infra/paperspec
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit
check / check (macos-latest) (push) Canceled after 0s
Details
check / check (ubuntu-latest) (push) Canceled after 0s
Details

Browse Source
This commit is contained in:
alexm committed 2026-10-11 23:45:29 -04:00
commit 62f54ed869
373 files changed
+16704
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

registry/formats.json
+222
View File
@@ -0,0 +1,222 @@
{
"registry": "formats",
"version": "0.1.0",
"formats": [
{
"format": "scienting-package/1",
"media_type": "application/vnd.scienting.doc+zip",
"schema": "manifest.schema.json",
"status": "candidate",
"chapter": "spec/12-package.md",
"description": "A package: MANIFEST.json and its files, a folder or a zip."
},
{
"format": "scienting-doc/1",
"media_type": "application/vnd.scienting.doc+json",
"schema": "document.schema.json",
"status": "candidate",
"chapter": "spec/02-model.md",
"description": "A document: document.json, with nodes.jsonl and the package's other files."
},
{
"format": "scienting-page/1",
"media_type": null,
"schema": "page.schema.json",
"status": "candidate",
"chapter": "spec/07-geometry.md",
"description": "The page fingerprint function, and a page record."
},
{
"format": "scienting-anchor/1",
"media_type": "application/vnd.scienting.anchor+json",
"schema": "anchor.schema.json",
"status": "candidate",
"chapter": "spec/06-anchors.md",
"description": "A pinned address with enough context to survive change."
},
{
"format": "scienting-correction/1",
"media_type": "application/vnd.scienting.correction+json",
"schema": "correction.schema.json",
"status": "candidate",
"chapter": "spec/11-corrections.md",
"description": "An operation on an established document."
},
{
"format": "scienting-receipt/1",
"media_type": "application/vnd.scienting.receipt+json",
"schema": "receipt.schema.json",
"status": "candidate",
"chapter": "spec/08-fidelity.md",
"description": "A signature over a Merkle root of reviewed values."
},
{
"format": "scienting-revocation/1",
"media_type": "application/vnd.scienting.revocation+json",
"schema": "revocation.schema.json",
"status": "candidate",
"chapter": "spec/08-fidelity.md",
"description": "A signed withdrawal of receipts."
},
{
"format": "scienting-roster/1",
"media_type": "application/vnd.scienting.roster+json",
"schema": "roster.schema.json",
"status": "candidate",
"chapter": "spec/08-fidelity.md",
"description": "The keys that may sign, and for what."
},
{
"format": "scienting-qa-report/1",
"media_type": "application/vnd.scienting.qa-report+json",
"schema": "qa-report.schema.json",
"status": "candidate",
"chapter": "spec/08-fidelity.md",
"description": "Reviewer error bounds for a delivery."
},
{
"format": "scienting-rights/1",
"media_type": "application/vnd.scienting.rights+json",
"schema": "rights.schema.json",
"status": "candidate",
"chapter": "spec/14-rights.md",
"description": "A witness's license, basis and uses."
},
{
"format": "scienting-policy/1",
"media_type": "application/vnd.scienting.policy+json",
"schema": "policy.schema.json",
"status": "candidate",
"chapter": "spec/14-rights.md",
"description": "A signed team decision that resolves unknown uses."
},
{
"format": "scienting-stages/1",
"media_type": "application/vnd.scienting.stages+json",
"schema": "stages.schema.json",
"status": "candidate",
"chapter": "spec/14-rights.md",
"description": "The uses each stage needs."
},
{
"format": "scienting-backend/1",
"media_type": "application/vnd.scienting.backend+json",
"schema": "backend.schema.json",
"status": "candidate",
"chapter": "spec/14-rights.md",
"description": "A tool's code and weight licenses and their conditions."
},
{
"format": "scienting-profile/1",
"media_type": "application/vnd.scienting.profile+json",
"schema": "profile.schema.json",
"status": "candidate",
"chapter": "spec/14-rights.md",
"description": "What backend conditions ask about a team."
},
{
"format": "scienting-stamps/1",
"media_type": "application/vnd.scienting.stamps+json",
"schema": "stamps.schema.json",
"status": "candidate",
"chapter": "spec/07-geometry.md",
"description": "Download-stamp line rules."
