docs/search/resources.json

{
  "generated_on": "2026-02-22T00:00:00Z",
  "count": 225,
  "resources": [
    {
      "id": "dataset-common-voice-ps-v24",
      "title": "Common Voice Scripted Speech 24.0 - Pashto",
      "url": "https://datacollective.mozillafoundation.org/datasets/cmj8u3pnb00llnxxbfvxo3b14",
      "category": "dataset",
      "source": "mozilla",
      "status": "verified",
      "summary": "Large open Pashto speech dataset for ASR training and evaluation.",
      "primary_use": "ASR training and evaluation",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "speech",
        "asr"
      ],
      "evidence_text": "Official dataset page is for Pashto.",
      "evidence_url": "https://datacollective.mozillafoundation.org/datasets/cmj8u3pnb00llnxxbfvxo3b14",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "dataset-google-fleurs",
      "title": "Google FLEURS",
      "url": "https://huggingface.co/datasets/google/fleurs",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Standard multilingual speech benchmark dataset with Pashto subset.",
      "primary_use": "Speech benchmark and external evaluation",
      "tasks": [
        "asr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "speech",
        "benchmark"
      ],
      "evidence_text": "Dataset config includes ps_af.",
      "evidence_url": "https://huggingface.co/datasets/google/fleurs/blob/main/fleurs.py",
      "markers": [
        "ps_af"
      ]
    },
    {
      "id": "dataset-oscar-ps",
      "title": "OSCAR Corpus",
      "url": "https://huggingface.co/datasets/oscar-corpus/oscar",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Large web text corpus that includes Pashto text split.",
      "primary_use": "Language modeling and lexicon expansion",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "text",
        "nlp"
      ],
      "evidence_text": "Dataset includes unshuffled_deduplicated_ps split.",
      "evidence_url": "https://huggingface.co/datasets/oscar-corpus/oscar",
      "markers": [
        "unshuffled_deduplicated_ps"
      ]
    },
    {
      "id": "dataset-wikipedia-ps",
      "title": "Wikimedia Wikipedia",
      "url": "https://huggingface.co/datasets/wikimedia/wikipedia",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Wikipedia corpus with Pashto edition for cleaner text resources.",
      "primary_use": "Terminology and balanced text corpus",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "text",
        "nlp"
      ],
      "evidence_text": "Dataset includes 20231101.ps subset.",
      "evidence_url": "https://huggingface.co/datasets/wikimedia/wikipedia",
      "markers": [
        "20231101.ps"
      ]
    },
    {
      "id": "dataset-belebele-pbt-arab",
      "title": "Belebele",
      "url": "https://huggingface.co/datasets/facebook/belebele",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Reading comprehension dataset with Pashto script subset.",
      "primary_use": "Comprehension and multilingual NLP benchmark",
      "tasks": [
        "nlp",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "nlp",
        "benchmark"
      ],
      "evidence_text": "Dataset includes pbt_Arab subset.",
      "evidence_url": "https://huggingface.co/datasets/facebook/belebele",
      "markers": [
        "pbt_Arab"
      ]
    },
    {
      "id": "dataset-opus100-en-ps",
      "title": "OPUS-100",
      "url": "https://huggingface.co/datasets/Helsinki-NLP/opus-100",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Parallel corpus with English to Pashto split for MT tasks.",
      "primary_use": "Machine translation training and evaluation",
      "tasks": [
        "mt",
        "nlp"
      ],
      "tags": [
        "pashto",
        "mt",
        "parallel-corpus"
      ],
      "evidence_text": "Dataset viewer includes en-ps split.",
      "evidence_url": "https://huggingface.co/datasets/Helsinki-NLP/opus-100/viewer/en-ps",
      "markers": [
        "en-ps"
      ]
    },
    {
      "id": "model-pashto-bert",
      "title": "PashtoBERT",
      "url": "https://huggingface.co/mdarhri/pashto-bert",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-specific encoder model for NLP transfer tasks.",
      "primary_use": "Pashto NLP baseline encoder",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "nlp",
        "bert"
      ],
      "evidence_text": "Model card states training on Pashto corpus data.",
      "evidence_url": "https://huggingface.co/mdarhri/pashto-bert",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "benchmark-fleurs-ps-af",
      "title": "FLEURS Pashto Benchmark",
      "url": "https://huggingface.co/datasets/google/fleurs",
      "category": "benchmark",
      "source": "huggingface",
      "status": "verified",
      "summary": "Fixed multilingual speech benchmark with Pashto subset for WER and CER.",
      "primary_use": "ASR benchmark reporting",
      "tasks": [
        "asr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "benchmark",
        "asr"
      ],
      "evidence_text": "Dataset includes ps_af split.",
      "evidence_url": "https://huggingface.co/datasets/google/fleurs/blob/main/fleurs.py",
      "markers": [
        "ps_af"
      ]
    },
    {
      "id": "benchmark-common-voice-ps-v24",
      "title": "Common Voice Pashto v24 Benchmark",
      "url": "https://datacollective.mozillafoundation.org/datasets/cmj8u3pnb00llnxxbfvxo3b14",
      "category": "benchmark",
      "source": "mozilla",
      "status": "verified",
      "summary": "Core benchmark reference for project-level Pashto ASR tracking.",
      "primary_use": "ASR baseline tracking",
      "tasks": [
        "asr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "benchmark",
        "asr"
      ],
      "evidence_text": "Official Pashto split and versioned release.",
      "evidence_url": "https://datacollective.mozillafoundation.org/datasets/cmj8u3pnb00llnxxbfvxo3b14",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "benchmark-belebele-pbt-arab",
      "title": "Belebele Pashto Benchmark",
      "url": "https://huggingface.co/datasets/facebook/belebele",
      "category": "benchmark",
      "source": "huggingface",
      "status": "verified",
      "summary": "Comprehension benchmark for multilingual NLP with Pashto variant.",
      "primary_use": "NLP benchmark reporting",
      "tasks": [
        "nlp",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "benchmark",
        "nlp"
      ],
      "evidence_text": "Includes pbt_Arab language variant.",
      "evidence_url": "https://huggingface.co/datasets/facebook/belebele",
      "markers": [
        "pbt_Arab"
      ]
    },
    {
      "id": "benchmark-flores-200-pbt-arab",
      "title": "FLORES-200 Pashto Benchmark",
      "url": "https://github.com/facebookresearch/flores/tree/main/flores200",
      "category": "benchmark",
      "source": "github",
      "status": "verified",
      "summary": "Translation benchmark language inventory including Pashto script variant.",
      "primary_use": "MT benchmark with BLEU and chrF",
      "tasks": [
        "mt",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "benchmark",
        "mt"
      ],
      "evidence_text": "Language list includes pbt_Arab.",
      "evidence_url": "https://raw.githubusercontent.com/facebookresearch/flores/main/flores200/README.md",
      "markers": [
        "pbt_Arab"
      ]
    },
    {
      "id": "dataset-nexdata-99h-pashto-dialogue",
      "title": "99 Hours Pashto Spontaneous Dialogue Smartphone Speech Dataset",
      "url": "https://huggingface.co/datasets/Nexdata/99_Hours_Pashto_Spontaneous_Dialogue_Smartphone_speech_dataset",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Large spontaneous Pashto smartphone speech dataset for robust ASR experimentation.",
      "primary_use": "Spontaneous speech ASR training and robustness evaluation",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "speech",
        "asr",
        "dialogue"
      ],
      "evidence_text": "Dataset title explicitly includes Pashto and API metadata marks audio and text modalities.",
      "evidence_url": "https://huggingface.co/datasets/Nexdata/99_Hours_Pashto_Spontaneous_Dialogue_Smartphone_speech_dataset",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "dataset-zirak-ai-pashto-ocr",
      "title": "Zirak-AI PashtoOCR",
      "url": "https://huggingface.co/datasets/zirak-ai/PashtoOCR",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused OCR dataset with image-text pairs for document understanding tasks.",
      "primary_use": "OCR and text extraction benchmarking",
      "tasks": [
        "ocr",
        "nlp"
      ],
      "tags": [
        "pashto",
        "ocr",
        "nlp",
        "vision"
      ],
      "evidence_text": "Dataset tags include language:ps and the dataset name is PashtoOCR.",
      "evidence_url": "https://huggingface.co/datasets/zirak-ai/PashtoOCR",
      "markers": [
        "ps",
        "PashtoOCR"
      ]
    },
    {
      "id": "dataset-ihanif-pashto-wikipedia-corpus",
      "title": "Pashto Wikipedia Corpus",
      "url": "https://huggingface.co/datasets/ihanif/pashto-wikipedia-corpus",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto text corpus prepared from Wikipedia data for NLP and language modeling.",
      "primary_use": "Pashto text corpus for NLP baselines",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "text",
        "nlp",
        "wikipedia"
      ],
      "evidence_text": "Dataset metadata includes language:ps and the title specifies Pashto corpus.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto-wikipedia-corpus",
      "markers": [
        "ps",
        "Pashto"
      ]
    },
    {
      "id": "model-ihanif-wav2vec2-xls-r-300m-pashto",
      "title": "wav2vec2 XLS-R 300M Pashto",
      "url": "https://huggingface.co/ihanif/wav2vec2-xls-r-300m-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Fine-tuned wav2vec2 XLS-R model for Pashto ASR with published FLEURS evaluation tags.",
      "primary_use": "Pashto ASR baseline and comparative experiments",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "asr",
        "wav2vec2",
        "fleurs"
      ],
      "evidence_text": "Model tags include pashto and ps, and model index references FLEURS config ps_af.",
      "evidence_url": "https://huggingface.co/ihanif/wav2vec2-xls-r-300m-pashto",
      "markers": [
        "pashto",
        "ps",
        "ps_af"
      ]
    },
    {
      "id": "model-ihanif-whisper-medium-pashto",
      "title": "Whisper Medium Pashto",
      "url": "https://huggingface.co/ihanif/whisper-medium-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Fine-tuned Whisper Medium checkpoint for Pashto ASR with benchmark metadata.",
      "primary_use": "Pashto ASR baseline and transcription quality comparisons",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "asr",
        "whisper",
        "fleurs"
      ],
      "evidence_text": "Model tags include pashto and ps, and model index uses FLEURS ps_af split.",
      "evidence_url": "https://huggingface.co/ihanif/whisper-medium-pashto",
      "markers": [
        "pashto",
        "ps",
        "ps_af"
      ]
    },
    {
      "id": "project-hf-space-ihanif-pashto-asr-v3",
      "title": "Pashto ASR V3 Space",
      "url": "https://huggingface.co/spaces/ihanif/pashto-asr-v3",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Interactive Hugging Face Space for Pashto automatic speech recognition demos.",
      "primary_use": "Project demo for Pashto ASR user testing",
      "tasks": [
        "asr",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface-space",
        "asr"
      ],
      "evidence_text": "Space card title is Pashto ASR V3 and short description states Pashto ASR.",
      "evidence_url": "https://huggingface.co/api/spaces/ihanif/pashto-asr-v3",
      "markers": [
        "Pashto",
        "ASR"
      ]
    },
    {
      "id": "project-hf-space-pashto2english-dictionary",
      "title": "Pashto to English Dictionary Space",
      "url": "https://huggingface.co/spaces/EngrAamirBangash/Pashto2English-Dictionary",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Streamlit project for Pashto to English dictionary lookups.",
      "primary_use": "Interactive bilingual lookup project",
      "tasks": [
        "dictionary",
        "translation",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface-space",
        "dictionary"
      ],
      "evidence_text": "Space metadata title states Pashto to English Dictionary.",
      "evidence_url": "https://huggingface.co/api/spaces/EngrAamirBangash/Pashto2English-Dictionary",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "project-hf-space-umar4321-pashto-translator",
      "title": "Pashto Translator Space",
      "url": "https://huggingface.co/spaces/Umar4321/Pashto-Translator",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Streamlit translator project for Pashto to English and Urdu conversion.",
      "primary_use": "Interactive translation project demo",
      "tasks": [
        "translation",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface-space",
        "translation"
      ],
      "evidence_text": "Space title is Pashto Translator and description states Pashto to English and Urdu translation.",
      "evidence_url": "https://huggingface.co/api/spaces/Umar4321/Pashto-Translator",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "code-github-ijazul-haq-nlpashto",
      "title": "nlpashto Toolkit",
      "url": "https://github.com/ijazul-haq/nlpashto",
      "category": "code",
      "source": "github",
      "status": "verified",
      "summary": "Pashto NLP toolkit codebase for tokenization, embeddings, and downstream NLP workflows.",
      "primary_use": "Pashto NLP code integration and experimentation",
      "tasks": [
        "nlp",
        "tooling"
      ],
      "tags": [
        "pashto",
        "code",
        "github",
        "nlp"
      ],
      "evidence_text": "Repository name and description explicitly identify a Pashto NLP toolkit.",
      "evidence_url": "https://api.github.com/repos/ijazul-haq/nlpashto",
      "markers": [
        "Pashto",
        "NLP"
      ]
    },
    {
      "id": "model-hf-zirak-ai-pashto-bert-v1",
      "title": "zirak-ai/pashto-bert-v1",
      "url": "https://huggingface.co/zirak-ai/pashto-bert-v1",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto BERT model checkpoint for low-resource Pashto NLP experiments.",
      "primary_use": "Pashto encoder baseline for NLP tasks",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "huggingface",
        "bert",
        "nlp"
      ],
      "evidence_text": "Hugging Face model ID and search tags explicitly include pashto marker.",
      "evidence_url": "https://huggingface.co/zirak-ai/pashto-bert-v1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-ihanif-pashto-asr",
      "title": "Pashto ASR Space",
      "url": "https://huggingface.co/spaces/ihanif/pashto-asr",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Interactive Hugging Face Space for Pashto ASR inference demos.",
      "primary_use": "Live Pashto speech-to-text demo project",
      "tasks": [
        "asr",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface-space",
        "asr"
      ],
      "evidence_text": "Space ID includes pashto-asr and is returned by Hugging Face Pashto space search.",
      "evidence_url": "https://huggingface.co/api/spaces/ihanif/pashto-asr",
      "markers": [
        "pashto",
        "asr"
      ]
    },
    {
      "id": "paper-s2-psocr-lmm-pashto",
      "title": "PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language",
      "url": "https://www.semanticscholar.org/paper/d2743c0dcdbc65f5b46fcec2f0ba7cb379c4134f",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Research paper benchmarking multimodal OCR models on low-resource Pashto OCR tasks.",
      "primary_use": "Pashto OCR research baseline and evaluation reference",
      "tasks": [
        "ocr",
        "research"
      ],
