_json":"https://pith.science/api/pith-number/QPKBCORRG3L7PRUFDZ3T66N527/graph.json","events_json":"https://pith.science/api/pith-number/QPKBCORRG3L7PRUFDZ3T66N527/events.json","paper":"https://pith.science/paper/QPKBCORR"},"agent_actions":{"view_html":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527","download_json":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527.json","view_paper":"https://pith.science/paper/QPKBCORR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25069&json=true","fetch_graph":"https://pith.science/api/pith-number/QPKBCORRG3L7PRUFDZ3T66N527/graph.json","fetch_events":"https://pith.science/api/pith-number/QPKBCORRG3L7PRUFDZ3T66N527/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527/action/storage_attestation","attest_author":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527/action/author_attestation","sign_citation":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527/action/citation_signature","submit_replication":"https://pith.science/pith/QPKBCORRG3L7PRUFDZ3T66N527/action/replication_record"}},"created_at":"2026-07-29T00:25:00.984285+00:00","updated_at":"2026-07-29T00:25:00.984285+00:00"}