superpaper/assets/ledger.schema.yaml

$schema: "http://json-schema.org/draft-07/schema#"
$id: "https://local/superpaper.ledger/v1"
type: object
required: [schema, paper, coverage]
additionalProperties: true
properties:
  schema: {const: superpaper.ledger/v1}
  retired_ids:
    type: array
    items: {type: string, pattern: "^(C|Q|D|A|L|E|DER|F|SA)[1-9][0-9]*$"}
  paper:
    type: object
    required: [id, title, source]
    additionalProperties: true
    properties:
      id: {type: string, minLength: 1}
      title: {type: string}
      authors: {type: array, items: {type: string}}
      year: {type: integer}
      venue: {type: string}
      notes_language: {type: string, enum: [zh, en]}
      degraded:
        type: array
        items: {type: string, enum: [scanned, no-eprint, no-pdftotext]}
      source:
        type: object
        required: [kind]
        additionalProperties: true
        properties:
          kind: {enum: [arxiv, pdf, tex, excerpt, markdown]}
          arxiv: {type: string}
          local_pdf: {type: string}
          pages: {type: integer, minimum: 1}
          language: {type: string}
  coverage:
    type: object
    required: [mode]
    additionalProperties: true
    properties:
      mode: {enum: [full, excerpt, body-only]}
      sections_in: {type: array, items: {type: string}}
      sections_skipped: {type: array, items: {type: string}}
      skip_reasons:
        type: array
        items:
          type: object
          required: [section, reason]
          properties:
            section: {type: string}
            reason: {type: string}
  questions:
    type: array
    items:
      type: object
      required: [id, text]
      properties:
        id: {type: string, pattern: "^Q[1-9][0-9]*$"}
        text: {type: string}
        source: {type: string}
  claims:
    type: array
    items:
      type: object
      required: [id, text, kind, status]
      properties:
        id: {type: string, pattern: "^C[1-9][0-9]*$"}
        text: {type: string}
        kind: {enum: [contribution, theoretical, empirical, methodological]}
        status: {enum: [core, supporting, dropped]}
        supports: {type: array, items: {type: string}}
        depends_on: {type: array, items: {type: string}}
        evidence: {type: array, items: {type: string}}
        source: {type: string}
  definitions:
    type: array
    items:
      type: object
      required: [id, name, text]
      properties:
        id: {type: string, pattern: "^D[1-9][0-9]*$"}
        name: {type: string}
        text: {type: string}
        source: {type: string}
  assumptions:
    type: array
    items:
      type: object
      required: [id, text]
      properties:
        id: {type: string, pattern: "^A[1-9][0-9]*$"}
        text: {type: string}
        source: {type: string}
        used_by: {type: array, items: {type: string}}
  lemmas:
    type: array
    items:
      type: object
      required: [id, text]
      properties:
        id: {type: string, pattern: "^L[1-9][0-9]*$"}
        text: {type: string}
        depends_on: {type: array, items: {type: string}}
        used_by: {type: array, items: {type: string}}
        source: {type: string}
  symbols:
    type: array
    items:
      type: object
      required: [name, latex, meaning, kind]
      properties:
        name: {type: string}
        latex: {type: string}
        meaning: {type: string}
        domain: {type: string}
        kind:
          enum: [value, score, probability, index, rank, count, id, mask,
                 permutation, "shape parameter", scalar, set]
        introduced: {type: string}
        used: {type: array, items: {type: string}}
        aliases: {type: array, items: {type: string}}
  derivations:
    type: array
    items:
      type: object
      required: [id, claim, title, expand]
      properties:
        id: {type: string, pattern: "^DER[1-9][0-9]*$"}
        claim: {type: string}
        title: {type: string}
        source: {type: string}
        expand: {type: boolean}
        figure: {type: ["string", "null"]}
        steps:
          type: array
          items:
            type: object
            required: [id, from, to, rule]
            properties:
              id: {type: string}
              from: {type: string}
              to: {type: string}
              rule:
                enum: [definition, substitute, cancel, factor, scale,
                       take-limit, approx, cite, rearrange, introduce]
              cite: {type: string}
              justify: {type: string}
  figures:
    type: array
    items:
      type: object
      required: [id, claim, title, grammar, toolkit, signals, status]
      properties:
        id: {type: string, pattern: "^F[1-9][0-9]*$"}
        claim: {type: string}
        title: {type: string}
        grammar:
          enum: [architecture, pipeline, data-flow, state, time, dependency,
                 argument-map, tensor-face, derivation, screenshot, plot,
                 notation, none]
        toolkit:
          enum: [superfig, supertensor, superderive, screenshot,
                 matplotlib, none, align]
        signals: {type: array, items: {type: string}}
        source_fig: {type: string}
        source_pages: {type: array, items: {type: integer, minimum: 1}}
        crop_bbox:
          type: ["array", "null"]
          minItems: 4
          maxItems: 4
          items: {type: number}
        request: {type: ["string", "null"]}
        include: {type: ["string", "null"]}
        status: {enum: [planned, delegated, built, included, dropped]}
        drop_reason: {type: ["string", "null"]}
  evidence:
    type: array
    items:
      type: object
      required: [id, kind, source, supports, handling]
      properties:
        id: {type: string, pattern: "^E[1-9][0-9]*$"}
        kind: {enum: [table, plot, ablation, theorem, example]}
        source: {type: string}
        supports: {type: array, items: {type: string}}
        handling:
          enum: [redraw-superfig, redraw-supertensor, redraw-superderive,
                 screenshot, matplotlib, omit]
  terms:
    type: array
    items:
      type: object
      required: [canonical]
      properties:
        canonical: {type: string}
        aliases: {type: array, items: {type: string}}
        first_defined: {type: string}
  source_assets:
    type: array
    items:
      type: object
      required: [id, kind, handling]
      properties:
        id: {type: string, pattern: "^SA[1-9][0-9]*$"}
        kind: {enum: [figure, table]}
        paper_ref: {type: string}
        handling:
          enum: [redraw-superfig, redraw-supertensor, redraw-superderive,
                 screenshot, matplotlib, omit]
        pages: {type: array, items: {type: integer}}
        note: {type: string}