      "tags": [
        "pashto",
        "paper",
        "ocr",
        "multimodal"
      ],
      "evidence_text": "Paper title explicitly references low-resource Pashto language OCR benchmarking.",
      "evidence_url": "https://www.semanticscholar.org/paper/d2743c0dcdbc65f5b46fcec2f0ba7cb379c4134f",
      "markers": [
        "Pashto",
        "OCR"
      ]
    },
    {
      "id": "dataset-hf-adnankhan769-english-to-pashto",
      "title": "English to Pashto Sentences Dataset",
      "url": "https://huggingface.co/datasets/adnankhan769/english_to_pashto_sentences_dataset",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Parallel English-Pashto sentence dataset for bilingual NLP and translation experiments.",
      "primary_use": "MT and bilingual sentence alignment baseline",
      "tasks": [
        "mt",
        "nlp"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "translation"
      ],
      "evidence_text": "Dataset ID explicitly states English-to-Pashto and includes Pashto-script sentence column.",
      "evidence_url": "https://huggingface.co/api/datasets/adnankhan769/english_to_pashto_sentences_dataset",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "dataset-hf-saillab-alpaca-pashto-cleaned",
      "title": "alpaca-pashto-cleaned",
      "url": "https://huggingface.co/datasets/saillab/alpaca-pashto-cleaned",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Instruction-style Pashto text dataset suitable for LLM tuning and instruction-following research.",
      "primary_use": "Pashto instruction tuning and conversational NLP experiments",
      "tasks": [
        "nlp",
        "llm"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "instruction"
      ],
      "evidence_text": "Dataset metadata includes language:ps and dataset name includes Pashto.",
      "evidence_url": "https://huggingface.co/api/datasets/saillab/alpaca-pashto-cleaned",
      "markers": [
        "ps",
        "Pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-whisper-base-pashto",
      "title": "Whisper Base Pashto",
      "url": "https://huggingface.co/ihanif/whisper-base-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Fine-tuned Whisper Base checkpoint for Pashto ASR with FLEURS ps_af evaluation metadata.",
      "primary_use": "Pashto ASR baseline and speed-accuracy comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Model ID includes Pashto and card metadata references FLEURS config ps_af.",
      "evidence_url": "https://huggingface.co/api/models/ihanif/whisper-base-pashto",
      "markers": [
        "Pashto",
        "ps_af"
      ]
    },
    {
      "id": "project-hf-space-zamai-mistral-7b-pashto",
      "title": "ZamAI-Mistral-7B-Pashto Space",
      "url": "https://huggingface.co/spaces/tasal9/ZamAI-Mistral-7B-Pashto-space",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Gradio project space demonstrating a Pashto-adapted Mistral 7B interface.",
      "primary_use": "Interactive Pashto LLM project demo",
      "tasks": [
        "llm",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface-space",
        "llm"
      ],
      "evidence_text": "Space title and ID explicitly include Pashto and model card metadata exposes project details.",
      "evidence_url": "https://huggingface.co/api/spaces/tasal9/ZamAI-Mistral-7B-Pashto-space",
      "markers": [
        "Pashto"
      ]
    },
    {
      "id": "dataset-hf-adnankhan769-proper-dataset-english-2-pashto",
      "title": "adnankhan769/proper_dataset_english_2_pashto",
      "url": "https://huggingface.co/datasets/adnankhan769/proper_dataset_english_2_pashto",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto bilingual/translation dataset discovered from huggingface for MT experimentation.",
      "primary_use": "Machine translation and bilingual corpus development",
      "tasks": [
        "mt"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "mt"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/adnankhan769/proper_dataset_english_2_pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-ihanif-pashto-asr-wer",
      "title": "ihanif/pashto_asr_wer",
      "url": "https://huggingface.co/datasets/ihanif/pashto_asr_wer",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto speech dataset discovered from huggingface for ASR training and evaluation.",
      "primary_use": "ASR training and evaluation data source",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto_asr_wer",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-ihanif-pashto-speech-ds",
      "title": "ihanif/pashto_speech_ds",
      "url": "https://huggingface.co/datasets/ihanif/pashto_speech_ds",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto speech dataset discovered from huggingface for ASR training and evaluation.",
      "primary_use": "ASR training and evaluation data source",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto_speech_ds",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-ihanif-pashto-speech-parquet-10k",
      "title": "ihanif/pashto_speech_parquet_10k",
      "url": "https://huggingface.co/datasets/ihanif/pashto_speech_parquet_10k",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto speech dataset discovered from huggingface for ASR training and evaluation.",
      "primary_use": "ASR training and evaluation data source",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto_speech_parquet_10k",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-saillab-alpaca-pashto-taco",
      "title": "saillab/alpaca_pashto_taco",
      "url": "https://huggingface.co/datasets/saillab/alpaca_pashto_taco",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused dataset discovered from huggingface candidate sync.",
      "primary_use": "Instruction tuning and LLM adaptation data source",
      "tasks": [
        "llm"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "llm"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/saillab/alpaca_pashto_taco",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-sherwindesouza-pashto-common-voice-20",
      "title": "SherwinDesouza/pashto-common-voice-20",
      "url": "https://huggingface.co/datasets/SherwinDesouza/pashto-common-voice-20",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused dataset discovered from huggingface candidate sync.",
      "primary_use": "Pashto data source for NLP experimentation",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "nlp"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/SherwinDesouza/pashto-common-voice-20",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-tasal9-zamai-pashto-dataset",
      "title": "tasal9/ZamAI_Pashto_Dataset",
      "url": "https://huggingface.co/datasets/tasal9/ZamAI_Pashto_Dataset",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused dataset discovered from huggingface candidate sync.",
      "primary_use": "Pashto data source for NLP experimentation",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "nlp"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/tasal9/ZamAI_Pashto_Dataset",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-pashto-asr-base",
      "title": "ihanif/pashto-asr-base",
      "url": "https://huggingface.co/ihanif/pashto-asr-base",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ihanif/pashto-asr-base",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-wav2vec2-xls-r-300m-pashto-lm",
      "title": "ihanif/wav2vec2-xls-r-300m-pashto-lm",
      "url": "https://huggingface.co/ihanif/wav2vec2-xls-r-300m-pashto-lm",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ihanif/wav2vec2-xls-r-300m-pashto-lm",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-whisper-large-pashto",
      "title": "ihanif/whisper-large-pashto",
      "url": "https://huggingface.co/ihanif/whisper-large-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ihanif/whisper-large-pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-whisper-medium-pashto-3e-7",
      "title": "ihanif/whisper-medium-pashto-3e-7",
      "url": "https://huggingface.co/ihanif/whisper-medium-pashto-3e-7",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ihanif/whisper-medium-pashto-3e-7",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-whisper-small-pashto",
      "title": "ihanif/whisper-small-pashto",
      "url": "https://huggingface.co/ihanif/whisper-small-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ihanif/whisper-small-pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-xls-r-1b-pashto",
      "title": "ihanif/xls-r-1b-pashto",
      "url": "https://huggingface.co/ihanif/xls-r-1b-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ihanif/xls-r-1b-pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ijazulhaq-bert-base-pashto-v1",
      "title": "ijazulhaq/bert-base-pashto-v1",
      "url": "https://huggingface.co/ijazulhaq/bert-base-pashto-v1",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto NLP model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto model baseline for downstream NLP tasks",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "nlp"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ijazulhaq/bert-base-pashto-v1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-ihanif-wav2vec2-bert-pashto-asr",
      "title": "ihanif/wav2vec2-bert-pashto-asr",
      "url": "https://huggingface.co/spaces/ihanif/wav2vec2-bert-pashto-asr",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and quick evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "asr",
        "nlp",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "asr",
        "nlp",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/ihanif/wav2vec2-bert-pashto-asr",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-nasirkhansayyad-pashto-whisper-demo",
      "title": "nasirkhansayyad/pashto-whisper-demo",
      "url": "https://huggingface.co/spaces/nasirkhansayyad/pashto-whisper-demo",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and quick evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "asr",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "asr",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/nasirkhansayyad/pashto-whisper-demo",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-tasal9-zamai-phi3-mini-pashto-demo",
      "title": "tasal9/ZamAI-Phi3-Mini-Pashto-Demo",
      "url": "https://huggingface.co/spaces/tasal9/ZamAI-Phi3-Mini-Pashto-Demo",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and quick evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "llm",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "llm",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/tasal9/ZamAI-Phi3-Mini-Pashto-Demo",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-umar4321-pashto-to-english-urdu",
      "title": "Umar4321/Pashto-To-English-Urdu",
      "url": "https://huggingface.co/spaces/Umar4321/Pashto-To-English-Urdu",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and quick evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "mt",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "mt",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/Umar4321/Pashto-To-English-Urdu",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-github-fazlullahmamond-pashto-typing",
      "title": "Fazlullahmamond/Pashto-Typing",
      "url": "https://github.com/Fazlullahmamond/Pashto-Typing",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from github for demonstration and quick evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "github",
        "demo"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/Fazlullahmamond/Pashto-Typing",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-s2-benchmarking-whisper-for-low-resource-speech-recognition-an-n-shot-evaluation-on-pashto-pu",
      "title": "Benchmarking Whisper for Low-Resource Speech Recognition: An N-Shot Evaluation on Pashto, Punjabi, and Urdu",
      "url": "https://www.semanticscholar.org/paper/13104eddc785756132a19242ac7e74442b145693",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from other for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "asr",
        "mt"
      ],
      "tags": [
        "pashto",
        "paper",
        "other",
        "asr",
        "mt"
      ],
      "evidence_text": "Matched by Semantic Scholar query: pashto.",
      "evidence_url": "https://www.semanticscholar.org/paper/13104eddc785756132a19242ac7e74442b145693",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-s2-deep-learning-based-detection-of-one-and-two-column-textual-blocks-in-camera-captured-pash",
      "title": "Deep Learning-Based Detection of One and Two-Column Textual Blocks in Camera-Captured Pashto Documents Images",
      "url": "https://www.semanticscholar.org/paper/8c9d2628e23d5c27edc656071f11f0e78124d182",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from other for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "ocr"
      ],
      "tags": [
        "pashto",
        "paper",
        "other",
        "ocr"
      ],
      "evidence_text": "Matched by Semantic Scholar query: pashto.",
      "evidence_url": "https://www.semanticscholar.org/paper/8c9d2628e23d5c27edc656071f11f0e78124d182",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-s2-out-of-vocabulary-pashto-spell-checker-using-morphological-operations",
      "title": "Out-of-Vocabulary Pashto Spell Checker using Morphological Operations",
      "url": "https://www.semanticscholar.org/paper/802aae68a6a7fdfb29d51be03fb2b09e29311fa7",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from other for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "paper",
        "other",
        "nlp"
      ],
      "evidence_text": "Matched by Semantic Scholar query: pashto.",
      "evidence_url": "https://www.semanticscholar.org/paper/802aae68a6a7fdfb29d51be03fb2b09e29311fa7",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-s2-pashto-shallow-parsing-a-deep-learning-approach",
      "title": "Pashto Shallow Parsing: A Deep Learning Approach",
      "url": "https://www.semanticscholar.org/paper/be36455bb4eca60accb3e6866f345132f0dac1e5",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from other for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "paper",
        "other",
        "nlp"
      ],
      "evidence_text": "Matched by Semantic Scholar query: pashto.",
      "evidence_url": "https://www.semanticscholar.org/paper/be36455bb4eca60accb3e6866f345132f0dac1e5",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-s2-pos-tagging-of-low-resource-pashto-language-annotated-corpus-and-bert-based-model",
      "title": "POS tagging of low-resource Pashto language: annotated corpus and BERT-based model",
      "url": "https://www.semanticscholar.org/paper/1b2d5c896fec735483e8c8fb0a75e13125e08769",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from other for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "paper",
        "other",
        "nlp"
      ],
      "evidence_text": "Matched by Semantic Scholar query: pashto.",
      "evidence_url": "https://www.semanticscholar.org/paper/1b2d5c896fec735483e8c8fb0a75e13125e08769",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-arxiv-enhancing-pashto-text-classification-using-language-processing-techniques-for-single-and-m",
      "title": "Enhancing Pashto Text Classification using Language Processing Techniques for Single And Multi-Label Analysis",
      "url": "http://arxiv.org/abs/2305.03201v1",
      "category": "paper",
      "source": "arxiv",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from arxiv for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "paper",
        "arxiv",
        "nlp"
      ],
      "evidence_text": "Matched by arXiv query: all:pashto.",
      "evidence_url": "http://arxiv.org/abs/2305.03201v1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-arxiv-knn-and-ann-based-recognition-of-handwritten-pashto-letters-using-zoning-features",
      "title": "KNN and ANN-based Recognition of Handwritten Pashto Letters using Zoning Features",
      "url": "http://arxiv.org/abs/1904.03391v2",
