example.jsonl

{
  "documentary_role": {
    "reason": "The text contains technical, scientific data regarding water quality, including specific chemical parameters (pH, iron content, oxygen levels), measurements (area in km2, rainfall in mm), and an analysis of environmental impact caused by logging activities. This scientific and analytical approach is characteristic of research or scientific discourse.",
    "classes": [
      "scholarly"
    ]
  },
  "emotional_tone": {
    "reason": "The text is a scientific/technical report presenting hydrological data, measurements (area, pH, oxygen levels), and the physical impact of a specific event on water quality. The language is purely descriptive, objective, and lacks any emotional coloring or subjective commentary.",
    "classes": [
      "neutral_or_detached"
    ]
  },
  "narrative_perspective": {
    "reason": "The text is a scientific/technical report focused on environmental measurements and data. It lacks any first-person or second-person pronouns. The grammatical subjects are impersonal or inanimate entities, such as 'source of pollution', 'intervention', 'end profile', and 'quality', with no prominent personal agent.",
    "classes": [
      "third_person_impersonal"
    ]
  },
  "language": "ces",
  "document": "ce2541d0-d33f-11ea-9a89-005056825209",
  "cluster_id": 2867,
  "style": {
    "reason": "The text is highly precise, analytical, and uses technical/scientific terminology (e.g., 'pH', 'vodíkových iontů', 'kysíkovém režimu', 'koncentrace') and quantitative data to report findings, which is characteristic of a research or technical study style.",
    "classes": [
      "scholarly"
    ]
  },
  "start_page_id": "faee717c-7074-4367-b41e-515cffb92df2",
  "to_page": 55,
  "order": 320,
  "complexity": {
    "reason": "The text is a technical scientific report (likely environmental or hydrological) containing specialized terminology such as 'kyslíkový režim' (oxygen regime), 'koncentrace vodíkových iontů pH' (hydrogen ion concentration), and 'bodový zdroj znečištění' (point source of pollution). It also presents dense quantitative data and environmental classification systems, which require domain-specific knowledge to fully interpret.",
    "classes": [
      "advanced"
    ]
  },
  "end_paragraph": false,
  "vector_index": 320,
  "id": "3271d732-3fd6-42cb-9371-9b95648d47ef",
  "textual_stance": {
    "reason": "The passage goes beyond simple description by interpreting environmental measurements (pH, iron, oxygen) to assign specific quality classes and by framing a specific event (logging) as the cause of pollution. Furthermore, the language used, such as 'Prokazatelně' (demonstrably) and 'jednoznačně' (unambiguously), demonstrates a high level of certainty and authoritative assertion.",
    "classes": [
      "interpretive",
      "committed_assertive"
    ]
  },
  "reliability_signals": {
    "reason": "The passage provides specific numerical data, including area measurements (km2), precise timestamps, rainfall amounts (24 mm), and specific chemical/physical water quality classifications (III, IV, and V classes) to support the claim of pollution.",
    "classes": [
      "evidence_based"
    ]
  },
  "information_granularity": {
    "reason": "The text describes a specific, instance-level event: a pollution incident in the Bílá Ostravice river basin caused by logging with an LKT tractor following a specific rainfall event (with precise dates, times, and amounts). It also provides highly precise measurements and classifications regarding water quality (pH, oxygen, and iron levels) and area.",
    "classes": [
      "highly_specific"
    ]
  },
  "intertextual_density": {
    "reason": "The text is a technical description of hydrological observations and water quality measurements. It contains no citations, quotations, or explicit references to other authors, works, or scientific literature.",
    "classes": [
      "no_references"
    ]
  },
  "text": "Sp = 0,15; 6,75; 14,54 a 42,49 km2.\nProkazatelně nejnižší kvalitu vykázal zdroj znečištění v koncové části povodí po\npřiblížení asi 2 svazků vytěženého dříví kolovým traktorem LKT zhruba do 4 h po\nustání regionálního deště (od 9.7 ve 23,45 h do 10. 7. v 10,50 h úhrn 24 mm). Svými\núčinky tento ojedinělý zásah ovlivnil prakticky celou délku toku rozsáhlého povodí\nBílé Ostravice s výměrou Sp = 42,49 km2. Koncový profil vykázal v kyslíkovém režimu\nIII. třídu kvality, obsahy veškerého železa a koncentrace vodíkových iontů pH zařadily\ntento vzorek do IV. třídy a nerozpuštěné látky jednoznačně do nejnižší V. třídy kvality.\nSměrem po toku se sice kvalita poněkud postupným nařeďováním zlepšila, ale přesto\ntento téměř bodový zdroj znečištění (koncové dotčené povodíčko představuje 2,4",
  "named_entity_focus": {
    "reason": "The passage focuses on the water quality and pollution levels within a specific geographic feature, the Bílé Ostravice river basin (povodí Bílé Ostravice).",
    "classes": [
      "place_centric"
    ]
  },
  "subject_domain": {
    "reason": "The passage describes scientific measurements and observations regarding water quality (pH, oxygen levels, iron content, undissolved matter), hydrology (the Bílá Ostravice river basin), and the environmental impact of rainfall and forestry activities. This falls under the domain of natural sciences, specifically hydrology and environmental science.",
    "classes": [
      "ddc_500_natural_sciences"
    ]
  },
  "temporal_reference_frame": {
    "reason": "The passage describes a specific, recent environmental event involving rainfall and logging (dated July 9th and 10th) and its immediate impact on water quality, which constitutes a report of events current or recent to the time of the study/writing.",
    "classes": [
      "contemporary_to_authorship"
    ]
  },
  "communicative_mode": {
    "reason": "The text explains the causal relationship between forestry activities, rainfall, and the resulting decline in water quality (exposition) while documenting specific scientific measurements, dates, and observations (record).",
    "classes": [
      "exposition",
      "record"
    ]
  },
  "from_page": 55,
  "structural_form": {
    "reason": "The text consists of complete sentences and paragraphs describing environmental observations and water quality data in a narrative format.",
    "classes": [
      "continuous_prose"
    ]
  },
  "geographic_scope": {
    "reason": "The text focuses on a specific, relatively small geographic area: the watershed of the Bílá Ostravice (povodí Bílé Ostravice), which is explicitly measured at 42.49 km². This describes a specific hydrological feature and its local environmental impact.",
    "classes": [
      "local_or_municipal"
    ]
  }
}