{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2HT4RRCEBV2AMCO6GY52LXSGT4","short_pith_number":"pith:2HT4RRCE","schema_version":"1.0","canonical_sha256":"d1e7c8c4440d740609de363ba5de469f2484fd07f615b89d14da7f841798519e","source":{"kind":"arxiv","id":"2409.09659","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Open-Source Large Language Models for Native Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilia Markov, Yee Man Ng","submitted_at":"2024-09-15T08:14:18Z","abstract_excerpt":"Native Language Identification (NLI) - the task of identifying the native language (L1) of a person based on their writing in the second language (L2) - has applications in forensics, marketing, and second language acquisition. Historically, conventional machine learning approaches that heavily rely on extensive feature engineering have outperformed transformer-based language models on this task. Recently, closed-source generative large language models (LLMs), e.g., GPT-4, have demonstrated remarkable performance on NLI in a zero-shot setting, including promising results in open-set classifica"},"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":"2409.09659","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-15T08:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"790fc67983a795057af40f4fffcff7dbe0379ce50d6e9475886d64c604f80675","abstract_canon_sha256":"7b223e8957166893c782d1ead98db077f5e8fc156628d68aad3b6c8572bc9f44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:51.665054Z","signature_b64":"95tkt0PXxa1F+JqCXt//+kApzGlUrYq28bV5WrPLcYEC4MLIif95jj2jUmyp66AKPueojQhGGBmrzM7c90CbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1e7c8c4440d740609de363ba5de469f2484fd07f615b89d14da7f841798519e","last_reissued_at":"2026-07-05T10:02:51.664619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:51.664619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Open-Source Large Language Models for Native Language Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilia Markov, Yee Man Ng","submitted_at":"2024-09-15T08:14:18Z","abstract_excerpt":"Native Language Identification (NLI) - the task of identifying the native language (L1) of a person based on their writing in the second language (L2) - has applications in forensics, marketing, and second language acquisition. Historically, conventional machine learning approaches that heavily rely on extensive feature engineering have outperformed transformer-based language models on this task. Recently, closed-source generative large language models (LLMs), e.g., GPT-4, have demonstrated remarkable performance on NLI in a zero-shot setting, including promising results in open-set classifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09659","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/2409.09659/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":"2409.09659","created_at":"2026-07-05T10:02:51.664683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09659v2","created_at":"2026-07-05T10:02:51.664683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09659","created_at":"2026-07-05T10:02:51.664683+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HT4RRCEBV2A","created_at":"2026-07-05T10:02:51.664683+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HT4RRCEBV2AMCO6","created_at":"2026-07-05T10:02:51.664683+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HT4RRCE","created_at":"2026-07-05T10:02:51.664683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11811","citing_title":"BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4","json":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4.json","graph_json":"https://pith.science/api/pith-number/2HT4RRCEBV2AMCO6GY52LXSGT4/graph.json","events_json":"https://pith.science/api/pith-number/2HT4RRCEBV2AMCO6GY52LXSGT4/events.json","paper":"https://pith.science/paper/2HT4RRCE"},"agent_actions":{"view_html":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4","download_json":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4.json","view_paper":"https://pith.science/paper/2HT4RRCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09659&json=true","fetch_graph":"https://pith.science/api/pith-number/2HT4RRCEBV2AMCO6GY52LXSGT4/graph.json","fetch_events":"https://pith.science/api/pith-number/2HT4RRCEBV2AMCO6GY52LXSGT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4/action/storage_attestation","attest_author":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4/action/author_attestation","sign_citation":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4/action/citation_signature","submit_replication":"https://pith.science/pith/2HT4RRCEBV2AMCO6GY52LXSGT4/action/replication_record"}},"created_at":"2026-07-05T10:02:51.664683+00:00","updated_at":"2026-07-05T10:02:51.664683+00:00"}