      "category": "paper",
      "source": "arxiv",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from arxiv for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "ocr"
      ],
      "tags": [
        "pashto",
        "paper",
        "arxiv",
        "ocr"
      ],
      "evidence_text": "Matched by arXiv query: all:pashto.",
      "evidence_url": "http://arxiv.org/abs/1904.03391v2",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-oowais-pushto-text-to-speech-dataset",
      "title": "oowais/pushto-text-to-speech-dataset",
      "url": "https://huggingface.co/datasets/oowais/pushto-text-to-speech-dataset",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto speech dataset discovered from huggingface candidate sync for ASR training and evaluation.",
      "primary_use": "ASR training and evaluation data source",
      "tasks": [
        "asr",
        "tts"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "asr",
        "tts"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/oowais/pushto-text-to-speech-dataset",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-ihanif-pashto-speech-20k",
      "title": "ihanif/pashto_speech_20k",
      "url": "https://huggingface.co/datasets/ihanif/pashto_speech_20k",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto speech dataset discovered from huggingface candidate sync for ASR training and evaluation.",
      "primary_use": "ASR training and evaluation data source",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto_speech_20k",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-ihanif-pashto-speech-5k",
      "title": "ihanif/pashto_speech_5k",
      "url": "https://huggingface.co/datasets/ihanif/pashto_speech_5k",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto speech dataset discovered from huggingface candidate sync for ASR training and evaluation.",
      "primary_use": "ASR training and evaluation data source",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto_speech_5k",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-tasal9-pashto-dataset",
      "title": "tasal9/Pashto_Dataset",
      "url": "https://huggingface.co/datasets/tasal9/Pashto_Dataset",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused dataset discovered from huggingface candidate sync.",
      "primary_use": "Pashto data source for NLP experimentation",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "nlp"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/tasal9/Pashto_Dataset",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ijazulhaq-bert-base-pashto",
      "title": "ijazulhaq/bert-base-pashto",
      "url": "https://huggingface.co/ijazulhaq/bert-base-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto NLP model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto model baseline for downstream NLP tasks",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "nlp"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ijazulhaq/bert-base-pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-ihanif-whisper-small-pashto-dropout",
      "title": "ihanif/whisper-small-pashto-dropout",
      "url": "https://huggingface.co/ihanif/whisper-small-pashto-dropout",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ihanif/whisper-small-pashto-dropout",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-koochikoo25-pashto-whisper-large",
      "title": "koochikoo25/pashto-whisper-large",
      "url": "https://huggingface.co/koochikoo25/pashto-whisper-large",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint discovered from huggingface candidate sync.",
      "primary_use": "Pashto ASR baseline and model comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/koochikoo25/pashto-whisper-large",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-ihanif-wav2vec-pashto-asr",
      "title": "ihanif/wav2vec-pashto-asr",
      "url": "https://huggingface.co/spaces/ihanif/wav2vec-pashto-asr",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "asr",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "asr",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/ihanif/wav2vec-pashto-asr",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-afaqalinagra-pashto-asr-model",
      "title": "afaqalinagra/PASHTO-ASR-MODEL",
      "url": "https://huggingface.co/spaces/afaqalinagra/PASHTO-ASR-MODEL",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "asr",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "asr",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/afaqalinagra/PASHTO-ASR-MODEL",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-ilyas02828-pashto-sign-language",
      "title": "ilyas02828/Pashto_Sign_Language",
      "url": "https://huggingface.co/spaces/ilyas02828/Pashto_Sign_Language",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/ilyas02828/Pashto_Sign_Language",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-mahmudaq-pashtoasrnmt1",
      "title": "mahmudaq/PashtoASRNMT1",
      "url": "https://huggingface.co/spaces/mahmudaq/PashtoASRNMT1",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto-focused interactive project discovered from huggingface for demonstration and evaluation.",
      "primary_use": "Interactive Pashto demo and quick qualitative validation",
      "tasks": [
        "asr",
        "mt",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "asr",
        "mt",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/mahmudaq/PashtoASRNMT1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-s2-enhancing-pashto-ner-using-machine-labeled-data-and-transformer-based-models",
      "title": "Enhancing Pashto NER Using Machine-Labeled Data and Transformer-Based Models",
      "url": "https://www.semanticscholar.org/paper/be851ecf9197ef9bb8bf764abf4db0dda95cd9da",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Pashto language technology paper discovered from other for research reference.",
      "primary_use": "Pashto research reference for methods and benchmarking",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "paper",
        "other",
        "nlp"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/be851ecf9197ef9bb8bf764abf4db0dda95cd9da",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-aamirhs-pashto-audio-wav2vec",
      "title": "aamirhs/pashto-audio-wav2vec",
      "url": "https://huggingface.co/datasets/aamirhs/pashto-audio-wav2vec",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto speech dataset surfaced from Hugging Face candidate sync for ASR experiments.",
      "primary_use": "Pashto ASR data exploration and baseline training",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "speech",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/aamirhs/pashto-audio-wav2vec",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-alimuhammad73-pashto-poetry",
      "title": "AliMuhammad73/Pashto-Poetry",
      "url": "https://huggingface.co/datasets/AliMuhammad73/Pashto-Poetry",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto poetry text dataset surfaced from Hugging Face candidate sync for NLP experiments.",
      "primary_use": "Pashto poetry corpus for language modeling and text analysis",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "dataset",
        "huggingface",
        "text",
        "poetry",
        "nlp"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/AliMuhammad73/Pashto-Poetry",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "model-hf-aamirhs-wav2vec2-large-xls-r-300m-pashto-colab",
      "title": "aamirhs/wav2vec2-large-xls-r-300m-pashto-colab",
      "url": "https://huggingface.co/aamirhs/wav2vec2-large-xls-r-300m-pashto-colab",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR model checkpoint surfaced from Hugging Face candidate sync.",
      "primary_use": "Pashto ASR baseline and transfer-learning comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "model",
        "huggingface",
        "asr"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/aamirhs/wav2vec2-large-xls-r-300m-pashto-colab",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-aizazayyubi-pashto-asr",
      "title": "Aizazayyubi/pashto_asr",
      "url": "https://huggingface.co/spaces/Aizazayyubi/pashto_asr",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto ASR interactive demo surfaced from Hugging Face Spaces candidate sync.",
      "primary_use": "Interactive Pashto ASR demo for qualitative evaluation",
      "tasks": [
        "asr",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface",
        "asr",
        "demo"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/Aizazayyubi/pashto_asr",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-arxiv-from-scarcity-to-scale-pashto-common-voice",
      "title": "From Scarcity to Scale: A Release-Level Analysis of the Pashto Common Voice Dataset",
      "url": "http://arxiv.org/abs/2602.14062v1",
      "category": "paper",
      "source": "arxiv",
      "status": "verified",
      "summary": "Research paper analyzing Pashto Common Voice releases and dataset scaling characteristics.",
      "primary_use": "ASR data quality and release trend reference",
      "tasks": [
        "asr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "paper",
        "arxiv",
        "asr",
        "common-voice"
      ],
      "evidence_text": "Matched by Pashto marker in paper title from arXiv query results.",
      "evidence_url": "http://arxiv.org/abs/2602.14062v1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-arxiv-tuning-traditional-pashto-text-classification",
      "title": "Tuning Traditional Language Processing Approaches for Pashto Text Classification",
      "url": "http://arxiv.org/abs/2305.03737v1",
      "category": "paper",
      "source": "arxiv",
      "status": "verified",
      "summary": "Research paper focused on Pashto text classification using traditional NLP approaches.",
      "primary_use": "Pashto text classification method reference",
      "tasks": [
        "nlp"
      ],
      "tags": [
        "pashto",
        "paper",
        "arxiv",
        "nlp",
        "classification"
      ],
      "evidence_text": "Matched by Pashto marker in paper title from arXiv query results.",
      "evidence_url": "http://arxiv.org/abs/2305.03737v1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-dataverse-iarpa-babel-pashto-language-pack-v0-4by",
      "title": "IARPA Babel Pashto Language Pack IARPA-babel104b-v0.4bY",
      "url": "https://hdl.handle.net/11272.1/AB2/GLFN3X",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Pashto Babel language pack dataset for speech and language processing evaluation.",
      "primary_use": "Pashto speech dataset for ASR and language identification experiments",
      "tasks": [
        "asr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "dataset",
        "dataverse",
        "speech",
        "asr",
        "babel"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://hdl.handle.net/11272.1/AB2/GLFN3X",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-arxiv-image-to-text-pashto-farsi-traditional-chinese",
      "title": "Development of a New Image-to-text Conversion System for Pashto, Farsi and Traditional Chinese",
      "url": "http://arxiv.org/abs/2005.08650v1",
      "category": "paper",
      "source": "arxiv",
      "status": "verified",
      "summary": "Research paper on image-to-text conversion including Pashto OCR.",
      "primary_use": "Pashto OCR method reference",
      "tasks": [
        "ocr",
        "nlp"
      ],
      "tags": [
        "pashto",
        "paper",
        "arxiv",
        "ocr"
      ],
      "evidence_text": "Matched by Pashto marker in paper title from arXiv query results.",
      "evidence_url": "http://arxiv.org/abs/2005.08650v1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-benchmark-pashto-handwritten-character-dataset-ocr",
      "title": "Benchmark Pashto Handwritten Character Dataset and Pashto Object Character Recognition (OCR) Using Deep Neural Network with Rule Activation Function",
      "url": "https://doi.org/10.1155/2021/6669672",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper introducing a benchmark dataset and OCR approach for Pashto handwritten characters.",
      "primary_use": "Pashto handwritten OCR benchmark and methodology reference",
      "tasks": [
        "ocr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr",
        "benchmark"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1155/2021/6669672",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-asr-isolated-pashto-spoken-digits-mfcc-knn",
      "title": "Database development and automatic speech recognition of isolated Pashto spoken digits using MFCC and K-NN",
      "url": "https://doi.org/10.1007/s10772-014-9267-z",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on isolated Pashto spoken-digit ASR with MFCC and K-NN.",
      "primary_use": "Pashto ASR baseline method reference for digit recognition",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "asr",
        "speech"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1007/s10772-014-9267-z",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-pashto-isolated-digits-recognition-dcnn",
      "title": "Pashto isolated digits recognition using deep convolutional neural network",
      "url": "https://doi.org/10.1016/j.heliyon.2020.e03372",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on Pashto isolated-digit recognition using deep convolutional neural networks.",
      "primary_use": "Pashto speech recognition research reference",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "asr",
        "deep-learning"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1016/j.heliyon.2020.e03372",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-pashto-offensive-language-detection-benchmark-bert",
      "title": "Pashto offensive language detection: a benchmark dataset and monolingual Pashto BERT",
      "url": "https://doi.org/10.7717/peerj-cs.1617",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on Pashto offensive language detection with benchmark dataset and monolingual BERT model.",
      "primary_use": "Pashto NLP toxicity detection benchmark and model reference",
      "tasks": [
        "nlp",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "nlp",
        "bert",
        "benchmark"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.7717/peerj-cs.1617",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-phti-pashto-handwritten-text-imagebase",
      "title": "PHTI: Pashto Handwritten Text Imagebase for Deep Learning Applications",
      "url": "https://doi.org/10.1109/access.2022.3216881",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper describing PHTI, a Pashto handwritten text imagebase for deep learning.",
      "primary_use": "Pashto OCR dataset and benchmark reference",
      "tasks": [
        "ocr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr",
        "dataset"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1109/access.2022.3216881",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-recognition-of-pashto-handwritten-characters-deep-learning",
      "title": "Recognition of Pashto Handwritten Characters Based on Deep Learning",
      "url": "https://doi.org/10.3390/s20205884",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on deep-learning-based recognition of Pashto handwritten characters.",
      "primary_use": "Pashto OCR model reference for handwritten character recognition",
      "tasks": [
        "ocr"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr",
        "deep-learning"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.3390/s20205884",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-kpti-katib-pashto-text-imagebase-benchmark",
      "title": "KPTI: Katib's Pashto Text Imagebase and Deep Learning Benchmark",
      "url": "https://doi.org/10.1109/icfhr.2016.0090",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper introducing KPTI, a Pashto text imagebase and benchmark for handwritten recognition.",
