{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TAA6E7KMFUR6CUPHV5J4QPU4QG","short_pith_number":"pith:TAA6E7KM","schema_version":"1.0","canonical_sha256":"9801e27d4c2d23e151e7af53c83e9c81873f4f462afffae2f08cf936ced74ae4","source":{"kind":"arxiv","id":"2302.11157","version":2},"attestation_state":"computed","paper":{"title":"FiNER-ORD: Financial Named Entity Recognition Open Research Dataset","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Abhinav Gullapalli, Agam Shah, Michael Galarnyk, Ruchit Vithani, Sudheer Chava","submitted_at":"2023-02-22T05:41:27Z","abstract_excerpt":"Over the last two decades, the development of the CoNLL-2003 named entity recognition (NER) dataset has helped enhance the capabilities of deep learning and natural language processing (NLP). The finance domain, characterized by its unique semantic and lexical variations for the same entities, presents specific challenges to the NER task; thus, a domain-specific customized dataset is crucial for advancing research in this field. In our work, we develop the first high-quality English Financial NER Open Research Dataset (FiNER-ORD). We benchmark multiple pre-trained language models (PLMs) and la"},"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":"2302.11157","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-22T05:41:27Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c083d0c04cdb4fb5a01046c89be610b5db7cf6a86fa5c3c210d889752e811fd8","abstract_canon_sha256":"282bb2fecaa49b7b80ac5e4c9d8e591911d9c2f9dad5bb370be25df27be31e8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:06.933937Z","signature_b64":"jUhDsGHzRnEWEaE8qkbUx8e0+enqU96N3+rOskJoYU+usSAJggOdRHIrVb3LRrtaptl0obIsLzo/8uBBKYuiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9801e27d4c2d23e151e7af53c83e9c81873f4f462afffae2f08cf936ced74ae4","last_reissued_at":"2026-07-05T09:04:06.933508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:06.933508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FiNER-ORD: Financial Named Entity Recognition Open Research Dataset","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Abhinav Gullapalli, Agam Shah, Michael Galarnyk, Ruchit Vithani, Sudheer Chava","submitted_at":"2023-02-22T05:41:27Z","abstract_excerpt":"Over the last two decades, the development of the CoNLL-2003 named entity recognition (NER) dataset has helped enhance the capabilities of deep learning and natural language processing (NLP). The finance domain, characterized by its unique semantic and lexical variations for the same entities, presents specific challenges to the NER task; thus, a domain-specific customized dataset is crucial for advancing research in this field. In our work, we develop the first high-quality English Financial NER Open Research Dataset (FiNER-ORD). We benchmark multiple pre-trained language models (PLMs) and la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11157","kind":"arxiv","version":2},"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/2302.11157/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":"2302.11157","created_at":"2026-07-05T09:04:06.933564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11157v2","created_at":"2026-07-05T09:04:06.933564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11157","created_at":"2026-07-05T09:04:06.933564+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAA6E7KMFUR6","created_at":"2026-07-05T09:04:06.933564+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAA6E7KMFUR6CUPH","created_at":"2026-07-05T09:04:06.933564+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAA6E7KM","created_at":"2026-07-05T09:04:06.933564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08129","citing_title":"Cross-LLM Consistency in Inference: Evidence from Shared Interactions","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31608","citing_title":"CLExEval: A Human-in-the-Loop Framework for Qualitative Evaluation of LLM Clinical Reasoning","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20650","citing_title":"FinTagging: Benchmarking LLMs for Extracting and Structuring Financial Information","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04489","citing_title":"A Hybrid Method for Low-Resource Named Entity Recognition","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG","json":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG.json","graph_json":"https://pith.science/api/pith-number/TAA6E7KMFUR6CUPHV5J4QPU4QG/graph.json","events_json":"https://pith.science/api/pith-number/TAA6E7KMFUR6CUPHV5J4QPU4QG/events.json","paper":"https://pith.science/paper/TAA6E7KM"},"agent_actions":{"view_html":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG","download_json":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG.json","view_paper":"https://pith.science/paper/TAA6E7KM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11157&json=true","fetch_graph":"https://pith.science/api/pith-number/TAA6E7KMFUR6CUPHV5J4QPU4QG/graph.json","fetch_events":"https://pith.science/api/pith-number/TAA6E7KMFUR6CUPHV5J4QPU4QG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG/action/storage_attestation","attest_author":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG/action/author_attestation","sign_citation":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG/action/citation_signature","submit_replication":"https://pith.science/pith/TAA6E7KMFUR6CUPHV5J4QPU4QG/action/replication_record"}},"created_at":"2026-07-05T09:04:06.933564+00:00","updated_at":"2026-07-05T09:04:06.933564+00:00"}