},
{
"format": "scienting-suspect/1",
"media_type": null,
"schema": "suspect.schema.json",
"status": "candidate",
"chapter": "spec/05-hashes.md",
"description": "A doubtful reading for review."
},
{
"format": "scienting-layer/1",
"media_type": "application/ld+json; profile=\"http://www.w3.org/ns/anno.jsonld\"",
"schema": "layer.schema.json",
"status": "candidate",
"chapter": "spec/18-layers.md",
"description": "A layer of W3C Web Annotations."
},
{
"format": "scienting-exercise/1",
"media_type": null,
"schema": "exercise.schema.json",
"status": "candidate",
"chapter": "spec/19-exercises.md",
"description": "The body of an exercise annotation."
},
{
"format": "scienting-submission/1",
"media_type": "application/vnd.scienting.submission+json",
"schema": "submission.schema.json",
"status": "candidate",
"chapter": "spec/19-exercises.md",
"description": "A student's answer under a pseudonym."
},
{
"format": "scienting-grade/1",
"media_type": "application/vnd.scienting.grade+json",
"schema": "grade.schema.json",
"status": "candidate",
"chapter": "spec/19-exercises.md",
"description": "The grader's result."
},
{
"format": "scienting-project/1",
"media_type": "application/vnd.scienting.project+json",
"schema": "project.schema.json",
"status": "provisional",
"chapter": "spec/20-projects.md",
"description": "A project."
},
{
"format": "scienting-bundle/1",
"media_type": "application/vnd.sqlite3",
"schema": "sql/bundle-sqlite.sql",
"status": "provisional",
"chapter": "spec/13-database.md",
"description": "The SQLite bundle readers and servers query."
},
{
"format": "scienting-dataset/1",
"media_type": "application/vnd.scienting.dataset+json",
"schema": "dataset.schema.json",
"status": "provisional",
"chapter": "spec/15-datasets.md",
"description": "A Frictionless Data Package with units, uncertainty and origin."
},
{
"format": "scienting-digitization/1",
"media_type": "application/vnd.scienting.digitization+json",
"schema": "digitization.schema.json",
"status": "provisional",
"chapter": "spec/16-digitization.md",
"description": "How values were read off a figure panel."
},
{
"format": "scienting-view/1",
"media_type": "application/vnd.vegalite+json",
"schema": "view.schema.json",
"status": "provisional",
"chapter": "spec/17-views.md",
"description": "A Vega-Lite view that pins its data."
},
{
"format": "scienting-snapshot/1",
"media_type": "application/vnd.scienting.snapshot+json",
"schema": "snapshot.schema.json",
"status": "provisional",
"chapter": "spec/21-drafts.md",
"description": "What a draft cites, pinned."
},
{
"format": "scienting-draft-ids/1",
"media_type": null,
"schema": "draft-ids.schema.json",
"status": "provisional",
"chapter": "spec/21-drafts.md",
"description": "A Typst project's sentence-ID sidecar."
}
]
}
registry/rules.json
+442
View File
@@ -0,0 +1,442 @@
{
"registry": "rules",
"version": "0.1.0",
"note": "Rule IDs name each refusal, so tools report file, node and rule in the form path:line: rule: message.",
"rules": [
{
"id": "correction.digits",
"description": "A digit changes without crop evidence, or a leaf's digits change undeclared.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.evidence",
"description": "An insert has no crop evidence.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.find",
"description": "`find` is empty or does not occur exactly once.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.insert",
"description": "Text is inserted outside the runs of a node, or at a bad offset.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.merge",
"description": "The nodes differ in kind, are not mergeable, or are not adjacent siblings.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.move",
"description": "The destination is unknown or inside the moved node.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.op",
"description": "The operation is unknown.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.reclassify",
"description": "The new kind has another content shape.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.relabel",
"description": "The kind takes no label.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.replace",
"description": "Runs replace text outside a text run, or include an equation run.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.set",
"description": "The attribute cannot be set on the kind.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.split",
"description": "The node is not a sentence, the offset is outside it or inside a run other than text, or a part is empty.",
"chapter": "spec/22-conformance.md"
},
{
"id": "correction.target",
"description": "A target, parent or sibling is not a live node, or the root is deleted, moved, merged or reclassified.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.correction.after",
"description": "The last correction of a leaf does not end at the leaf's current node_hash.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.correction.id",
"description": "A correction's id does not derive from its record.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.correction.index",
"description": "Correction indexes do not count from 1 without gaps.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.correction.rev",
"description": "document.json's rev is not the number of corrections.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.fidelity.report",
"description": "document.json's fidelity distribution does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.align-key",
"description": "An align_key does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.key",
"description": "The key supplied does not match the package's key_id.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.match-hash",
"description": "A match_hash does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.meta",