      "primary_use": "Pashto OCR dataset and benchmarking reference",
      "tasks": [
        "ocr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr",
        "benchmark"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1109/icfhr.2016.0090",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-pioneer-dataset-handwritten-pashto-cnn",
      "title": "Pioneer dataset and recognition of Handwritten Pashto characters using Convolution Neural Networks",
      "url": "https://doi.org/10.1177/0020294020964826",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on a pioneer handwritten Pashto character dataset with CNN-based recognition.",
      "primary_use": "Pashto handwritten character recognition reference",
      "tasks": [
        "ocr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr",
        "deep-learning"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1177/0020294020964826",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-scale-rotation-invariant-ocr-pashto-mdlstm",
      "title": "Scale and rotation invariant OCR for Pashto cursive script using MDLSTM network",
      "url": "https://doi.org/10.1109/icdar.2015.7333931",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on scale- and rotation-invariant OCR for cursive Pashto using MDLSTM.",
      "primary_use": "Pashto OCR model architecture reference",
      "tasks": [
        "ocr"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr",
        "mdlstm"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1109/icdar.2015.7333931",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-recognizable-units-pashto-ocr",
      "title": "Recognizable units in Pashto language for OCR",
      "url": "https://doi.org/10.1109/icdar.2015.7333963",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper defining recognizable units in Pashto for OCR workflows.",
      "primary_use": "Pashto OCR preprocessing and unit-design reference",
      "tasks": [
        "ocr"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1109/icdar.2015.7333963",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-shape-analysis-pashto-script-image-database-ocr",
      "title": "Shape analysis of Pashto script and creation of image database for OCR",
      "url": "https://doi.org/10.1109/icet.2009.5353160",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on Pashto script shape analysis and image database creation for OCR.",
      "primary_use": "Pashto OCR dataset design and feature reference",
      "tasks": [
        "ocr",
        "benchmarking"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "ocr",
        "dataset"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1109/icet.2009.5353160",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "paper-openalex-speech-translation-low-resource-case-pashto",
      "title": "Speech translation for low-resource languages: the case of Pashto",
      "url": "https://doi.org/10.21437/interspeech.2005-723",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Research paper on speech translation for low-resource languages, including Pashto.",
      "primary_use": "Pashto speech translation and low-resource MT reference",
      "tasks": [
        "asr",
        "mt"
      ],
      "tags": [
        "pashto",
        "paper",
        "openalex",
        "speech",
        "translation"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.21437/interspeech.2005-723",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-ihanif-pashto-speech-2k",
      "title": "ihanif/pashto_speech_2k",
      "url": "https://huggingface.co/datasets/ihanif/pashto_speech_2k",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto synthetic speech dataset with paired audio-text samples for low-resource ASR baselines.",
      "primary_use": "ASR training and controlled synthetic-speech evaluation",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "speech",
        "dataset",
        "asr",
        "huggingface"
      ],
      "evidence_text": "Dataset metadata includes language:ps and Pashto speech dataset card details.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto_speech_2k",
      "markers": [
        "language:ps",
        "pashto",
        "speech"
      ]
    },
    {
      "id": "dataset-hf-ihanif-pashto-speech-3k",
      "title": "ihanif/pashto_speech_3k",
      "url": "https://huggingface.co/datasets/ihanif/pashto_speech_3k",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto synthetic speech parquet dataset with audio-text pairs and language metadata.",
      "primary_use": "ASR training and reproducible speech-data experimentation",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "speech",
        "dataset",
        "asr",
        "huggingface",
        "parquet"
      ],
      "evidence_text": "Dataset metadata includes language:ps and task category automatic speech recognition.",
      "evidence_url": "https://huggingface.co/datasets/ihanif/pashto_speech_3k",
      "markers": [
        "language:ps",
        "automatic-speech-recognition",
        "pashto"
      ]
    },
    {
      "id": "dataset-hf-koochikoo25-pashto-concatenated",
      "title": "koochikoo25/Pashto-Concatenated",
      "url": "https://huggingface.co/datasets/koochikoo25/Pashto-Concatenated",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto concatenated audio-text dataset with predefined train-validation-test splits.",
      "primary_use": "ASR dataset preparation and split-based benchmark experiments",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "speech",
        "dataset",
        "asr",
        "huggingface"
      ],
      "evidence_text": "Dataset title explicitly states Pashto and card metadata exposes audio-text features and splits.",
      "evidence_url": "https://huggingface.co/datasets/koochikoo25/Pashto-Concatenated",
      "markers": [
        "Pashto",
        "audio",
        "transcription"
      ]
    },
    {
      "id": "model-hf-koochikoo25-whisper-medium-pashto",
      "title": "koochikoo25/Whisper-medium-pashto",
      "url": "https://huggingface.co/koochikoo25/Whisper-medium-pashto",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Whisper medium fine-tuned checkpoint for Pashto automatic speech recognition.",
      "primary_use": "Pashto ASR baseline modeling and transcription comparison",
      "tasks": [
        "asr"
      ],
      "tags": [
        "pashto",
        "asr",
        "model",
        "whisper",
        "huggingface"
      ],
      "evidence_text": "Model tags include ps and automatic-speech-recognition with a Pashto model name.",
      "evidence_url": "https://huggingface.co/koochikoo25/Whisper-medium-pashto",
      "markers": [
        "ps",
        "automatic-speech-recognition",
        "pashto"
      ]
    },
    {
      "id": "project-hf-space-afaaaak-urdu-pashto-translator",
      "title": "afaaaak/urdu_pashto_translator",
      "url": "https://huggingface.co/spaces/afaaaak/urdu_pashto_translator",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Interactive Urdu-to-Pashto translation Space with a runnable web demo.",
      "primary_use": "Translation demo and bilingual usability testing",
      "tasks": [
        "mt",
        "translation",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface-space",
        "translation",
        "demo"
      ],
      "evidence_text": "Space metadata title is Urdu Pashto Translator and the slug includes pashto.",
      "evidence_url": "https://huggingface.co/spaces/afaaaak/urdu_pashto_translator",
      "markers": [
        "Pashto",
        "translator"
      ]
    },
    {
      "id": "project-hf-space-drsaqlainhassan-pashto-tokenixer",
      "title": "DrSaqlainHassan/PashtoTokenixer",
      "url": "https://huggingface.co/spaces/DrSaqlainHassan/PashtoTokenixer",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Pashto parts-of-speech identification Space for interactive NLP exploration.",
      "primary_use": "Pashto NLP demo for token and part-of-speech analysis",
      "tasks": [
        "nlp",
        "pos-tagging",
        "demo"
      ],
      "tags": [
        "pashto",
        "project",
        "huggingface-space",
        "nlp",
        "demo"
      ],
      "evidence_text": "Space card title states Pashto Parts of Speech Identifier and the slug contains Pashto.",
      "evidence_url": "https://huggingface.co/spaces/DrSaqlainHassan/PashtoTokenixer",
      "markers": [
        "Pashto",
        "parts-of-speech"
      ]
    },
    {
      "id": "candidate-hf-dataset-aamirhs-pashto",
      "title": "aamirhs/pashto",
      "url": "https://huggingface.co/datasets/aamirhs/pashto",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate dataset returned from Hugging Face search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/aamirhs/pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-dataset-arsalagrey-pashto",
      "title": "arsalagrey/pashto",
      "url": "https://huggingface.co/datasets/arsalagrey/pashto",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate dataset returned from Hugging Face search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/arsalagrey/pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-dataset-arsalagrey-pashto-books",
      "title": "arsalagrey/pashto-books",
      "url": "https://huggingface.co/datasets/arsalagrey/pashto-books",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate dataset returned from Hugging Face search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/arsalagrey/pashto-books",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-dataset-arsalagrey-pashto-books-json",
      "title": "arsalagrey/pashto-books-json",
      "url": "https://huggingface.co/datasets/arsalagrey/pashto-books-json",
      "category": "dataset",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate dataset returned from Hugging Face search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/datasets/arsalagrey/pashto-books-json",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-model-jawaria-wav2vec2-large-xls-r-300m-pashto-colab-final-1",
      "title": "Jawaria/wav2vec2-large-xls-r-300m-pashto-colab-final-1",
      "url": "https://huggingface.co/Jawaria/wav2vec2-large-xls-r-300m-pashto-colab-final-1",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate model returned from Hugging Face search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "model"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/Jawaria/wav2vec2-large-xls-r-300m-pashto-colab-final-1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-dataset-oped-open-pashto-english-dictionary-preliminary-version-30-october-2025",
      "title": "OPED (Open Pashto-English Dictionary): Preliminary version, 30 October 2025",
      "url": "https://zenodo.org/records/17487678",
      "category": "dataset",
      "source": "zenodo",
      "status": "verified",
      "summary": "Candidate resource returned from Zenodo search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/17487678",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-pushto-pakhto-nasar-kay-da-matbooa-tarjumo-yova-tanqeedi-mutala-jaiza",
      "title": "(Pushto) Pakhto Nasar Kay Da Matbooa Tarjumo Yova Tanqeedi Mutala/Jaiza.",
      "url": "https://www.semanticscholar.org/paper/0da0e8535262d1f26f04dd6bc2f091474cab4150",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/0da0e8535262d1f26f04dd6bc2f091474cab4150",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-a-dictionary-of-the-pukhto-pushto-or-language-of-the-afghans",
      "title": "A Dictionary of the Pukhto, Pushto, or Language of the Afghans",
      "url": "https://www.semanticscholar.org/paper/777c0aa56991f55826339915363de2ceb8dd7141",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/777c0aa56991f55826339915363de2ceb8dd7141",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-a-dictionary-of-the-pukhto-pushto-or-language-of-the-afghans-with-remarks-on-the",
      "title": "A dictionary of the Pukhto, Pushto, or language of the Afghans; with remarks on the originality of the language, and its affinity to the Semitic and other Oriental tongues, etc.",
      "url": "https://www.semanticscholar.org/paper/d12502a6c245ff6f537bf68d9db4b449dca827bb",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/d12502a6c245ff6f537bf68d9db4b449dca827bb",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-a-grammar-of-the-puk-h-to-or-pus-h-to-language",
      "title": "A grammar of the Puk̲h̲to or Pus̲'h̲to language",
      "url": "https://www.semanticscholar.org/paper/99c46409a55ac0bf68e2c530a377becfcb46dd47",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/99c46409a55ac0bf68e2c530a377becfcb46dd47",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-a-new-etymological-vocabulary-of-pashto",
      "title": "A New Etymological Vocabulary of Pashto",
      "url": "https://openalex.org/W2071464713",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://openalex.org/W2071464713",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-a-reference-grammar-of-pashto",
      "title": "A reference grammar of Pashto",
      "url": "http://wals.info/refdb/record/7189",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "http://wals.info/refdb/record/7189",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-project-adnankarim-ihanif-whisper-base-pashto",
      "title": "adnankarim/ihanif-whisper-base-pashto",
      "url": "https://huggingface.co/spaces/adnankarim/ihanif-whisper-base-pashto",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate project app returned from Hugging Face Spaces Pashto search.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "space"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/adnankarim/ihanif-whisper-base-pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-project-adnankarim-ihanif-whisper-medium-pashto-3e-7",
      "title": "adnankarim/ihanif-whisper-medium-pashto-3e-7",
      "url": "https://huggingface.co/spaces/adnankarim/ihanif-whisper-medium-pashto-3e-7",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate project app returned from Hugging Face Spaces Pashto search.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "space"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/adnankarim/ihanif-whisper-medium-pashto-3e-7",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-amirajorloo-jira-auto-direction-chrome-extension",
      "title": "amirajorloo/jira-auto-direction-chrome-extension",
      "url": "https://github.com/amirajorloo/jira-auto-direction-chrome-extension",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "This is an extension to set dir=\"auto\" in content wrappers to make them right-aligned when the language is an RTL language (like Persian, Arabic, ...)",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "arabic",
        "chrome-extension",
        "farsi"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/amirajorloo/jira-auto-direction-chrome-extension",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-cer-hv-a-cer-based-human-in-the-loop-framework-for-cleaning-datasets-applied-to-",
      "title": "CER-HV: A CER-Based Human-in-the-Loop Framework for Cleaning Datasets Applied to Arabic-Script HTR",
      "url": "https://arxiv.org/abs/2601.16713",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "Handwritten text recognition (HTR) for Arabic-script languages still lags behind Latin-script HTR, despite recent advances in model architectures, datasets, and benchmarks. We show that data quality is a significant limiting factor in many",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://arxiv.org/abs/2601.16713",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-dataset-clitic-particles-and-the-typology-of-2p-languages",
      "title": "Clitic Particles and the Typology of 2P Languages",
      "url": "https://zenodo.org/records/15010591",
      "category": "dataset",
      "source": "zenodo",
      "status": "verified",
