{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:63R7DN2VF7IQ6PBDVXY2JYU7JK","short_pith_number":"pith:63R7DN2V","schema_version":"1.0","canonical_sha256":"f6e3f1b7552fd10f3c23adf1a4e29f4a9951ce897780fc43a72fe01a22098aa2","source":{"kind":"arxiv","id":"2605.03742","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Parameter-Efficient Fine-Tuning of Large Language Models for Low-Resource Tajik Text Generation with the Tajik Web Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Mistral 7B with QLoRA rank 16 reaches mean perplexity 5.03 on Tajik text generation after release of the largest open Tajik web corpus.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mullosharaf K. Arabov","submitted_at":"2026-05-05T13:28:31Z","abstract_excerpt":"We release the Tajik Web Corpus (319k docs, 1.11B chars) and benchmark generative LLMs on prompt continuation in Tajik, a low-resource Cyrillic-script language. Seventeen configurations across nine architectures are evaluated under three fine-tuning strategies: full fine-tuning, LoRA, and QLoRA (ranks 8 and 16). Because perplexity is not directly comparable across model families with different tokenizers, generation quality is assessed through perplexity interpreted within each family, complemented by qualitative analysis performed by a native Tajik speaker. Computational cost is measured via "},"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":"2605.03742","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T13:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"8adc5928b591238e86711a9db759efd6cf7b308323ccd7c75d34322a95716a71","abstract_canon_sha256":"bd279189055479395f8ce35e5a5af4576172286dbd13b713f45fbbefb9257e9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:23:59.699067Z","signature_b64":"WjkKY38AWWvj1nF0smOiVPnY/86uHDKee2nA6rv3+fZtPXwOplViNz6lEmKgvP8D+9k5ct+hPb2EUe/qGc0ABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6e3f1b7552fd10f3c23adf1a4e29f4a9951ce897780fc43a72fe01a22098aa2","last_reissued_at":"2026-08-11T02:23:59.697059Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:23:59.697059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Parameter-Efficient Fine-Tuning of Large Language Models for Low-Resource Tajik Text Generation with the Tajik Web Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Mistral 7B with QLoRA rank 16 reaches mean perplexity 5.03 on Tajik text generation after release of the largest open Tajik web corpus.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mullosharaf K. Arabov","submitted_at":"2026-05-05T13:28:31Z","abstract_excerpt":"We release the Tajik Web Corpus (319k docs, 1.11B chars) and benchmark generative LLMs on prompt continuation in Tajik, a low-resource Cyrillic-script language. Seventeen configurations across nine architectures are evaluated under three fine-tuning strategies: full fine-tuning, LoRA, and QLoRA (ranks 8 and 16). Because perplexity is not directly comparable across model families with different tokenizers, generation quality is assessed through perplexity interpreted within each family, complemented by qualitative analysis performed by a native Tajik speaker. Computational cost is measured via "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Best results were achieved by Mistral 7B with QLoRA (r=16): mean perplexity 5.03, standard deviation 0.03. The novelty lies in creating the largest verified Tajik corpus and the first systematic analysis of PEFT effectiveness for Tajik text generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a random 10,000-document subsample from the web corpus is representative of Tajik text distribution and that perplexity alone sufficiently captures generation quality without human evaluation or downstream task metrics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Releases Tajik Web Corpus (~1.11B characters) and finds Mistral 7B with QLoRA rank 16 yields lowest perplexity of 5.03 for Tajik generation while full fine-tuning on small models causes forgetting.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mistral 7B with QLoRA rank 16 reaches mean perplexity 5.03 on Tajik text generation after release of the largest open Tajik web corpus.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6b66de2a5a6e37fe606131a1f27dbe62ef5042f87cc73de35ba40f54785bd05c"},"source":{"id":"2605.03742","kind":"arxiv","version":2},"verdict":{"id":"1f1c4ca6-dd72-4b2e-96a1-35a4f05cb29f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T16:31:03.654143Z","strongest_claim":"Best results were achieved by Mistral 7B with QLoRA (r=16): mean perplexity 5.03, standard deviation 0.03. The novelty lies in creating the largest verified Tajik corpus and the first systematic analysis of PEFT effectiveness for Tajik text generation.","one_line_summary":"Releases Tajik Web Corpus (~1.11B characters) and finds Mistral 7B with QLoRA rank 16 yields lowest perplexity of 5.03 for Tajik generation while full fine-tuning on small models causes forgetting.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a random 10,000-document subsample from the web corpus is representative of Tajik text distribution and that perplexity alone sufficiently captures generation quality without human evaluation or downstream task metrics.","pith_extraction_headline":"Mistral 7B with QLoRA rank 16 reaches mean perplexity 5.03 on Tajik text generation after release of the largest open Tajik web corpus."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03742/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T13:35:06.129330Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T00:31:21.265357Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:03:40.914349Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c4e28d378dded36d83236726677ca1e749897cf06c4178ab01245f8ae1efdbb3"},"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":"2605.03742","created_at":"2026-08-11T02:23:59.697734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.03742v2","created_at":"2026-08-11T02:23:59.697734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03742","created_at":"2026-08-11T02:23:59.697734+00:00"},{"alias_kind":"pith_short_12","alias_value":"63R7DN2VF7IQ","created_at":"2026-08-11T02:23:59.697734+00:00"},{"alias_kind":"pith_short_16","alias_value":"63R7DN2VF7IQ6PBD","created_at":"2026-08-11T02:23:59.697734+00:00"},{"alias_kind":"pith_short_8","alias_value":"63R7DN2V","created_at":"2026-08-11T02:23:59.697734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04186","citing_title":"Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK","json":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK.json","graph_json":"https://pith.science/api/pith-number/63R7DN2VF7IQ6PBDVXY2JYU7JK/graph.json","events_json":"https://pith.science/api/pith-number/63R7DN2VF7IQ6PBDVXY2JYU7JK/events.json","paper":"https://pith.science/paper/63R7DN2V"},"agent_actions":{"view_html":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK","download_json":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK.json","view_paper":"https://pith.science/paper/63R7DN2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.03742&json=true","fetch_graph":"https://pith.science/api/pith-number/63R7DN2VF7IQ6PBDVXY2JYU7JK/graph.json","fetch_events":"https://pith.science/api/pith-number/63R7DN2VF7IQ6PBDVXY2JYU7JK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK/action/storage_attestation","attest_author":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK/action/author_attestation","sign_citation":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK/action/citation_signature","submit_replication":"https://pith.science/pith/63R7DN2VF7IQ6PBDVXY2JYU7JK/action/replication_record"}},"created_at":"2026-08-11T02:23:59.697734+00:00","updated_at":"2026-08-11T02:23:59.697734+00:00"}