{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DIPAGTSNNIOQKZN5CXDIWIMYVA","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":"674af5c23111db99dee0bcf8d1d5f116684a4b690486ecdf3306cdd91ca3be5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-06T07:32:35Z","title_canon_sha256":"0ac9c224bb6b1393b255409ed84af5aa0d03f5051b13b9705cd790402f7ca393"},"schema_version":"1.0","source":{"id":"2605.04583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04583","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04583v2","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04583","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"DIPAGTSNNIOQ","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"DIPAGTSNNIOQKZN5","created_at":"2026-05-29T02:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"DIPAGTSN","created_at":"2026-05-29T02:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:c401e920cc5d56ebef817d7b6d160d82785456dbae04c2b6707fb0fc324402e9","target":"graph","created_at":"2026-05-29T02:05:45Z","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":"TajikNLP thus establishes a foundational technological infrastructure for Tajik language processing, lowering the barrier to entry for both academic and industrial applications in low-resource Cyrillic-script environments."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The novel unified morphology engine with controlled and deep analysis modes significantly improves handling of Tajik's agglutinative nominal and verbal inflections, as claimed without reported accuracy metrics or comparisons in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TajikNLP delivers the first comprehensive open-source NLP toolkit for Tajik Cyrillic text with a unified morphology engine, standard components, sentiment analysis, embeddings, and four supporting linguistic datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TajikNLP provides the first comprehensive open-source toolkit for processing Tajik text in its original Cyrillic script."}],"snapshot_sha256":"a9d9d88d49afda15894183bb89d73cbb8b6e6cc0867d3325398b7d94c6c66639"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T11:39:28.463470Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:20.061602Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T14:19:18.687968Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.04583/integrity.json","findings":[],"snapshot_sha256":"6ceab80651805d684f6414a54c2af5b55a32c23b84d2be9c78b4e769f91100a1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Tajik language, written in Cyrillic script, remains severely under-resourced in terms of publicly available natural language processing (NLP) toolkits, hindering both linguistic research and applied development. This paper introduces TajikNLP, an open-source Python library that provides the first comprehensive pipeline for processing authentic Tajik text while preserving the original Cyrillic orthography. The library implements a modular architecture centered around a unified Doc object, enabling sequential application of components for cleaning, normalization, tokenization (including subw","authors_text":"Mullosharaf K. Arabov","cross_cats":[],"headline":"TajikNLP provides the first comprehensive open-source toolkit for processing Tajik text in its original Cyrillic script.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-06T07:32:35Z","title":"TajikNLP: An Open-Source Toolkit for Comprehensive Text Processing of Tajik (Cyrillic Script)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.04583","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T16:25:22.420585Z","id":"f341a505-9a66-4b1a-97ff-509c6af17b44","model_set":{"reader":"grok-4.3"},"one_line_summary":"TajikNLP delivers the first comprehensive open-source NLP toolkit for Tajik Cyrillic text with a unified morphology engine, standard components, sentiment analysis, embeddings, and four supporting linguistic datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"TajikNLP provides the first comprehensive open-source toolkit for processing Tajik text in its original Cyrillic script.","strongest_claim":"TajikNLP thus establishes a foundational technological infrastructure for Tajik language processing, lowering the barrier to entry for both academic and industrial applications in low-resource Cyrillic-script environments.","weakest_assumption":"The novel unified morphology engine with controlled and deep analysis modes significantly improves handling of Tajik's agglutinative nominal and verbal inflections, as claimed without reported accuracy metrics or comparisons in the abstract."}},"verdict_id":"f341a505-9a66-4b1a-97ff-509c6af17b44"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f1c7662f987408b6a80832146da605c7ed1ea299b8153c8f6af6bd4f1434a54c","target":"record","created_at":"2026-05-29T02:05:45Z","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":"674af5c23111db99dee0bcf8d1d5f116684a4b690486ecdf3306cdd91ca3be5e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-06T07:32:35Z","title_canon_sha256":"0ac9c224bb6b1393b255409ed84af5aa0d03f5051b13b9705cd790402f7ca393"},"schema_version":"1.0","source":{"id":"2605.04583","kind":"arxiv","version":2}},"canonical_sha256":"1a1e034e4d6a1d0565bd15c68b2198a83edf8ec6b27df79b69f146143a823b6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a1e034e4d6a1d0565bd15c68b2198a83edf8ec6b27df79b69f146143a823b6c","first_computed_at":"2026-05-29T02:05:45.933100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:45.933100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ggFPcgukBzdy9XdDnBcvjOZoikfIDJNZZbzoiK43cNYUW1czzMn0Ubp7EZ4aQM8QgnwYZxPaA88PI/xuTqYnDw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:45.933821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.04583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1c7662f987408b6a80832146da605c7ed1ea299b8153c8f6af6bd4f1434a54c","sha256:c401e920cc5d56ebef817d7b6d160d82785456dbae04c2b6707fb0fc324402e9"],"state_sha256":"650ac7462573a746cce768bc7fdd60ef8894938931661f054b537bec6c4eec6a"}