      "summary": "This paper was prepared after the Particle Workshop (Cambridge, 30-31 October 2008) for the prospective conference volume. I am grateful to the audience of the Particle Workshop in Cambrigde, October 30-31, 2008 and personally to Anders Hol",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/15010591",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-critical-study-of-the-travelogues-of-dr-altaf-yousafzai-in-the-context-of-thaila",
      "title": "Critical study of the travelogues of Dr Altaf Yousafzai (In The Context of \"Thailand kay Rang\", \"Nile kay Sang\" and  \"Bakhal-e-Hinduwush Bakhsham\")",
      "url": "https://zenodo.org/records/13937101",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Dr. Muhammad Altaf Yusufzai, is an Associate Professor in the Department of Urdu (Hazara University Mansehra). Dr Muhammad Altaf Yusufzai is a well-known Personality of Urdu literature, \"Mukhtar Masood ka Asloob\", \"Urdu Nazam or Nine Eleven",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/13937101",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-depiction-of-women-s-cries-in-pashto-landai-poetry",
      "title": "Depiction of Women's Cries in Pashto Landai Poetry",
      "url": "https://zenodo.org/records/15524281",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Pashto folk literature represents various social realities through poetic expressions, with Landai being a crucial form. This article explores the representation of women’s grief and protest in Pashto Landai. Through qualitative and analyti",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/15524281",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-descriptive-grammar-of-pashto-and-its-dialects",
      "title": "Descriptive Grammar of Pashto and its Dialects",
      "url": "https://doi.org/10.1515/9781614512318",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1515/9781614512318",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-divorce-and-women-s-rights-should-women-have-equal-rights-pashto",
      "title": "Divorce And Women’s Rights: Should Women have Equal Rights? (Pashto)",
      "url": "https://opendata.uni-halle.de//handle/1981185920/123991",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "This article looks at the fiqhi formulations of the divorce law through the lense of the Qur’anic verse (al-Baqarah, 2:228). Whereas the leading schools of fiqh have articulated a regime of divorce law that is decidedly onesided and generat",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://opendata.uni-halle.de//handle/1981185920/123991",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-doing-pashto",
      "title": "Doing Pashto",
      "url": "https://doi.org/10.1080/02690055.2015.1068987",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.1080/02690055.2015.1068987",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-project-early-pregnancy-loss-pashto",
      "title": "Early Pregnancy Loss [Pashto]",
      "url": "https://zenodo.org/doi/10.5281/zenodo.18325729",
      "category": "project",
      "source": "datacite",
      "status": "verified",
      "summary": "Candidate record returned from DataCite DOI search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/doi/10.5281/zenodo.18325729",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-editorial-note-dari",
      "title": "Editorial Note (Dari)",
      "url": "https://opendata.uni-halle.de//handle/1981185920/123994",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "The Journal of Afghan Legal Studies (JALS) is the first peer-reviewed, trilingual scientific law journal in Afghanistan. It provides a unique intellectual venue for national and international scholars and researchers in the field of Afghan",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://opendata.uni-halle.de//handle/1981185920/123994",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-editorial-note-english",
      "title": "Editorial Note (English)",
      "url": "https://opendata.uni-halle.de//handle/1981185920/123993",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "The Journal of Afghan Legal Studies (JALS) is the first peer-reviewed, trilingual scientific law journal in Afghanistan. It provides a unique intellectual venue for national and international scholars and researchers in the field of Afghan",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://opendata.uni-halle.de//handle/1981185920/123993",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-editorial-note-pashto",
      "title": "Editorial Note (Pashto)",
      "url": "https://opendata.uni-halle.de//handle/1981185920/123995",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "The Journal of Afghan Legal Studies (JALS) is the first peer-reviewed, trilingual scientific law journal in Afghanistan. It provides a unique intellectual venue for national and international scholars and researchers in the field of Afghan",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://opendata.uni-halle.de//handle/1981185920/123995",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-educational-and-linguistic-aspects-of-text-preprocessing-in-pashto",
      "title": "EDUCATIONAL AND LINGUISTIC ASPECTS OF TEXT PREPROCESSING IN PASHTO",
      "url": "https://zenodo.org/records/15917449",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Abstract : This paper introduces foundational text preprocessing strategies designed for the Pashto language, focusing on linguistic structure, educational adaptation, and syntactic modeling. Given Pashto's complex morphology, diverse diale",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/15917449",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-embedding-elements-from-foreign-language-into-the-native-language-through-pashto",
      "title": "Embedding Elements from Foreign Language into The Native Language Through Pashto-English Code-Mixed Speech",
      "url": "https://zenodo.org/records/14756994",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "An individual's language style may undergo changes based on factors such as the topic of conversation, the passage of time, the interlocutors involved, and the social context or setting of the conversation. During this shift in speech style",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/14756994",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-evaluation-of-antibacterial-activity-of-zizyphus-jujuba",
      "title": "EVALUATION OF ANTIBACTERIAL ACTIVITY OF ZIZYPHUS JUJUBA",
      "url": "https://zenodo.org/records/3595881",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Objective: The objective of the study was to evaluate in-vitro efficacy of antibacterial activity of crude methanol, n-hexane, chloroform, ethyl acetate and aqueous extracts of Zizyphus jujuba against some human pathogenic bacterial strains",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/3595881",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-evaluation-of-antipyretic-activity-of-zizyphus-jujuba-lam-leaves-on-albino-rats",
      "title": "EVALUATION OF ANTIPYRETIC ACTIVITY OF ZIZYPHUS JUJUBA LAM. LEAVES ON ALBINO RATS",
      "url": "https://zenodo.org/records/4269214",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Objective : The objective of the study was to evaluate antipyretic activity of crude methanol extract of Zizyphus jujuba leaves. Z.jujuba commonly called, Red date or Chinese date or Bera (Pushto), belonging to family Rhamnaceae, is used pr",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/4269214",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-exploring-hospitality-as-a-cultural-tradition-a-qualitative-study-of-pashto-and-",
      "title": "Exploring Hospitality as a Cultural Tradition: A Qualitative Study of Pashto and Hindko Customs",
      "url": "https://zenodo.org/records/14872725",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Candidate resource returned from Zenodo search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/14872725",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-fairness-evaluation-and-inference-level-mitigation-in-llms",
      "title": "Fairness Evaluation and Inference Level Mitigation in LLMs",
      "url": "https://figshare.mq.edu.au/articles/thesis/Fairness_Evaluation_and_Inference_Level_Mitigation_in_LLMs/31093552/1",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "Recent advances in Large Language Models (LLMs) have shown remarkable capability and now sit at the center of this revolution, delivering strong performance across diverse Natural Language Processing (NLP) and multilingualism tasks. LLMs sh",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://figshare.mq.edu.au/articles/thesis/Fairness_Evaluation_and_Inference_Level_Mitigation_in_LLMs/31093552/1",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-fazlullahmamond-hadith-collection-pashto",
      "title": "Fazlullahmamond/hadith-collection-pashto",
      "url": "https://github.com/Fazlullahmamond/hadith-collection-pashto",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Hadith collection in Pashto language, developed by flutter.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "flutter",
        "hadith",
        "islamic"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/Fazlullahmamond/hadith-collection-pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-project-female-birth-control-part-i-pashto",
      "title": "Female Birth Control Part I [Pashto]",
      "url": "https://zenodo.org/doi/10.5281/zenodo.18325040",
      "category": "project",
      "source": "datacite",
      "status": "verified",
      "summary": "Candidate record returned from DataCite DOI search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/doi/10.5281/zenodo.18325040",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-project-female-birth-control-part-ii-pashto",
      "title": "Female Birth Control Part II [Pashto]",
      "url": "https://zenodo.org/doi/10.5281/zenodo.18325401",
      "category": "project",
      "source": "datacite",
      "status": "verified",
      "summary": "Candidate record returned from DataCite DOI search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/doi/10.5281/zenodo.18325401",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-framing-political-bias-in-multilingual-llms-across-pakistani-languages",
      "title": "Framing Political Bias in Multilingual LLMs Across Pakistani Languages",
      "url": "https://arxiv.org/abs/2506.00068",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "Large Language Models (LLMs) increasingly shape public discourse, yet most evaluations of political and economic bias have focused on high-resource, Western languages and contexts. This leaves critical blind spots in low-resource, multiling",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://arxiv.org/abs/2506.00068",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-from-scarcity-to-scale-a-release-level-analysis-of-the-pashto-common-voice-datas",
      "title": "From Scarcity to Scale: A Release-Level Analysis of the Pashto Common Voice Dataset",
      "url": "https://arxiv.org/abs/2602.14062",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "Large, openly licensed speech datasets are essential for building automatic speech recognition (ASR) systems, yet many widely spoken languages remain underrepresented in public resources. Pashto, spoken by more than 60 million people, has h",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://arxiv.org/abs/2602.14062",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-gemination-in-pashto",
      "title": "Gemination in Pashto",
      "url": "https://doi.org/10.24312/ucp-jll.02.02.405",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "The purpose of the present study was to analyze gemination in Pashto. For this purpose, first, data was collected generally from elder native speakers who speak the Yousafzai dialect. The collected data then was verified and discussed sever",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.24312/ucp-jll.02.02.405",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-haroon-blip-khan-pukhtoon",
      "title": "Haroon-blip/khan-pukhtoon",
      "url": "https://github.com/Haroon-blip/khan-pukhtoon",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Asslama o alaikom guys",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/Haroon-blip/khan-pukhtoon",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-haseebjanhamraz-pashtofonts",
      "title": "haseebjanhamraz/PashtoFonts",
      "url": "https://github.com/haseebjanhamraz/PashtoFonts",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "This repo contains Pashto fonts hosted by pashtology.com",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "fonts",
        "fontserver",
        "pashto"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/haseebjanhamraz/PashtoFonts",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-project-hassaankabir-pashto-malgaray",
      "title": "Hassaankabir/Pashto_Malgaray",
      "url": "https://huggingface.co/spaces/Hassaankabir/Pashto_Malgaray",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate project app returned from Hugging Face Spaces Pashto search.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "space"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/Hassaankabir/Pashto_Malgaray",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-project-ihanif-whisper-medium-pashto",
      "title": "ihanif/whisper-medium-pashto",
      "url": "https://huggingface.co/spaces/ihanif/whisper-medium-pashto",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate project app returned from Hugging Face Spaces Pashto search.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "space"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/ihanif/whisper-medium-pashto",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-ihyacommunity-khushkhat-extension",
      "title": "IhyaCommunity/Khushkhat-Extension",
      "url": "https://github.com/IhyaCommunity/Khushkhat-Extension",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Beautifies Arabic, Persian, Urdu, Pashto and other right-to-left (RTL) languages",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "addon",
        "arabic",
        "beautify"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/IhyaCommunity/Khushkhat-Extension",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-is-the-pushto-a-semitic-language",
      "title": "Is the Pushto a Semitic Language",
      "url": "https://zenodo.org/records/16001185",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "(Uploaded by Plazi from the Biodiversity Heritage Library) No abstract provided.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/16001185",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-knn-and-ann-based-recognition-of-handwritten-pashto-letters-using-zoning-feature",
      "title": "KNN and ANN-based Recognition of Handwritten Pashto Letters using Zoning Features",
      "url": "https://doi.org/10.14569/ijacsa.2018.091069",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.14569/ijacsa.2018.091069",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-language-barrier-and-its-effect-on-learning-at-the-public-primary-school-level-i",
      "title": "Language Barrier and its Effect on Learning at the Public Primary School Level in Lahore",
      "url": "https://zenodo.org/records/17728944",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Context and Purpose: Linguistic shift in general education and the use of English as a medium of instruction (EMI) at the primary level poses a large language barrier to the learners of other languages. This paper particularly examined the",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/17728944",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-lecramyajiv-ttf-x2",
      "title": "lecramyajiv/ttf-x2",
      "url": "https://github.com/lecramyajiv/ttf-x2",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "X Series 2 Webfont for Arabic Script",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "arabic",
