{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WSXXFGXJO3QBQG6EODXEYV7A45","short_pith_number":"pith:WSXXFGXJ","schema_version":"1.0","canonical_sha256":"b4af729ae976e0181bc470ee4c57e0e75d91d0238eb3be30bcb30ccfd3fabc11","source":{"kind":"arxiv","id":"2607.21340","version":1},"attestation_state":"computed","paper":{"title":"Capital Markets LLM Reliability Score (CM-LRS): From Plausible to Bankable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Prerit Ahuja","submitted_at":"2026-07-23T14:10:58Z","abstract_excerpt":"In capital-markets workflows the question is rarely whether a large language model can produce a fluent draft, but whether the draft is bankable: defensible in front of a counter-party or a regulator, with the documents in hand. Existing methods address parts of that gap: open-domain QA benchmarks reward surface accuracy, and finance benchmarks (FinanceBench, FinQA, ConvFinQA) advance document-grounded and numerical QA but evaluate at the question-answer layer rather than the workflow outputs practitioners defend.\n  We introduce CM-LRS, a Capital Markets LLM Reliability Score, evaluating outpu"},"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":"2607.21340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T14:10:58Z","cross_cats_sorted":[],"title_canon_sha256":"da45bc1c515afbed891970aeb6b3eacd98a4f14f116fa94c1606c768a7d3fa9a","abstract_canon_sha256":"479ea4314d966c7baae092c49c40360c6c25bc1f7d842547aae4bcb53db4edab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:26.645051Z","signature_b64":"CiQaydghyqd8P/sEJp1SSkwXzV8xvxn73U4kapTZQUHjZ26lb1iC02awHMz1aWuEiHI3jXVKCCjbsW3s1mfzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4af729ae976e0181bc470ee4c57e0e75d91d0238eb3be30bcb30ccfd3fabc11","last_reissued_at":"2026-07-24T01:24:26.644152Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:26.644152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Capital Markets LLM Reliability Score (CM-LRS): From Plausible to Bankable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Prerit Ahuja","submitted_at":"2026-07-23T14:10:58Z","abstract_excerpt":"In capital-markets workflows the question is rarely whether a large language model can produce a fluent draft, but whether the draft is bankable: defensible in front of a counter-party or a regulator, with the documents in hand. Existing methods address parts of that gap: open-domain QA benchmarks reward surface accuracy, and finance benchmarks (FinanceBench, FinQA, ConvFinQA) advance document-grounded and numerical QA but evaluate at the question-answer layer rather than the workflow outputs practitioners defend.\n  We introduce CM-LRS, a Capital Markets LLM Reliability Score, evaluating outpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21340","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/2607.21340/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":"2607.21340","created_at":"2026-07-24T01:24:26.644609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21340v1","created_at":"2026-07-24T01:24:26.644609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21340","created_at":"2026-07-24T01:24:26.644609+00:00"},{"alias_kind":"pith_short_12","alias_value":"WSXXFGXJO3QB","created_at":"2026-07-24T01:24:26.644609+00:00"},{"alias_kind":"pith_short_16","alias_value":"WSXXFGXJO3QBQG6E","created_at":"2026-07-24T01:24:26.644609+00:00"},{"alias_kind":"pith_short_8","alias_value":"WSXXFGXJ","created_at":"2026-07-24T01:24:26.644609+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/WSXXFGXJO3QBQG6EODXEYV7A45","json":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45.json","graph_json":"https://pith.science/api/pith-number/WSXXFGXJO3QBQG6EODXEYV7A45/graph.json","events_json":"https://pith.science/api/pith-number/WSXXFGXJO3QBQG6EODXEYV7A45/events.json","paper":"https://pith.science/paper/WSXXFGXJ"},"agent_actions":{"view_html":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45","download_json":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45.json","view_paper":"https://pith.science/paper/WSXXFGXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21340&json=true","fetch_graph":"https://pith.science/api/pith-number/WSXXFGXJO3QBQG6EODXEYV7A45/graph.json","fetch_events":"https://pith.science/api/pith-number/WSXXFGXJO3QBQG6EODXEYV7A45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45/action/storage_attestation","attest_author":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45/action/author_attestation","sign_citation":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45/action/citation_signature","submit_replication":"https://pith.science/pith/WSXXFGXJO3QBQG6EODXEYV7A45/action/replication_record"}},"created_at":"2026-07-24T01:24:26.644609+00:00","updated_at":"2026-07-24T01:24:26.644609+00:00"}