{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ALJQIKS6M7JDRNM5EYYGLSWILI","short_pith_number":"pith:ALJQIKS6","schema_version":"1.0","canonical_sha256":"02d3042a5e67d238b59d263065cac85a11d39c65dfdec4e3df37cd3fa3bd341e","source":{"kind":"arxiv","id":"2607.16229","version":1},"attestation_state":"computed","paper":{"title":"FinBench: Time-Gated Calibration and Uncertainty Benchmarking for Agentic Financial Forecasting","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","q-fin.CP","q-fin.PM"],"primary_cat":"stat.AP","authors_text":"Rishab Ghosh, Vinay Devarakonda","submitted_at":"2026-06-24T01:27:30Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as components of agentic systems that observe, plan, and act. In finance, even \"assistive\" systems become decision-relevant once their outputs are used to size trades or allocate risk. A key failure mode is the confidence--competence gap: a model that is only slightly better than chance but consistently overconfident will, under typical bet-sizing rules, generate negative long-run growth. Existing benchmarks emphasize semantic understanding or point accuracy, but do not directly test probabilistic calibration under the temporal constraints and"},"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":"2607.16229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"stat.AP","submitted_at":"2026-06-24T01:27:30Z","cross_cats_sorted":["cs.LG","q-fin.CP","q-fin.PM"],"title_canon_sha256":"ccdeb89de185f42ff502e1235ee4f1078190559b26ac683ddc20eb11a6f51d53","abstract_canon_sha256":"1b7f6b8b6d3b242f6c20841af6611a4cbee8e799658d04568ecb267803a7edfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:06.857487Z","signature_b64":"Omk8/vX6/+wAcC3JHgPIelaHM0idi8/x1lXlPNCrNP0vlQEvQ/L+zNerFtAtw0XTeZSZVh8hkMGw3fFH4YzeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02d3042a5e67d238b59d263065cac85a11d39c65dfdec4e3df37cd3fa3bd341e","last_reissued_at":"2026-07-21T00:20:06.856721Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:06.856721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinBench: Time-Gated Calibration and Uncertainty Benchmarking for Agentic Financial Forecasting","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","q-fin.CP","q-fin.PM"],"primary_cat":"stat.AP","authors_text":"Rishab Ghosh, Vinay Devarakonda","submitted_at":"2026-06-24T01:27:30Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as components of agentic systems that observe, plan, and act. In finance, even \"assistive\" systems become decision-relevant once their outputs are used to size trades or allocate risk. A key failure mode is the confidence--competence gap: a model that is only slightly better than chance but consistently overconfident will, under typical bet-sizing rules, generate negative long-run growth. Existing benchmarks emphasize semantic understanding or point accuracy, but do not directly test probabilistic calibration under the temporal constraints and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16229","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/2607.16229/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":"2607.16229","created_at":"2026-07-21T00:20:06.857104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16229v1","created_at":"2026-07-21T00:20:06.857104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16229","created_at":"2026-07-21T00:20:06.857104+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALJQIKS6M7JD","created_at":"2026-07-21T00:20:06.857104+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALJQIKS6M7JDRNM5","created_at":"2026-07-21T00:20:06.857104+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALJQIKS6","created_at":"2026-07-21T00:20:06.857104+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/ALJQIKS6M7JDRNM5EYYGLSWILI","json":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI.json","graph_json":"https://pith.science/api/pith-number/ALJQIKS6M7JDRNM5EYYGLSWILI/graph.json","events_json":"https://pith.science/api/pith-number/ALJQIKS6M7JDRNM5EYYGLSWILI/events.json","paper":"https://pith.science/paper/ALJQIKS6"},"agent_actions":{"view_html":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI","download_json":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI.json","view_paper":"https://pith.science/paper/ALJQIKS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16229&json=true","fetch_graph":"https://pith.science/api/pith-number/ALJQIKS6M7JDRNM5EYYGLSWILI/graph.json","fetch_events":"https://pith.science/api/pith-number/ALJQIKS6M7JDRNM5EYYGLSWILI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI/action/storage_attestation","attest_author":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI/action/author_attestation","sign_citation":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI/action/citation_signature","submit_replication":"https://pith.science/pith/ALJQIKS6M7JDRNM5EYYGLSWILI/action/replication_record"}},"created_at":"2026-07-21T00:20:06.857104+00:00","updated_at":"2026-07-21T00:20:06.857104+00:00"}