        "dari",
        "farsi"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/lecramyajiv/ttf-x2",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-code-lgug2z-tashkil",
      "title": "LGUG2Z/tashkil",
      "url": "https://github.com/LGUG2Z/tashkil",
      "category": "code",
      "source": "github",
      "status": "verified",
      "summary": "A lightweight Rust library for removing Arabic diacritics",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "code",
        "github",
        "arabic",
        "dari",
        "diacritics"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/LGUG2Z/tashkil",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-mastermoo-pashto-quran",
      "title": "mastermoo/pashto-quran",
      "url": "https://github.com/mastermoo/pashto-quran",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Website for reading Quran with Pashto translation",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "pashto",
        "quran"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/mastermoo/pashto-quran",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-morphology-of-pashto-adverbs-word-and-paradigm-approach",
      "title": "Morphology of Pashto Adverbs: Word and Paradigm Approach",
      "url": "https://zenodo.org/records/16211508",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Candidate resource returned from Zenodo search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/16211508",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-code-mrychlik-worldly-ocr",
      "title": "mrychlik/worldly-ocr",
      "url": "https://github.com/mrychlik/worldly-ocr",
      "category": "code",
      "source": "github",
      "status": "verified",
      "summary": "Text-to-image conversion (OCR) for Pashto and Chinese, with a view towards comprehensive, multi-lingual OCR",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "code",
        "github",
        "multi-lingual-ocr",
        "ocr",
        "pashto"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/mrychlik/worldly-ocr",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-muhammadullah7-pakhtoonn",
      "title": "MuhammadUllah7/PAKHTOONN",
      "url": "https://github.com/MuhammadUllah7/PAKHTOONN",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Candidate Pashto-related GitHub repository.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/MuhammadUllah7/PAKHTOONN",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-multi-language-conversational-telephone-speech-2011-central-asian",
      "title": "Multi-Language Conversational Telephone Speech 2011 -- Central Asian",
      "url": "https://hdl.handle.net/11272.1/AB2/YW9PX3",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Introduction Multi-Language Conversational Telephone Speech 2011 – Central Asian was developed by the Linguistic Data Consortium (LDC) and is comprised of approximately 37 hours of telephone speech in three distinct language varieties of Ce",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://hdl.handle.net/11272.1/AB2/YW9PX3",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-nabeelest-pakhtoodle",
      "title": "nabeelest/pakhtoodle",
      "url": "https://github.com/nabeelest/pakhtoodle",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Candidate Pashto-related GitHub repository.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/nabeelest/pakhtoodle",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-nanonulla-lorem",
      "title": "NanoNulla/lorem",
      "url": "https://github.com/NanoNulla/lorem",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "ایجاد متن های ساختگی دری و پشتو",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "dari",
        "lorem",
        "pashto"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/NanoNulla/lorem",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-dataset-navoiy-terra-corpus-v1-0-first-computational-corpus-of-alisher-navoi-works-with-",
      "title": "NAVOIY-TERRA Corpus v1.0: First Computational Corpus of Alisher Navoi Works with Nine-Language Semantic Annotations",
      "url": "https://zenodo.org/doi/10.5281/zenodo.18602634",
      "category": "dataset",
      "source": "datacite",
      "status": "verified",
      "summary": "NAVOIY-TERRA v1.0 is the first open-access computational corpus of Alisher Navoi's (1441-1501) literary works, featuring fractal semantic annotations and a nine-language Plural-Lingual Translation (PLT) layer. Contents: 26 authentic texts i",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/doi/10.5281/zenodo.18602634",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-negation-in-pashto",
      "title": "Negation in Pashto",
      "url": "https://zenodo.org/records/18233956",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "In this paper, we explore negation in Pashto – an Eastern Iranian language spoken mainly in Pakistan and Afghanistan. Based on the Yousafzai dialect of Pashto, with the questionnaire provided by the editors as our main instrument, we invest",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/18233956",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-negotiating-pakhto-proverbs-islam-and-the-construction-of-identity-among-pashtun",
      "title": "Negotiating Pakhto: Proverbs, Islam and the Construction of Identity among Pashtuns",
      "url": "https://www.semanticscholar.org/paper/8a503f164e0c1f5be13866dad00539c7e5b1cabc",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/8a503f164e0c1f5be13866dad00539c7e5b1cabc",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-nisarmasid-nisar-pakhtoon",
      "title": "nisarmasid/NisAr-PakhtoOn",
      "url": "https://github.com/nisarmasid/NisAr-PakhtoOn",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Config files for my GitHub profile.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "config",
        "github-config"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/nisarmasid/NisAr-PakhtoOn",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-omid-persian-log2vis",
      "title": "omid/Persian-Log2Vis",
      "url": "https://github.com/omid/Persian-Log2Vis",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Persian Log2Vis / Arabic Log2Vis / A PHP project to convert logical UTF8 Persian and Arabic characters to visual.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "arabic",
        "arabic-language",
        "character"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/omid/Persian-Log2Vis",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-only-2-of-141-global-languages-employ-a-labial-for-tongue-in-1st-position-challe",
      "title": "Only 2 of 141 Global Languages Employ a Labial for \"Tongue\" in 1st position Challenging Saussure's Arbitrariness With Near Universal Embodied Iconicity for Tongue Vs Mouth in \"inverse\" Control",
      "url": "https://zenodo.org/doi/10.5281/zenodo.17807676",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "141 (now 154) of most spoken languages - the word \"Tongue\" provides statistical significant evidence for \"Embodied Iconicity\" Please note that the list was expanded to 154 languages, the additional 13 languages - all with more than 1 millio",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/doi/10.5281/zenodo.17807676",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-pakhtoon9900-pakhtoon",
      "title": "Pakhtoon9900/Pakhtoon-",
      "url": "https://github.com/Pakhtoon9900/Pakhtoon-",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Candidate Pashto-related GitHub repository.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/Pakhtoon9900/Pakhtoon-",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-pashto",
      "title": "Pashto",
      "url": "https://doi.org/10.4324/9780203301524-34",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.4324/9780203301524-34",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-pashto-endo-clitics-in-a-parallel-architecture",
      "title": "Pashto (Endo-)clitics in a Parallel Architecture",
      "url": "http://nbn-resolving.de/urn:nbn:de:bsz:352-0-278290",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "http://nbn-resolving.de/urn:nbn:de:bsz:352-0-278290",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-pashto-pashto-english-english-pashto-dictionary-phrasebook",
      "title": "Pashto : Pashto-English, English-Pashto dictionary & phrasebook",
      "url": "https://www.semanticscholar.org/paper/8ff77d35396d17225d97772e577e472a2ab1c47a",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/8ff77d35396d17225d97772e577e472a2ab1c47a",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-pashto-handwritten-books",
      "title": "Pashto Handwritten Books",
      "url": "https://doi.org/10.1163/9789004737358_003",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.1163/9789004737358_003",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-pashto-language",
      "title": "Pashto Language",
      "url": "https://doi.org/10.32388/pxbtfv",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.32388/pxbtfv",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-pashto-poetry-and-militancy-in-khyber-pakhtunkhwa-after-9-11-thematic-analysis-o",
      "title": "PASHTO POETRY AND MILITANCY IN KHYBER PAKHTUNKHWA AFTER 9/11: THEMATIC ANALYSIS OF PASHTO POETRY IN RESISTING MILITANCY",
      "url": "https://www.semanticscholar.org/paper/e81d4e7ac6cd7519643bf5d5c0bdfd9be554a8f2",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "The present study sheds light on Pashto or Pakhto Poetry and Militancy in Khyber Pakhtunkhwa after 9/11. The fieldwork for this study was conducted in the Peshawar district of Khyber Pakhtunkhwa, Pakistan, from December 2020 to April 2021.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/e81d4e7ac6cd7519643bf5d5c0bdfd9be554a8f2",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-pashto-tappa",
      "title": "Pashto Tappa",
      "url": "https://doi.org/10.4324/9781003604877-9",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.4324/9781003604877-9",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-pashto-verse",
      "title": "Pashto Verse",
      "url": "https://doi.org/10.1017/s0041977x00072700",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "In , and since, the nineteenth century a more than passing interest inPashto verse, both literary and popular, has been shown in Europe, as thefollowing titles (not to mention a number of chrestomathies) testify:",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.1017/s0041977x00072700",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-persian-loanwords-and-calques-in-pashto",
      "title": "Persian loanwords and calques in Pashto",
      "url": "https://www.semanticscholar.org/paper/ed232f1c2abd6e6f8a49f04de8ac76bf922521ea",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/ed232f1c2abd6e6f8a49f04de8ac76bf922521ea",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-persian-urdu-and-pashto-a-comparative-orthographic-analysis",
      "title": "Persian, Urdu, and Pashto: A comparative orthographic analysis",
      "url": "https://doi.org/10.1093/wsr/wsq005",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1093/wsr/wsq005",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-portrayal-of-death-in-the-selected-poems-of-abdul-ghani-khan-and-emily-dickinson",
      "title": "Portrayal of Death in the Selected Poems of Abdul Ghani Khan and Emily Dickinson: A Comparative Thematic Analysis",
      "url": "https://zenodo.org/records/15046502",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "This article studies the theme of death in the works of two poets for whom death is the most resonant, mysterious, moving and fascinating of all possible poetic themes that is connected to an awareness of human finitude: Ghani khan and Emil",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/15046502",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-pukhtoon203-pukhtoon",
      "title": "Pukhtoon203/PUKHTOON",
      "url": "https://github.com/Pukhtoon203/PUKHTOON",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Installation : 😈 apt update  😈 apt upgrade  😈 apt install git  😈 pkg install python  😈 pkg install python2 -y  😈 pip2 install requests  😈 pip2 install mechanize  😈 git clone https://github.com/pikhtoon203/",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/Pukhtoon203/PUKHTOON",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-rats-language-identification",
      "title": "RATS Language Identification",
      "url": "https://hdl.handle.net/11272.1/AB2/UP3WJC",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "RATS Language Identification was developed by the Linguistic Data Consortium (LDC) and is comprised of approximately 5,400 hours of Levantine Arabic, Farsi, Dari, Pashto and Urdu conversational telephone speech with annotation of speech seg",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://hdl.handle.net/11272.1/AB2/UP3WJC",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-rats-low-speech-density",
      "title": "RATS Low Speech Density",
      "url": "https://doi.org/10.35111/4ENA-FG30",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Abstract Introduction RATS Low Speech Density was developed by the Linguistic Data Consortium (LDC) and is comprised of approximately 87 hours of English, Levantine Arabic, Farsi, Pashto and Urdu speech and non-speech samples. The recording",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://doi.org/10.35111/4ENA-FG30",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-rats-speaker-identification",
      "title": "RATS Speaker Identification",
      "url": "https://doi.org/10.35111/ZQET-2102",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Abstract Introduction RATS Speaker Identification was developed by the Linguistic Data Consortium (LDC) and is comprised of approximately 1,900 hours of Levantine Arabic, Farsi, Dari, Pashto and Urdu conversational telephone speech with ann",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://doi.org/10.35111/ZQET-2102",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-rats-speech-activity-detection",
      "title": "RATS Speech Activity Detection",
      "url": "https://hdl.handle.net/11272.1/AB2/1UISJ7",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Introduction RATS Speech Activity Detection was developed by the Linguistic Data Consortium (LDC) and is comprised of approximately 3,000 hours of Levantine Arabic, English, Farsi, Pashto, and Urdu conversational telephone speech with autom",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://hdl.handle.net/11272.1/AB2/1UISJ7",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-separating-phonology-from-syntax-a-reanalysis-of-pashto-cliticization",
      "title": "Separating phonology from syntax: a reanalysis of Pashto cliticization",
      "url": "https://doi.org/10.1017/s0022226700006952",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1017/s0022226700006952",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-shawanonymouse-pakhtoon",
      "title": "ShawAnonymouse/Pakhtoon",
      "url": "https://github.com/ShawAnonymouse/Pakhtoon",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Candidate Pashto-related GitHub repository.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/ShawAnonymouse/Pakhtoon",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-code-sinaahmadi-persoarabiclid",
      "title": "sinaahmadi/PersoArabicLID",
      "url": "https://github.com/sinaahmadi/PersoArabicLID",
      "category": "code",
      "source": "github",
      "status": "verified",
      "summary": "PALI: Language identification for Perso-Arabic Scripts",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "code",
        "github",
        "arabic",
        "balochi",
        "brahui"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/sinaahmadi/PersoArabicLID",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-dataset-smajram-a-large-scale-synthetic-ocr-dataset-for-punjabi-shahmukhi-perso-arabic-s",
