Ethos v0.6.0

Ethos v0.6.0

Ethos v0.6.0 is a release for deterministic document evidence grounding
and citation checking across native Ethos JSON and supported foreign parser outputs.

The release turns on capability the verifier already had internally but could not express on the
wire, and closes a set of correctness seams where two implementations of one rule had drifted
apart.

This release prepares:

• ethos.grounding.v1 schema 1.1.0, which admits eight page-less office media types — DOCX,
  XLSX, PPTX, ODT, ODS, ODP, RTF, EPUB — under a version-gated union. A 1.0.0 artifact is PDF
  and byte-for-byte the shape it always was; a 1.1.0 PDF artifact keeps that paginated shape; a
  1.1.0 office artifact states pages: [], carries no spans or tables, and gives every element
  the producer's native locator string in place of the page/bbox pair. Verification resolves by
  element id, at element-scoped evidence precision — what a page-less address can honestly claim;
• the first real producer for semantic_unverified, which every checker had hard-coded to
  false since the field shipped. A grounded quote whose match exists only as the sanctioned
  adjacent-element join now sets it: the text is present, but only as an assembly of two elements
  whose continuity was inferred from geometry. The bit fails the gate closed, as its contract
  always said it would;
• two repairs to false hallucination verdicts. A quote or value claim carrying a page-only
  locator is now searched on the cited page before being judged, rather than returned as a
  mismatch unexamined; and text_normalization gains an opt-in third profile,
  unicode_compat_v1, which folds the extraction artifacts a model cannot type;
• matching.adjacency_gap_tolerance_q, an opt-in bound on the distance between facing edges, so
  the adjacent-quote repair admits the gaps and slight overlaps real extractors produce rather
  than requiring perfectly touching boxes;
• hardening.include_nearest_match, an opt-in diagnostic carrying the nearest candidate for a
  failed quote, value, or table_cell check, as token-Jaccard similarity in integer basis points;
• schemas/normalization-vectors.json, which pins the normalization profiles as executable
  input/output vectors rather than prose, so an independent implementation can be tested against
  the contract instead of agreeing with it by inspection;
• OpenDataLoader adapter 0.2.0, whose real-shape table path emits 0-based row and column
  addresses, matching the rest of the contract;
• verify-batch --merged, emitting one canonical verification report with one attestation over
  every request, so callers stop hand-folding per-line reports; and a batch that builds the source
  index once rather than once per line;
• proof statements: every verdict-bearing command emits a self-describing, self-attesting report.

The intended v0.6.0 release surfaces are:

• Rust library crates ethos-doc-core, ethos-verify, and ethos-pdf at 0.6.0;
• the Python ethos-pdf wheel at 0.6.0;
• the npm @docushell/ethos-pdf@0.6.0 CLI package;
• macOS arm64 and Linux x64 CLI archives with checksums, inventory sidecars, and smoke evidence.

Ethos verifies citation grounding against supplied source representations. It does not establish
semantic truth, and applications remain responsible for relevance, synthesis policy, and final
answer-release decisions. semantic_unverified acquiring a producer does not change that: it
reports that a literal method did not effectively check meaning, never that meaning was checked.

PDFium-backed commands require caller-provided PDFium through ETHOS_PDFIUM_LIBRARY_PATH. This
release does not bundle a project-maintained PDFium build.

Upgrade notes

Three changes require action from an existing consumer. The first two are structural and affect
every caller; the third changes verdicts on unchanged input.

The verdict-bearing commands now write an in-toto Statement. verify, verify-batch,
grounding check, evidence anchor, security report, and crop_element emit
{_type, subject, predicateType, predicate}, and the verification report is at .predicate.
A caller that parses stdout as the report reads undefined for every field it wants. doc parse
and rag chunk are unchanged.

attestation is now a required field inside the report, and schema_version did not move.
A 0.5.x report and a 0.6.0 report both state schema_version: "1.0.0", so the migration cannot be
version-gated — a consumer must probe for the field rather than branch on the version. For the same
reason, stdout no longer validates against schemas/ethos-verification-report.schema.json, whose
root sets additionalProperties: false; only .predicate validates against it.

Verdict-visible: reports whose grounding passed through an adjacent-element join now gate
false where they gated true. semantic_unverified has its first producer and fails the gate
closed, so all_evidence_grounded no longer certifies on such a check. The joined match still
grounds and its evidence trail survives; what changes is certification. The native-split-quote
golden moved with it, and consumers who wired an amber state for this field will see it fire for
the first time. This is the only change that turns a passing report into a failing one on
unchanged input and unchanged config.

