{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:63R7DN2VF7IQ6PBDVXY2JYU7JK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bd279189055479395f8ce35e5a5af4576172286dbd13b713f45fbbefb9257e9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T13:28:31Z","title_canon_sha256":"8adc5928b591238e86711a9db759efd6cf7b308323ccd7c75d34322a95716a71"},"schema_version":"1.0","source":{"id":"2605.03742","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03742","created_at":"2026-08-11T02:23:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03742v2","created_at":"2026-08-11T02:23:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03742","created_at":"2026-08-11T02:23:59Z"},{"alias_kind":"pith_short_12","alias_value":"63R7DN2VF7IQ","created_at":"2026-08-11T02:23:59Z"},{"alias_kind":"pith_short_16","alias_value":"63R7DN2VF7IQ6PBD","created_at":"2026-08-11T02:23:59Z"},{"alias_kind":"pith_short_8","alias_value":"63R7DN2V","created_at":"2026-08-11T02:23:59Z"}],"graph_snapshots":[{"event_id":"sha256:98d05cca5d2752db5bff22dcd0154d3f02d2d260cd15de97aa6c5384410e81dc","target":"graph","created_at":"2026-08-11T02:23:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"6b66de2a5a6e37fe606131a1f27dbe62ef5042f87cc73de35ba40f54785bd05c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.03742/integrity.json","findings":[],"snapshot_sha256":"c4e28d378dded36d83236726677ca1e749897cf06c4178ab01245f8ae1efdbb3","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Mullosharaf K. Arabov","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T13:28:31Z","title":"Benchmarking Parameter-Efficient Fine-Tuning of Large Language Models for Low-Resource Tajik Text Generation with the Tajik Web Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.03742","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T16:31:03.654143Z","id":"1f1c4ca6-dd72-4b2e-96a1-35a4f05cb29f","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"1f1c4ca6-dd72-4b2e-96a1-35a4f05cb29f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eee99459f858fd952ec57967cb6539e02f2fa814a2ea319fbc10baf0b80f6a80","target":"record","created_at":"2026-08-11T02:23:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bd279189055479395f8ce35e5a5af4576172286dbd13b713f45fbbefb9257e9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-05T13:28:31Z","title_canon_sha256":"8adc5928b591238e86711a9db759efd6cf7b308323ccd7c75d34322a95716a71"},"schema_version":"1.0","source":{"id":"2605.03742","kind":"arxiv","version":2}},"canonical_sha256":"f6e3f1b7552fd10f3c23adf1a4e29f4a9951ce897780fc43a72fe01a22098aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6e3f1b7552fd10f3c23adf1a4e29f4a9951ce897780fc43a72fe01a22098aa2","first_computed_at":"2026-08-11T02:23:59.697059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:23:59.697059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WjkKY38AWWvj1nF0smOiVPnY/86uHDKee2nA6rv3+fZtPXwOplViNz6lEmKgvP8D+9k5ct+hPb2EUe/qGc0ABQ==","signature_status":"signed_v1","signed_at":"2026-08-11T02:23:59.699067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.03742","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eee99459f858fd952ec57967cb6539e02f2fa814a2ea319fbc10baf0b80f6a80","sha256:98d05cca5d2752db5bff22dcd0154d3f02d2d260cd15de97aa6c5384410e81dc"],"state_sha256":"1f9d5fc5f555eb0d25bb1404c9e6f1a74915b1343d43779ce8ec02b27b18330c"}