      "title": "SMAjram: A Large-Scale Synthetic OCR Dataset for Punjabi Shahmukhi (Perso-Arabic) Script",
      "url": "https://zenodo.org/records/15868719",
      "category": "dataset",
      "source": "zenodo",
      "status": "verified",
      "summary": "This dataset is designed for the development, training, and evaluation of Optical Character Recognition (OCR) systems for the Shahmukhi (Perso-Arabic) script, with emphasis on character-level recognition, dataset scalability, and comparativ",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/15868719",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-some-remarks-on-the-origin-of-the-afgh-n-people-and-dialect-and-on-the-connexion",
      "title": "Some Remarks on the Origin of the Afghán People and Dialect and on the Connexion of the Pushto Language with the Zend and Pehlavi and the Hebrew",
      "url": "https://zenodo.org/records/16191315",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "(Uploaded by Plazi from the Biodiversity Heritage Library) No abstract provided.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/16191315",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-summaries-in-pashto",
      "title": "Summaries in Pashto",
      "url": "https://doi.org/10.1097/01.wtf.0000437933.40809.39",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.1097/01.wtf.0000437933.40809.39",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-project-tasal9-pashto-base-bloom-space",
      "title": "tasal9/pashto-base-bloom-space",
      "url": "https://huggingface.co/spaces/tasal9/pashto-base-bloom-space",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate project app returned from Hugging Face Spaces Pashto search.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "space"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/tasal9/pashto-base-bloom-space",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-project-tasal9-zamai-mt5-pashto-demo",
      "title": "tasal9/ZamAI-mt5-Pashto-Demo",
      "url": "https://huggingface.co/spaces/tasal9/ZamAI-mt5-Pashto-Demo",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate project app returned from Hugging Face Spaces Pashto search.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "space"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/tasal9/ZamAI-mt5-Pashto-Demo",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-the-bbn-byblos-pashto-ocr-system",
      "title": "The BBN Byblos Pashto OCR system",
      "url": "https://doi.org/10.1145/1031442.1031447",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1145/1031442.1031447",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-the-grammar-of-clitics-evidence-from-pashto-and-other-languages",
      "title": "The grammar of clitics : evidence from Pashto and other languages",
      "url": "http://hdl.handle.net/11858/00-001M-0000-0012-7447-0",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "http://hdl.handle.net/11858/00-001M-0000-0012-7447-0",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-the-influence-of-the-arabic-language-on-the-pashto-language-the-abdur-rahman-bab",
      "title": "The Influence of the Arabic Language on the Pashto Language: The Abdur-Rahman Baba as a Model (A Case Study Analysis)",
      "url": "https://zenodo.org/records/18174368",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "The mixing of languages shows how deeply they are connected and how they influence each other,s culture and language. Many Urdu and Persian words have been absorbed into the Pashto language. Likewise, Arabic words entered Pashto through Isl",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/18174368",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-the-pashto-language-and-identity-formation-in-pakistan",
      "title": "The Pashto language and identity‐formation in Pakistan",
      "url": "https://doi.org/10.1080/09584939508719759",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1080/09584939508719759",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-the-regional-criminal-law-framework-for-the-combat-of-organized-crime-pashto",
      "title": "The Regional Criminal Law Framework for the Combat of Organized Crime (Pashto)",
      "url": "https://opendata.uni-halle.de//handle/1981185920/123975",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "Today, powerful networks of criminal organizations with a range of coordinated activities in the form of organized crimes around the world with a great deal of impact in different fields are considered one of the most significant concerns i",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://opendata.uni-halle.de//handle/1981185920/123975",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-the-social-structure-and-organization-of-a-pakhto-speaking-community-in-afghanis",
      "title": "The Social Structure and Organization of A Pakhto Speaking Community in Afghanistan.",
      "url": "https://www.semanticscholar.org/paper/306e9a04b8835de6e906303b5e27d43a6994cb1d",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/306e9a04b8835de6e906303b5e27d43a6994cb1d",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-dataset-towards-a-typology-of-endoclitics",
      "title": "Towards a Typology of Endoclitics",
      "url": "https://zenodo.org/records/15041544",
      "category": "dataset",
      "source": "zenodo",
      "status": "verified",
      "summary": "This is a draft of my conference talk prepared for the 'Typology of Morphosyntactic Parameters 2016' conference (Moscow, 12-14 October 2016). I discuss the perspectives of developing a parametric theory of endoclitics and offer empiric gene",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/15041544",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-trad-arabic-french-parallel-text-newsgroup",
      "title": "TRAD Arabic-French Parallel Text -- Newsgroup",
      "url": "https://hdl.handle.net/11272.1/AB2/0DET8M",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Introduction TRAD Arabic-French Parallel Text – Newsgroup was developed by ELDA as part of the PEA-TRAD project. It contains French translations of a subset of approximately 10,000 Arabic words from GALE Phase 1 Arabic Newsgroup Parallel Te",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://hdl.handle.net/11272.1/AB2/0DET8M",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-trad-arabic-french-parallel-text-newswire",
      "title": "TRAD Arabic-French Parallel Text -- Newswire",
      "url": "https://doi.org/10.35111/Z1WG-9X78",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Abstract Introduction TRAD Arabic-French Parallel Text -- Newswire was developed by ELDA as part of the PEA-TRAD project. It contains French translations of a subset of approximately 20,000 Arabic words from NIST 2008 Open Machine Translati",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://doi.org/10.35111/Z1WG-9X78",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-trad-chinese-french-parallel-text-blog",
      "title": "TRAD Chinese-French Parallel Text -- Blog",
      "url": "https://hdl.handle.net/11272.1/AB2/ATYE6I",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Introduction TRAD Chinese-French Parallel Text – Blog was developed by ELDA as part of the PEA-TRAD project. It contains French translations of a subset of approximately 10,000 Chinese words from GALE Phase 1 Chinese Blog Parallel Text (LDC",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://hdl.handle.net/11272.1/AB2/ATYE6I",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-dataverse-dataset-trad-chinese-french-parallel-text-broadcast-news",
      "title": "TRAD Chinese-French Parallel Text -- Broadcast News",
      "url": "https://doi.org/10.35111/7FW4-EV85",
      "category": "dataset",
      "source": "dataverse",
      "status": "verified",
      "summary": "Abstract Introduction TRAD Chinese-French Parallel Text -- Broadcast News was developed by ELDA as part of the PEA-TRAD project. It contains French translations of a subset of approximately 30,000 Chinese characters from GALE Phase 1 Chines",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "dataset",
        "dataverse"
      ],
      "evidence_text": "Dataverse metadata includes Pashto markers in dataset title or description.",
      "evidence_url": "https://doi.org/10.35111/7FW4-EV85",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-resource",
      "title": "بلوچستان میں \" فقہ اسلامی \"   کے فروغ و ارتقا٫ کا تحقیقی جائزہ",
      "url": "https://zenodo.org/records/18049233",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "ABSTRACT Research-based review of the development and promotion of Islamic jurisprudence (Ilm al-Fiqh) in Balochistan during the twentieth century reveals that this century was truly a golden era for the growth and advancement of Islamic Fi",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/18049233",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-a-comparative-analysis-of-pashto-ghazals-and-english-sonnets-in-17th-century",
      "title": "A Comparative Analysis of Pashto Ghazals and English Sonnets in 17th Century",
      "url": "https://www.semanticscholar.org/paper/55b044485b2f134c69c9b9b6dfeaa7e71e704b3d",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "This study conducts a comparative analysis of Pashto ghazals and English sonnets in 17th century  to explore their unique structures, themes, and cultural significance. Utilizing descriptive and comparative methods, the study examines how t",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/55b044485b2f134c69c9b9b6dfeaa7e71e704b3d",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-an-acoustic-analysis-of-consonants-of-khattak-dialect-of-pashto",
      "title": "An Acoustic Analysis of consonants of Khattak Dialect of Pashto",
      "url": "https://www.semanticscholar.org/paper/ed06d206e60a62c2bebdd487b4f8dea253a9a0a8",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Pashto, an ancient language written in Perso-Arabic script, is predominantly spoken in Pakistan's Khyber Pakhtunkhwa Province and Afghanistan. Despite its wide usage, more research is needed on the consonantal sounds of the Khattak dialect.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/ed06d206e60a62c2bebdd487b4f8dea253a9a0a8",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-an-analysis-of-freudian-concept-of-mourning-in-pashto-tappas-on-the-theme-of-mig",
      "title": "AN ANALYSIS OF FREUDIAN CONCEPT OF MOURNING IN PASHTO TAPPAS ON THE THEME OF MIGRATION",
      "url": "https://zenodo.org/records/11124039",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "Folk literature of any nation is its collective asset and is the preserver of its social history and culture. The most important genre of Pashto folk poetry is tappa. Tappa is composed of a couplet. It covers all aspects of the Pashtuns’ wa",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/11124039",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-an-analysis-of-the-syntactic-and-pragmatic-effects-on-word-order-flexibility-in-",
      "title": "An Analysis of the Syntactic and Pragmatic Effects on Word Order Flexibility in Pashto and English",
      "url": "https://www.semanticscholar.org/paper/136c23f176399f7dfc45e6ae990a975aafd7da1d",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "This research explores the syntactic and pragmatic aspects that condition word order flexibility in Pashto and English, comparing how the two languages communicate emphasis, focus, and topicalization. This paper compares the flexibility of",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/136c23f176399f7dfc45e6ae990a975aafd7da1d",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-analysing-deep-meaning-of-proverbs-in-pashto-language",
      "title": "Analysing Deep Meaning of Proverbs in Pashto Language",
      "url": "https://www.semanticscholar.org/paper/1a804a9701c5103ed38df3350da61abdf5df2b57",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "As other ancient languages of the world, Pashto is one of them having  rich folkloric literature. One of the most important part of this literature is proverbs, which makes a special part of history of this language. These proverbs shows  d",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/1a804a9701c5103ed38df3350da61abdf5df2b57",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-zenodo-paper-challenging-gender-roles-a-feminist-analysis-of-ghani-khan-s-the-pathans",
      "title": "CHALLENGING GENDER ROLES: A FEMINIST ANALYSIS OF GHANI KHAN'S THE PATHANS",
      "url": "https://zenodo.org/records/11216862",
      "category": "paper",
      "source": "zenodo",
      "status": "verified",
      "summary": "The present research aims to analyse the representation of gender dynamics in Ghani Khan’s The Pathans who is also known as Lewanai Phalsafi (The Lunatic Philosopher), is a towering literary figure in Pashto literature. He is commonly known",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "zenodo"
      ],
      "evidence_text": "Zenodo metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/records/11216862",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-cinematic-misnomers-examining-the-effects-of-pashto-movie-titles-on-the-percepti",
      "title": "Cinematic Misnomers: Examining the Effects of Pashto Movie Titles on the Perception of Pashtun Identity",
      "url": "https://www.semanticscholar.org/paper/1b4c38ce4ceb6ac7846062bb589351cc88a36617",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "The current research is a critical study of the impacts of inappropriate and misleading titles of Pashtu movies on the perception of Pashtun identity. Because most of the titles are abusive and immoral in nature and do not conform to the st",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/1b4c38ce4ceb6ac7846062bb589351cc88a36617",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-comparative-study-of-adjectives-in-pashto-and-dari-as-cognate-languages",
      "title": "Comparative Study of Adjectives in Pashto and Dari as Cognate Languages",
      "url": "https://www.semanticscholar.org/paper/558e9dd7d4027be391a39f5e5ef988cf05039dc7",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "In Pashto, adjectives align with nouns in terms of number, gender, and case, which distinguishthem from adjectives in Modern Persian-Dari. In both Old and Modern Persian, unlike in Pashto, adjectives are divided into two categories: attribu",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/558e9dd7d4027be391a39f5e5ef988cf05039dc7",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-comprehensive-socio-phonetic-study-of-the-plosive-p-and-fricative-f-merger-among",
      "title": "Comprehensive Socio-phonetic Study of the Plosive /p/ and Fricative /f/ Merger among Pashto Speakers in Khyber Pakhtunkhwa",
      "url": "https://www.semanticscholar.org/paper/4f01f2250c897dc53099f76a2455471b480f22cf",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Introduction: The phonological systems of a first language (L1) can fundamentally constrain the acquisition of a second language (L2), particularly in speech sound perception and production. In Pashto-English bilinguals, the absence of the",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/4f01f2250c897dc53099f76a2455471b480f22cf",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-essential-skills-for-a-lexicographer-based-on-pashto-lexicography",
      "title": "Essential Skills for a Lexicographer: Based on Pashto Lexicography",
      "url": "https://www.semanticscholar.org/paper/8fc45aa567cb78713e2fef41d5e748e8ee1d8470",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "How Pashto dictionaries meet rules of modern lexicography? Lexicography is a division of linguistic working on recording and developing data of languages. Pashto is one of the languages which do not have many resources in lexicography. Most",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/8fc45aa567cb78713e2fef41d5e748e8ee1d8470",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-exploring-the-impacts-of-emotion-through-language-learning-on-pashto-speakers-yo",