Two smaller migrations. The OpenDataLoader adapter at 0.2.0 emits 0-based real-shape table cell
addresses where 0.1.0 emitted 1-based; a stored table_cell claim written against the old
convention resolves to a different cell or not at all, and parser.adapter_version is the only
discriminator. And TextNormalization gains a variant, which breaks exhaustive Rust matches
downstream without affecting any stored artifact.

Published archive SHA256 values:

• ethos-macos-arm64.tar.gz: pending — recorded here from the approved archives before publication
• ethos-linux-x64.tar.gz: pending — recorded here from the approved archives before publication

Outside the v0.6.0 release boundary: Windows packaged artifacts, bundled/project-maintained
PDFium builds, ethos-mcp, hosted surfaces, the WASM playground, native OCR or scanned-document
support, Action Marketplace publication, public benchmark reports or comparative claims, speed,
footprint, parser-quality, table-quality, production positioning, ethos-doc, and ethos-rag.

Ethos v0.5.0

Ethos v0.5.0

The v0.5.0 publication is closed out in
docs/validation/v0-5-0-release-closeout-summary.md.

The release includes the published macOS arm64 and Linux x64 caller-PDFium CLI artifacts, the
optional ethos-full artifacts, Rust crates, the Python wheel, and the npm package. Windows
packaged artifacts, hosted surfaces, production positioning, and public benchmark claims remain
outside the approved boundary.

Release v0.4.0

Ethos v0.4.0

Ethos v0.4.0 is a public-beta evaluation release for deterministic document evidence grounding
and citation checking across native Ethos JSON and supported foreign parser outputs.

This release prepares:

• verification hardening for claim kinds, matching, staleness, resource limits, capability
  downgrades, proof summaries, and application answer-release inputs;
• additive 1.1.0 verification-config, verification-report, evidence-anchor, and answer-release
  contracts while retaining the supported 1.0.0 forms;
• a versioned citation-emission JSON contract, dependency-free Python emission helpers for
  LangChain and LlamaIndex-shaped retrieval objects, and model-free walkthroughs;
• schema-derived TypeScript declarations for verification reports, citation emission, and
  answer-release decisions in @docushell/ethos-pdf;
• caller-run PDFium setup and ethos doctor checks. Ethos does not automatically download or
  bundle PDFium.

The intended v0.4.0 release surfaces are:

• Rust library crates ethos-doc-core, ethos-verify, and ethos-pdf at 0.4.0;
• the Python ethos-pdf wheel at 0.4.0;
• the npm @docushell/ethos-pdf@0.4.0 CLI package;
• macOS arm64 and Linux x64 CLI archives with checksums, inventory sidecars, and smoke evidence.

Archive SHA256:

• ethos-macos-arm64.tar.gz: 719f092101bb1e4cfeebc9507155b15739642f0b891664bd0d9f8a05d9688ba5
• ethos-linux-x64.tar.gz: 616be562306d64a293554ca4695f19deb6e135dd328e88598a80e76f6f8fb3cd

Ethos verifies citation grounding against supplied source representations. It does not establish
semantic truth, and applications remain responsible for relevance, synthesis policy, and final
answer-release decisions.

PDFium-backed commands require caller-provided PDFium through
ETHOS_PDFIUM_LIBRARY_PATH. This release does not bundle a project-maintained PDFium build.

Outside the v0.4.0 release boundary: Windows packaged artifacts, bundled/project-maintained
PDFium builds, ethos-mcp, hosted surfaces, the WASM playground, native OCR or scanned-document
support, Action Marketplace publication, public benchmark reports or comparative claims, speed,
footprint, parser-quality, table-quality, production positioning, ethos-doc, and ethos-rag.

Release v0.3.0

Ethos v0.3.0

Ethos v0.3.0 is a public-beta evaluation release for deterministic document evidence grounding and
citation checking across native Ethos JSON and supported foreign parser outputs.

The current release includes:

• Rust library crates ethos-doc-core, ethos-verify, and ethos-pdf at 0.3.0;
• the Python ethos-pdf wheel at 0.3.0;
• the npm @docushell/ethos-pdf@0.3.0 CLI package;
• macOS arm64 and Linux x64 CLI archives, checksums, inventory sidecars, and smoke evidence.

The v0.3.0 API adds proof-summary and app-answer-release helpers. Ethos verifies citation grounding
and derives proof summaries; applications remain responsible for question relevance, source-fact
versus synthesis labels, unsupported-claim labels, and final/review/blocked answer-release policy.

