{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WRZBUMKVNZTUL422D2BTORAKUF","short_pith_number":"pith:WRZBUMKV","schema_version":"1.0","canonical_sha256":"b4721a31556e6745f35a1e8337440aa160562917bbd207fd3956a8d225462aeb","source":{"kind":"arxiv","id":"2605.31201","version":1},"attestation_state":"computed","paper":{"title":"Learning Whom to Trust: Market-Feedback Adaptive Retrieval for Frozen LLMs in Event-Driven Financial RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Roy E. Welsch, Zijie Zhao","submitted_at":"2026-05-29T12:08:58Z","abstract_excerpt":"Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source depends on event type, forecast horizon, and market context. We study news-triggered event-impact prediction as a point-in-time financial RAG problem. For each company-news anchor, the system retrieves related financial news and SEC filing passages, appends a pre-decision market-context card, and predicts multi-horizon residual-return signals. Our method keeps the large language model (LLM) reader frozen and adapts the retrieval layer through "},"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":"2605.31201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T12:08:58Z","cross_cats_sorted":[],"title_canon_sha256":"b51388271993b404e3ad4a3419f0120df90762de6b301c77da2f732204bbf6c8","abstract_canon_sha256":"56b78eefb513ee07c3e32111056f66bd1111a89b1d8bf9926d3220ea8e4e8aa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:03.592833Z","signature_b64":"PwM5PQwa9cpTTkglExS5pe1vAasKix0jsY/57FhOVo2OMiqjAT/9z+Iym+9joDIWOEo42JSBTDDIp2OlLuW0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4721a31556e6745f35a1e8337440aa160562917bbd207fd3956a8d225462aeb","last_reissued_at":"2026-06-01T01:04:03.592341Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:03.592341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Whom to Trust: Market-Feedback Adaptive Retrieval for Frozen LLMs in Event-Driven Financial RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Roy E. Welsch, Zijie Zhao","submitted_at":"2026-05-29T12:08:58Z","abstract_excerpt":"Financial retrieval-augmented generation (RAG) systems typically rank evidence by textual relevance, but in financial markets the useful evidence source depends on event type, forecast horizon, and market context. We study news-triggered event-impact prediction as a point-in-time financial RAG problem. For each company-news anchor, the system retrieves related financial news and SEC filing passages, appends a pre-decision market-context card, and predicts multi-horizon residual-return signals. Our method keeps the large language model (LLM) reader frozen and adapts the retrieval layer through "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31201","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/2605.31201/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":"2605.31201","created_at":"2026-06-01T01:04:03.592415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31201v1","created_at":"2026-06-01T01:04:03.592415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31201","created_at":"2026-06-01T01:04:03.592415+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRZBUMKVNZTU","created_at":"2026-06-01T01:04:03.592415+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRZBUMKVNZTUL422","created_at":"2026-06-01T01:04:03.592415+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRZBUMKV","created_at":"2026-06-01T01:04:03.592415+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/WRZBUMKVNZTUL422D2BTORAKUF","json":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF.json","graph_json":"https://pith.science/api/pith-number/WRZBUMKVNZTUL422D2BTORAKUF/graph.json","events_json":"https://pith.science/api/pith-number/WRZBUMKVNZTUL422D2BTORAKUF/events.json","paper":"https://pith.science/paper/WRZBUMKV"},"agent_actions":{"view_html":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF","download_json":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF.json","view_paper":"https://pith.science/paper/WRZBUMKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31201&json=true","fetch_graph":"https://pith.science/api/pith-number/WRZBUMKVNZTUL422D2BTORAKUF/graph.json","fetch_events":"https://pith.science/api/pith-number/WRZBUMKVNZTUL422D2BTORAKUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF/action/storage_attestation","attest_author":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF/action/author_attestation","sign_citation":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF/action/citation_signature","submit_replication":"https://pith.science/pith/WRZBUMKVNZTUL422D2BTORAKUF/action/replication_record"}},"created_at":"2026-06-01T01:04:03.592415+00:00","updated_at":"2026-06-01T01:04:03.592415+00:00"}