      "title": "Exploring the Impacts of Emotion through Language Learning on Pashto Speakers Young Adulthood in District Peshawar",
      "url": "https://www.semanticscholar.org/paper/4549649112553aabccfac8b918c7e98cdbdd0f09",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "The current study explores the emotional experiences of Pashto speakers learning a second language, with a focus on how emotions are expressed, understood, and influenced by cultural and linguistic factors. While language learning is often",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/4549649112553aabccfac8b918c7e98cdbdd0f09",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-fragments-of-life-in-death-world-an-analysis-of-pashto-poetry-as-a-non-violent-r",
      "title": "Fragments of life in ‘death world’: an analysis of Pashto poetry as a non-violent resistance to necropolitics",
      "url": "https://www.semanticscholar.org/paper/9726f372b07f677fad23e2ee27a7f50f985e8ed8",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/9726f372b07f677fad23e2ee27a7f50f985e8ed8",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-gender-classification-from-pashto-handwritten-text-images",
      "title": "Gender Classification From Pashto Handwritten Text Images",
      "url": "https://www.semanticscholar.org/paper/2d70fffa9224d71f67ad3c1943b8a71b18164eeb",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Computer vision (CV) is a subfield of computer science that enables machines to perceive, interpret, and understand visual data. It combines image processing, analysis, and machine learning to extract meaningful insights from images and vid",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/2d70fffa9224d71f67ad3c1943b8a71b18164eeb",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-project-haseeb-007-pashto-sekho",
      "title": "Haseeb-007/Pashto-sekho",
      "url": "https://huggingface.co/spaces/Haseeb-007/Pashto-sekho",
      "category": "project",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate project app returned from Hugging Face Spaces Pashto search.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "space"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face Spaces search.",
      "evidence_url": "https://huggingface.co/spaces/Haseeb-007/Pashto-sekho",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-hf-model-ijazulhaq-bert-base-pashto-c",
      "title": "ijazulhaq/bert-base-pashto-c",
      "url": "https://huggingface.co/ijazulhaq/bert-base-pashto-c",
      "category": "model",
      "source": "huggingface",
      "status": "verified",
      "summary": "Candidate model returned from Hugging Face search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "model"
      ],
      "evidence_text": "Matched by Pashto keyword in Hugging Face search results.",
      "evidence_url": "https://huggingface.co/ijazulhaq/bert-base-pashto-c",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-introduction-to-pashto-word-s-characteristics",
      "title": "Introduction to Pashto Word’s Characteristics",
      "url": "https://www.semanticscholar.org/paper/6eb3febbb368a7eaccc6290bcd77683ed3d624aa",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "This study investigates the distinctive characteristics of Pashto words, focusing on their phonological, morphological, and semantic features. Pashto, an Eastern Iranian language spoken primarily in Afghanistan and Pakistan, exhibits a rich",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/6eb3febbb368a7eaccc6290bcd77683ed3d624aa",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-project-introduction-to-postpartum-care-for-refugee-women-pashto",
      "title": "Introduction to Postpartum Care for Refugee women [Pashto]",
      "url": "https://zenodo.org/doi/10.5281/zenodo.18324878",
      "category": "project",
      "source": "datacite",
      "status": "verified",
      "summary": "Candidate record returned from DataCite DOI search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/doi/10.5281/zenodo.18324878",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-isolated-handwritten-pashto-character-recognition-using-a-i-k-i-nn-classificatio",
      "title": "Isolated Handwritten Pashto Character Recognition Using a <i>K</i>‐NN Classification Tool based on Zoning and HOG Feature Extraction Techniques",
      "url": "https://doi.org/10.1155/2021/5558373",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1155/2021/5558373",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-le-verbe-pashto",
      "title": "Le verbe pashto",
      "url": "https://doi.org/10.29091/9783954907083",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.29091/9783954907083",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-lecramyajiv-fonts-arabic-extra",
      "title": "lecramyajiv/fonts-arabic-extra",
      "url": "https://github.com/lecramyajiv/fonts-arabic-extra",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Extra Arabic fonts for Slackware Linux",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "arabic",
        "fonts",
        "kufi"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/lecramyajiv/fonts-arabic-extra",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-project-negation-in-pashto",
      "title": "Negation in Pashto",
      "url": "https://zenodo.org/doi/10.5281/zenodo.18233956",
      "category": "project",
      "source": "datacite",
      "status": "verified",
      "summary": "In this paper, we explore negation in Pashto – an Eastern Iranian language spoken mainly in Pakistan and Afghanistan. Based on the Yousafzai dialect of Pashto,with the questionnaire provided by the editors as our main instrument, we investi",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://zenodo.org/doi/10.5281/zenodo.18233956",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-pashto-free-relatives-and-triply-filled-comp-evidence-for-a-headed-analysis",
      "title": "Pashto free relatives and triply-filled Comp: Evidence for a headed analysis",
      "url": "https://doi.org/10.1016/s0024-3841(96)00032-0",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1016/s0024-3841(96)00032-0",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-pashto-preverbs-v",
      "title": "Pashto preverbs V",
      "url": "https://www.semanticscholar.org/paper/1f59f22ae99379106b417186f3053c00b5fe391f",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Abstract This article deals with the perfective preverb wə́-. Pashto wə́- cannot be studied separately from aspectual oppositions: in fact, wə́- characterizes the “perfective” of simple verbs. Therefore, a quick review of aspect in Pashto w",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/1f59f22ae99379106b417186f3053c00b5fe391f",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-pashto-preverbs-iii-compound-verbs-with-preverb",
      "title": "Pashto preverbs, III. Compound verbs with preverb",
      "url": "https://www.semanticscholar.org/paper/53eeae3a973d6bb72839e9304be13a0362c92242",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Abstract This article, the third in a series, focuses on the “living” preverbs used in the verbal system of contemporary Pashto. The verbs treated here belong to the “compound verbs with preverb” class or to the “mixed verbs with preverb” c",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/53eeae3a973d6bb72839e9304be13a0362c92242",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-datacite-paper-psocr-benchmarking-large-multimodal-models-for-optical-character-recognition-in-",
      "title": "PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language",
      "url": "https://arxiv.org/abs/2505.10055",
      "category": "paper",
      "source": "datacite",
      "status": "verified",
      "summary": "This paper evaluates the performance of Large Multimodal Models (LMMs) on Optical Character Recognition (OCR) in the low-resource Pashto language. Natural Language Processing (NLP) in Pashto faces several challenges due to the cursive natur",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "datacite"
      ],
      "evidence_text": "DataCite metadata includes Pashto markers in title or description.",
      "evidence_url": "https://arxiv.org/abs/2505.10055",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-arxiv-psocr-benchmarking-large-multimodal-models-for-optical-character-recognition-in-",
      "title": "PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language",
      "url": "http://arxiv.org/abs/2505.10055v2",
      "category": "paper",
      "source": "arxiv",
      "status": "verified",
      "summary": "This paper evaluates the performance of Large Multimodal Models (LMMs) on Optical Character Recognition (OCR) in the low-resource Pashto language. Natural Language Processing (NLP) in Pashto faces several challenges due to the cursive natur",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by Pashto marker in paper title from arXiv query results.",
      "evidence_url": "http://arxiv.org/abs/2505.10055v2",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-pukhtoonmafia009-pukhtoonmafia009",
      "title": "Pukhtoonmafia009/Pukhtoonmafia009",
      "url": "https://github.com/Pukhtoonmafia009/Pukhtoonmafia009",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Config files for my GitHub profile.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "config",
        "github-config"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/Pukhtoonmafia009/Pukhtoonmafia009",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-pukhtoonyar406-pukhtoonyar406",
      "title": "pukhtoonyar406/pukhtoonyar406",
      "url": "https://github.com/pukhtoonyar406/pukhtoonyar406",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "Config files for my GitHub profile.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "config",
        "github-config"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/pukhtoonyar406/pukhtoonyar406",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-openalex-scale-and-rotation-invariant-recognition-of-cursive-pashto-script-using-sift-fea",
      "title": "Scale and rotation invariant recognition of cursive Pashto script using SIFT features",
      "url": "https://doi.org/10.1109/icet.2010.5638470",
      "category": "paper",
      "source": "openalex",
      "status": "verified",
      "summary": "Candidate paper returned from OpenAlex works search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "openalex"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from OpenAlex works search.",
      "evidence_url": "https://doi.org/10.1109/icet.2010.5638470",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-gh-project-shahzamanpatan-pashto-baran",
      "title": "ShahZamanPatan/Pashto-Baran",
      "url": "https://github.com/ShahZamanPatan/Pashto-Baran",
      "category": "project",
      "source": "github",
      "status": "verified",
      "summary": "پښتو باران يوه پښتو ليکبڼه ده چې په ځانګړې توګه د پښتو ژبې وېبپاڼو لپاره د نازنين او اېکس بي کيهان ليکبڼو تر اغېز لاندې ډيزاين شوې ده تاسو کولی شئ ياده ليکبڼه هرځای کې له وړيا سوداګريزې کارونې جواز سره د پښتو، اردو، عربي، فارسي، کهوار، سرائ",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "project",
        "github",
        "fonts",
        "freepashtofonts",
        "pashto"
      ],
      "evidence_text": "Repository metadata (name/description/topics) includes Pashto markers.",
      "evidence_url": "https://github.com/ShahZamanPatan/Pashto-Baran",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-switching-selves-online-pashto-english-bilingualism-identity-and-expression-in-p",
      "title": "SWITCHING SELVES ONLINE:PASHTO-ENGLISH BILINGUALISM,IDENTITY, AND EXPRESSION IN PAKISTAN’S DIGITAL DISCOURSE",
      "url": "https://www.semanticscholar.org/paper/7a330c5fb416a1105866a895748b4336f8ef8100",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "The language in modern digital realms goes beyond its message carrying center; it serves as a mirror of itself in identity, emotion, and cultural location. The current paper examines what happens when Pashto-English bilinguals in Pakistan n",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/7a330c5fb416a1105866a895748b4336f8ef8100",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-syntax-and-morphology-of-baniswola-pashto-investigating-universal-and-dialectal-",
      "title": "Syntax and morphology of Baniswola Pashto: investigating universal and dialectal variations",
      "url": "https://www.semanticscholar.org/paper/9f725b3b282cf05f9089002d474010c6021001f9",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/9f725b3b282cf05f9089002d474010c6021001f9",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-the-development-and-evaluation-of-an-automatic-clitic-generator-for-pashto-langu",
      "title": "The development and evaluation of an automatic clitic generator for Pashto language",
      "url": "https://www.semanticscholar.org/paper/3d95449d67799fcac83f855984cb0c29cc500d7b",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Candidate paper returned from Semantic Scholar search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/3d95449d67799fcac83f855984cb0c29cc500d7b",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-the-role-of-early-literary-biographies-tazkiri-in-the-ancient-history-of-pashto-",
      "title": "The Role of Early Literary Biographies (Tazkiri) in the Ancient History of Pashto Literature",
      "url": "https://www.semanticscholar.org/paper/4938170077d3430c2e3f9fadc161ed7b79242917",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "The role of early literary biographies in the ancient history of Pashto literature is a significant and fundamental subject, as these biographies have transmitted to us the thoughts, styles, and contributions of early poets, writers, and Su",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/4938170077d3430c2e3f9fadc161ed7b79242917",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-s2-the-roshani-movement-literary-services-and-the-contribution-of-this-movement-in-",
      "title": "The Roshani Movement literary services and the contribution of this Movement in the development of Pashto Literature",
      "url": "https://www.semanticscholar.org/paper/88a3cd1ec497844c5997ae1795f8e72bbb314112",
      "category": "paper",
      "source": "other",
      "status": "verified",
      "summary": "Literature is the mirror of society. The purpose of this article was to review the achievements and literary services of the Roshani Movement, in order to use their positive points in the development of Pashto language and literature. The r",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper"
      ],
      "evidence_text": "Matched by explicit Pashto marker in paper title from Semantic Scholar search.",
      "evidence_url": "https://www.semanticscholar.org/paper/88a3cd1ec497844c5997ae1795f8e72bbb314112",
      "markers": [
        "pashto"
      ]
    },
    {
      "id": "candidate-crossref-topicalization-in-pashto",
      "title": "Topicalization in Pashto",
      "url": "https://doi.org/10.31703/gssr.2020(v-i).17",
      "category": "paper",
      "source": "crossref",
      "status": "verified",
      "summary": "Candidate paper returned from Crossref search for Pashto.",
      "primary_use": "Automated discovery entry for Pashto resource tracking.",
      "tasks": [],
      "tags": [
        "pashto",
        "candidate",
        "paper",
        "crossref"
      ],
      "evidence_text": "Matched by explicit Pashto marker in title from Crossref search.",
      "evidence_url": "https://doi.org/10.31703/gssr.2020(v-i).17",
      "markers": [
        "pashto"
      ]
    }
  ]
}