{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V6MY3UX7VUWORZQFUEUYZTGQA6","short_pith_number":"pith:V6MY3UX7","schema_version":"1.0","canonical_sha256":"af998dd2ffad2ce8e605a1298cccd00797df6ddf8b9dd643c9b4458b46482c66","source":{"kind":"arxiv","id":"2507.06528","version":1},"attestation_state":"computed","paper":{"title":"InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hangjing Zhang, Hanqing Gao, Huisheng Wang, H. Vicky Zhao, Mingxiao Liu, Zhuoshi Pan","submitted_at":"2025-07-09T04:07:22Z","abstract_excerpt":"Aligning Large Language Models (LLMs) with investor decision-making processes under herd behavior is a critical challenge in behavioral finance, which grapples with a fundamental limitation: the scarcity of real-user data needed for Supervised Fine-Tuning (SFT). While SFT can bridge the gap between LLM outputs and human behavioral patterns, its reliance on massive authentic data imposes substantial collection costs and privacy risks. We propose InvestAlign, a novel framework that constructs high-quality SFT datasets by leveraging theoretical solutions to similar and simple optimal investment p"},"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":"2507.06528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T04:07:22Z","cross_cats_sorted":["cs.AI","cs.ET","cs.LG"],"title_canon_sha256":"9fd29b29b765aa41aceacb2651e8f2e765905b1e8f3c4d2f9349d634455fb56a","abstract_canon_sha256":"9aed5efecff2c84bb66c1a7e8368d34734eae9f7b5439fa567a3927edf614bb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:17.780674Z","signature_b64":"oy+3qZ5SiywgfAt8TswjmsJRGDofD/VniVc0be/c2lyEL1ZZ0w1bnqNm2X90nNhuCoCqvPC68W9JiVlNOwhWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af998dd2ffad2ce8e605a1298cccd00797df6ddf8b9dd643c9b4458b46482c66","last_reissued_at":"2026-07-05T11:34:17.780133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:17.780133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hangjing Zhang, Hanqing Gao, Huisheng Wang, H. Vicky Zhao, Mingxiao Liu, Zhuoshi Pan","submitted_at":"2025-07-09T04:07:22Z","abstract_excerpt":"Aligning Large Language Models (LLMs) with investor decision-making processes under herd behavior is a critical challenge in behavioral finance, which grapples with a fundamental limitation: the scarcity of real-user data needed for Supervised Fine-Tuning (SFT). While SFT can bridge the gap between LLM outputs and human behavioral patterns, its reliance on massive authentic data imposes substantial collection costs and privacy risks. We propose InvestAlign, a novel framework that constructs high-quality SFT datasets by leveraging theoretical solutions to similar and simple optimal investment p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06528","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/2507.06528/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":"2507.06528","created_at":"2026-07-05T11:34:17.780194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06528v1","created_at":"2026-07-05T11:34:17.780194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06528","created_at":"2026-07-05T11:34:17.780194+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6MY3UX7VUWO","created_at":"2026-07-05T11:34:17.780194+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6MY3UX7VUWORZQF","created_at":"2026-07-05T11:34:17.780194+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6MY3UX7","created_at":"2026-07-05T11:34:17.780194+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/V6MY3UX7VUWORZQFUEUYZTGQA6","json":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6.json","graph_json":"https://pith.science/api/pith-number/V6MY3UX7VUWORZQFUEUYZTGQA6/graph.json","events_json":"https://pith.science/api/pith-number/V6MY3UX7VUWORZQFUEUYZTGQA6/events.json","paper":"https://pith.science/paper/V6MY3UX7"},"agent_actions":{"view_html":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6","download_json":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6.json","view_paper":"https://pith.science/paper/V6MY3UX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06528&json=true","fetch_graph":"https://pith.science/api/pith-number/V6MY3UX7VUWORZQFUEUYZTGQA6/graph.json","fetch_events":"https://pith.science/api/pith-number/V6MY3UX7VUWORZQFUEUYZTGQA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6/action/storage_attestation","attest_author":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6/action/author_attestation","sign_citation":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6/action/citation_signature","submit_replication":"https://pith.science/pith/V6MY3UX7VUWORZQFUEUYZTGQA6/action/replication_record"}},"created_at":"2026-07-05T11:34:17.780194+00:00","updated_at":"2026-07-05T11:34:17.780194+00:00"}