"description": "meta_hash does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.node-hash",
"description": "A node_hash does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.own-hash",
"description": "An own_hash does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.root",
"description": "document.json's root is not the root node's node_hash.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.hash.text-hash",
"description": "A text_hash does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.id.alias",
"description": "An alias does not name a live node.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.id.form",
"description": "An ID is not seven letter-first Crockford base32 characters.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.id.retired-live",
"description": "An ID is both live and in the ID table.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.id.retired-missing",
"description": "A correction retired an ID that ids.jsonl does not record.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.id.successor",
"description": "A successor names an ID that is neither live nor in the ID table.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.id.unique",
"description": "An ID occurs twice.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.location.node",
"description": "A location names an unknown node.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.location.page",
"description": "A location's page_fp is not a page of any witness.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.node.attrs",
"description": "A section has no level.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.node.content",
"description": "A node's content does not have the shape its kind requires.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.node.kind",
"description": "A node kind is not in the list.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.node.label",
"description": "A node of a kind that takes no label has one.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.order.ids",
"description": "ids.jsonl is not aliases by ID, then retirements by revision and ID.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.order.locations",
"description": "locations.jsonl is not sorted by node order, page and fingerprint.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.order.pages",
"description": "pages.jsonl is not sorted by witness and page.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.order.receipts",
"description": "receipts.jsonl is not sorted by time and ID.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.order.references",
"description": "references.jsonl does not follow document order.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.order.suspects",
"description": "suspects.jsonl is not sorted by ID.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.page.witness",
"description": "A page names an unknown witness.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.policy.keyed",
"description": "A checks-only package carries plain hashes.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.policy.withheld",
"description": "Text is present where the policy withholds it, or withheld where the policy is full, or a checks-only package carries corrections or suspects.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.qa.key",
"description": "A spot-check seed key is not a registered Ed25519 spot-check key, or was registered after the receipt.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.qa.of",
"description": "A spot-check names a receipt the package does not hold.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.qa.sample",
"description": "A spot-check sample does not follow from its seed.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.qa.seed",
"description": "A spot-check seed is not the checker's signature over the receipt.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.receipt.doc",
"description": "A receipt names another document.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.receipt.id",
"description": "A receipt's or revocation's id does not derive from its record.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.receipt.nodes",
"description": "A receipt's nodes are not sorted by ID, or one repeats.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.receipt.root",
"description": "A receipt's Merkle root does not recompute.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.receipt.signature",
"description": "A signature does not verify against the roster.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.reference.node",
"description": "A reference record names a node that is not a reference.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.run.canonical",
"description": "Runs are not canonical: an empty text run, or two adjacent text runs with the same styles.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.run.cite",
"description": "A cite run names a node that is not a reference.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.run.equation",
"description": "Equation runs do not name the sentence's equation children, once each, in order.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.run.fnmark",
"description": "An fnmark run names a node that is not a footnote.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.run.kind",
"description": "A run kind is not in the list.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.run.style",
"description": "A style is unknown, or a run is both a subscript and a superscript.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.run.xref",
"description": "A same-document xref names no node.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.table.header",
"description": "A column or row header path names a node that is not a cell.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.tree.child",