PDFium-backed commands require caller-provided PDFium through
ETHOS_PDFIUM_LIBRARY_PATH. The release does not bundle a project-maintained PDFium build.

The *.inventory.json assets preserve the pre-publication CI provenance of the approved archive
bytes. Their draft_not_release_ready and publication: blocked fields describe the workflow
state in which those exact archives were produced; the later publication authorization and
closeout are recorded in the repository validation records.

Archive SHA256 values:

efb163f140bf4afffd1caeb396f79e42f484591c3e90a86810ca6c0f0c209c96  ethos-macos-arm64.tar.gz
b549ba5968e04b7679a8d3e879cd45d27f3e9a6fd226eee5c270a4e4f5c01405  ethos-linux-x64.tar.gz

Still outside the approved release boundary: additional release targets, DocuShell integration,
hosted surfaces, production positioning, Windows packaged artifacts, bundled project-maintained
PDFium builds, public benchmark reports or claims, speed, footprint, parser-quality, table-quality,
ethos-doc, and ethos-rag.

Ethos v0.2.0

Ethos v0.2.0 publishes JSON verification and evidence anchoring, Rust crates ethos-doc-core/ethos-verify/ethos-pdf 0.2.0, Python ethos-pdf 0.2.0, npm @docushell/ethos-pdf 0.2.1, and macOS arm64/Linux x64 CLI artifacts. npm @docushell/ethos-pdf 0.2.0 is deprecated because it shipped stale CLI binaries; use 0.2.1.

Release v0.1.2

Ethos patch 0.1.2 CLI artifacts for macOS arm64 and Linux x64 are requested for public beta evaluation with caller-provided PDFium. Rust crates, the Python wheel, npm package install instructions, and public README installation examples remain on the published 0.1.1 baseline until separate registry, npm vendor refresh, and public wording closeout records pass. Hosted surfaces, production positioning, Windows packaged artifacts, bundled project-maintained PDFium builds, ethos-doc, ethos-rag, public benchmark reports, public benchmark claims, and speed, footprint, parser-quality, table-quality, or production claims remain blocked.

SHA256:

• ethos-macos-arm64.tar.gz: 7da7da71fb0c21b25cd2ffc198480ee80bf9f0c9e70e461cffbdcbdda8d7023c
• ethos-linux-x64.tar.gz: 4e260b464dc9557bc31c29fb1d1dfa75311fe12734bc79af4a31e1649797e456

Release v0.1.1

Ethos is public beta for source, Rust crate, Python wheel, macOS arm64 CLI artifact, Linux x64 CLI artifact, and npm @docushell/ethos-pdf evaluation. It verifies whether AI citations are grounded in document evidence across native Ethos JSON and supported foreign parser outputs. Rust library crates ethos-doc-core, ethos-verify, and ethos-pdf are available on crates.io at 0.1.1 for evaluation. The Python ethos-pdf wheel, npm @docushell/ethos-pdf@0.1.1 package, and macOS arm64/Linux x64 CLI artifacts are available for evaluation with caller-provided PDFium. Hosted surfaces, production positioning, Windows packaged artifacts, bundled project-maintained PDFium builds, ethos-doc, ethos-rag, public benchmark reports, public benchmark claims, and speed, footprint, parser-quality, table-quality, or production claims remain blocked.

SHA256:
eac79cddc6f5fc834ecc279401905729978d73e99ae11a2bea82d7356a4bcd88 ethos-macos-arm64.tar.gz
842aa4b71333aecc54f344d9f5362160d0943d8efd32dffabe99dc19553916a0 ethos-linux-x64.tar.gz

Release v0.1.0

Ethos is public beta for source, Rust crate, macOS arm64 CLI artifact, and Python wheel evaluation. It verifies whether AI citations are grounded in document evidence across native Ethos JSON and supported foreign parser outputs. Rust library crates ethos-doc-core, ethos-verify, and ethos-pdf are available on crates.io at 0.1.0 for evaluation. The macOS arm64 CLI artifact and Python ethos-pdf wheel are available for evaluation with caller-provided PDFium. Hosted surfaces, production positioning, npm publication, Windows packaged artifacts, bundled project-maintained PDFium builds, ethos-doc, ethos-rag, and public benchmark claims remain blocked.

SHA256:
9cb66dac20f93c55f574357dd0494e0cad711e1e5969cdfb29ae4c64ddf7c95d ethos-macos-arm64.tar.gz