{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BHYAW3OZMWYWDLIXWYI73YNTJ5","short_pith_number":"pith:BHYAW3OZ","schema_version":"1.0","canonical_sha256":"09f00b6dd965b161ad17b611fde1b34f51e619d7bc45f36029f692838ff5ed4b","source":{"kind":"arxiv","id":"2506.13066","version":1},"attestation_state":"computed","paper":{"title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changjun Jiang, Dawei Cheng, Guang Chen, Jiangtong Li, Jiayong Zhu, Kai Lan","submitted_at":"2025-06-16T03:19:31Z","abstract_excerpt":"Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However, financial applications face challenges due to the lack of high-quality multimodal reasoning datasets and the inefficiency of existing training paradigms for reasoning enhancement. To address these issues, we propose an integrated framework, FinLMM-R1, combining an automated and scalable pipeline for data construction with enhanced training strategies to improve the multimodal reasoning of LMM. The Automated and Scalable Pipeline (ASP) resolves textual-visual misalignment in financial reports thr"},"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":"2506.13066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T03:19:31Z","cross_cats_sorted":[],"title_canon_sha256":"f4676562493d2a58808d46640a421feef6e9ccfffc7cd53d541557456726ff09","abstract_canon_sha256":"47c62c3fc346d2ab3b2a86cc589f7081625872fdbfe9ca84068c82753b9b6ac6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:04.598288Z","signature_b64":"oXars3oS+eSwbCpW0W+Korhb/dzHzKwS7bqqXgGzSl/tKNApwmtcgTSGM/CBPrrsBJcMi0HNcGX86qe2kBePCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09f00b6dd965b161ad17b611fde1b34f51e619d7bc45f36029f692838ff5ed4b","last_reissued_at":"2026-07-05T11:22:04.597858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:04.597858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changjun Jiang, Dawei Cheng, Guang Chen, Jiangtong Li, Jiayong Zhu, Kai Lan","submitted_at":"2025-06-16T03:19:31Z","abstract_excerpt":"Large Multimodal Models (LMMs) demonstrate significant cross-modal reasoning capabilities. However, financial applications face challenges due to the lack of high-quality multimodal reasoning datasets and the inefficiency of existing training paradigms for reasoning enhancement. To address these issues, we propose an integrated framework, FinLMM-R1, combining an automated and scalable pipeline for data construction with enhanced training strategies to improve the multimodal reasoning of LMM. The Automated and Scalable Pipeline (ASP) resolves textual-visual misalignment in financial reports thr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13066","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/2506.13066/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":"2506.13066","created_at":"2026-07-05T11:22:04.597917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13066v1","created_at":"2026-07-05T11:22:04.597917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13066","created_at":"2026-07-05T11:22:04.597917+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHYAW3OZMWYW","created_at":"2026-07-05T11:22:04.597917+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHYAW3OZMWYWDLIX","created_at":"2026-07-05T11:22:04.597917+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHYAW3OZ","created_at":"2026-07-05T11:22:04.597917+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/BHYAW3OZMWYWDLIXWYI73YNTJ5","json":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5.json","graph_json":"https://pith.science/api/pith-number/BHYAW3OZMWYWDLIXWYI73YNTJ5/graph.json","events_json":"https://pith.science/api/pith-number/BHYAW3OZMWYWDLIXWYI73YNTJ5/events.json","paper":"https://pith.science/paper/BHYAW3OZ"},"agent_actions":{"view_html":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5","download_json":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5.json","view_paper":"https://pith.science/paper/BHYAW3OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13066&json=true","fetch_graph":"https://pith.science/api/pith-number/BHYAW3OZMWYWDLIXWYI73YNTJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/BHYAW3OZMWYWDLIXWYI73YNTJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5/action/storage_attestation","attest_author":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5/action/author_attestation","sign_citation":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5/action/citation_signature","submit_replication":"https://pith.science/pith/BHYAW3OZMWYWDLIXWYI73YNTJ5/action/replication_record"}},"created_at":"2026-07-05T11:22:04.597917+00:00","updated_at":"2026-07-05T11:22:04.597917+00:00"}