{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O2D2YQE25SLMLFFFNYOYDGL777","short_pith_number":"pith:O2D2YQE2","schema_version":"1.0","canonical_sha256":"7687ac409aec96c594a56e1d81997fffe0d57cd5c0dca0b08010dea7c1292d37","source":{"kind":"arxiv","id":"2211.00083","version":1},"attestation_state":"computed","paper":{"title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Agam Shah, Charese Smiley, Dheeraj Eidnani, Diyi Yang, Jiaao Chen, Kunal Chawla, Natraj Raman, Raj Sanjay Shah, Sudheer Chava, Wendi Du","submitted_at":"2022-10-31T18:35:18Z","abstract_excerpt":"Pre-trained language models have shown impressive performance on a variety of tasks and domains. Previous research on financial language models usually employs a generic training scheme to train standard model architectures, without completely leveraging the richness of the financial data. We propose a novel domain specific Financial LANGuage model (FLANG) which uses financial keywords and phrases for better masking, together with span boundary objective and in-filing objective. Additionally, the evaluation benchmarks in the field have been limited. To this end, we contribute the Financial Lan"},"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":"2211.00083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T18:35:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6fe4972f7feb40df40a6d149256a2adf56157e5046d9010d34ccc1f7818ab8f4","abstract_canon_sha256":"5be367dff71d8452b08adfff68d0296c4b2e73acefa7e9c18de480d6ce827b6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:18.270186Z","signature_b64":"FIfMCx5c7Hyfqy3urIGQMKY2uMEmVJdsdxiO5cD5p42KxtJbp76M1SL2U0NGX0FV6Dc5d8c1K6szcgYpe/GtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7687ac409aec96c594a56e1d81997fffe0d57cd5c0dca0b08010dea7c1292d37","last_reissued_at":"2026-07-05T05:12:18.269772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:18.269772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Agam Shah, Charese Smiley, Dheeraj Eidnani, Diyi Yang, Jiaao Chen, Kunal Chawla, Natraj Raman, Raj Sanjay Shah, Sudheer Chava, Wendi Du","submitted_at":"2022-10-31T18:35:18Z","abstract_excerpt":"Pre-trained language models have shown impressive performance on a variety of tasks and domains. Previous research on financial language models usually employs a generic training scheme to train standard model architectures, without completely leveraging the richness of the financial data. We propose a novel domain specific Financial LANGuage model (FLANG) which uses financial keywords and phrases for better masking, together with span boundary objective and in-filing objective. Additionally, the evaluation benchmarks in the field have been limited. To this end, we contribute the Financial Lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00083","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/2211.00083/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":"2211.00083","created_at":"2026-07-05T05:12:18.269829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00083v1","created_at":"2026-07-05T05:12:18.269829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00083","created_at":"2026-07-05T05:12:18.269829+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2D2YQE25SLM","created_at":"2026-07-05T05:12:18.269829+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2D2YQE25SLMLFFF","created_at":"2026-07-05T05:12:18.269829+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2D2YQE2","created_at":"2026-07-05T05:12:18.269829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08051","citing_title":"How Small Can You Go? LoRA Fine-Tuning 270M-8B Models for Merchant Information Extraction in Financial Transactions","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28714","citing_title":"IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29462","citing_title":"Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation Dataset","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02429","citing_title":"MulFSA: Multi-level Financial Sentiment Analysis Framework for Bond Market","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09106","citing_title":"Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18272","citing_title":"MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777","json":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777.json","graph_json":"https://pith.science/api/pith-number/O2D2YQE25SLMLFFFNYOYDGL777/graph.json","events_json":"https://pith.science/api/pith-number/O2D2YQE25SLMLFFFNYOYDGL777/events.json","paper":"https://pith.science/paper/O2D2YQE2"},"agent_actions":{"view_html":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777","download_json":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777.json","view_paper":"https://pith.science/paper/O2D2YQE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00083&json=true","fetch_graph":"https://pith.science/api/pith-number/O2D2YQE25SLMLFFFNYOYDGL777/graph.json","fetch_events":"https://pith.science/api/pith-number/O2D2YQE25SLMLFFFNYOYDGL777/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777/action/storage_attestation","attest_author":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777/action/author_attestation","sign_citation":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777/action/citation_signature","submit_replication":"https://pith.science/pith/O2D2YQE25SLMLFFFNYOYDGL777/action/replication_record"}},"created_at":"2026-07-05T05:12:18.269829+00:00","updated_at":"2026-07-05T05:12:18.269829+00:00"}