"description": "A node holds a child kind it may not hold, a heading is not first, or a once-only child repeats.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.tree.empty",
"description": "A kind that must have children has none.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.tree.ord",
"description": "A parent's children do not have ord 0 to n-1.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.tree.order",
"description": "nodes.jsonl is not in document order.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.tree.root",
"description": "The tree does not have exactly one root, of kind document.",
"chapter": "spec/22-conformance.md"
},
{
"id": "doc.witness.id",
"description": "A witness ID does not derive from its SHA-256.",
"chapter": "spec/22-conformance.md"
},
{
"id": "grade.key-stale",
"description": "An anchor in the exercise's key is stale, so nothing is graded with it.",
"chapter": "spec/22-conformance.md"
},
{
"id": "grade.kind",
"description": "The exercise kind is unknown.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.file.canonical",
"description": "A JSON or JSON Lines record is not in canonical JSON.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.file.empty",
"description": "An optional JSON Lines file is present with no records.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.file.newline",
"description": "A line of a JSON Lines file does not end with a newline.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.file.required",
"description": "document.json, nodes.jsonl, witnesses.json or provenance.json is missing.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.absent",
"description": "An entry listed without its bytes is not an asset, or its bytes are present.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.hash",
"description": "A file's SHA-256 or size differs from its manifest entry.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.key",
"description": "The manifest's key differs from document.json's.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.missing",
"description": "The package has no MANIFEST.json.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.missing-file",
"description": "A file the manifest lists is not in the package.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.order",
"description": "Manifest entries are not sorted by path, or a path repeats.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.schema",
"description": "MANIFEST.json does not validate against manifest.schema.json.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.manifest.unlisted",
"description": "The package holds a file the manifest does not list.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.path.unsafe",
"description": "A path is absolute, has an empty, `.` or `..` segment, a backslash or a NUL, or is not normalized.",
"chapter": "spec/22-conformance.md"
},
{
"id": "package.schema",
"description": "A file or line does not validate against its schema.",
"chapter": "spec/22-conformance.md"
}
]
}
registry/stages/scienting-stages-default.json
+85
View File
@@ -0,0 +1,85 @@
{
"format": "scienting-stages/1",
"id": "scienting-stages-default",
"note": "Proposed defaults from the design, for counsel to set. Configuration, not code: a team may replace this file.",
"stages": {
"convert-model": {
"uses": [
"tdm"
],
"ai": {
"purpose": "internal"
},
"note": "Conversion by any model, local or outside."
},
"convert-deterministic": {
"uses": [
"tdm"
],
"note": "The text-layer witness, segmentation, hashing and the gate."
},
"index": {
"uses": [
"tdm"
],
"note": "The full-text index."
},
"review-model": {
"uses": [],
"ai": {
"purpose": "internal"
},
"note": "Model review of suspects, in a job zip or the direct API mode."
},
"propose-model": {
"uses": [],
"ai": {
"purpose": "internal"
},
"note": "Glosses, digitizations or claims a model proposes."
},
"mcp-text": {
"uses": [],
"ai": {
"purpose": "internal"
},
"note": "The MCP server returning text to the team's model."
},
"embed": {
"uses": [],
"ai": {
"purpose": "internal",
"processors": [
"local",
"tenancy"
]
},
"note": "Embeddings for search."
},
"ai-data-external": {
"uses": [],
"ai": {
"purpose": "external"
},
"note": "AI data built for others; in practice CC BY papers only."
},
"read": {
"uses": [
"read"
],
"note": "Reading in the reader."
},
"publish-quotes": {
"uses": [
"quote-public"
],
"note": "Publishing anything with quotations."
},
"accessible-copy": {
"uses": [
"accessible-copy"
],
"note": "An accessible copy for a user with a disability."
}
}
}
registry/stamps/scienting-stamps-1.json
+39
View File
@@ -0,0 +1,39 @@
{
"format": "scienting-stamps/1",
"id": "scienting-stamps-1",
"learned": false,
"note": "Published stamp-line rules, version 1. Patterns are matched against the normalized line, case-insensitively over ASCII. Teams add learned rules in files of their own.",
"rules": [
{
"id": "downloaded-via",
"pattern": "^Downloaded via .+ on .+",
"where": "any",
"note": "The institution-and-time stamp some publishers print in the margin."
},
{
"id": "downloaded-from-on",
"pattern": "^Downloaded from .+ on .+",
"where": "any",
"note": "The URL, institution and date stamp other publishers print."
},
{
"id": "sharing-guidelines",
"pattern": "^See https?://pubs\\.acs\\.org/sharingguidelines",
"where": "any",
"note": "A sharing notice printed beside a download stamp."
},
{
"id": "terms-and-conditions",
"pattern": "^See the Terms and Conditions \\(https?://onlinelibrary\\.wiley\\.com/",
"where": "any",
"note": "The rest of a stamp line, when a text layer splits it."
},
{
"id": "margin-downloaded",
"pattern": "^Downloaded",
"where": "margin",
"margin": 36,
"note": "Any line in the outer 36 points that begins with Downloaded."
}
]
}