Morph-Bench

Package Install

Installable package: python3.11 -m pip install gnosis-morph-bench. Current release: 0.1.0 on PyPI. Source: Zer0pa/Morph-Bench.

python3.11 -m pip install gnosis-morph-bench

For full install, smoke, source, and developer commands, click here.

---

00 · GNOSIS-MORPH-BENCH · ANCIENT SCRIPT RESEARCH UTILITY RESEARCH-READY · INDUS BLOCKED Toolkitting for ancient script research. A shared scoring rig for ancient-script methods · PyPI gnosis-morph-bench v0.1.0 · github.com/Zer0pa/Morph-Bench Every researcher studying ancient-script morphology rebuilds the same machinery from scratch: scoring routes, permutation nulls, stability sweeps. The result lives in one paper, then the next lab starts again from nothing. Morph-Bench is the shared rig that ends that cycle — it scores routes, preserves null results, runs stability checks, and records replay so the next study begins from a measured floor. Today 37 tests pass and runs are byte-identical across macOS and Linux. Live Indus Phase 4 rerun is blocked on Phase 3c manifest access.

Scope: morphology benchmark rig. Scoring, permutation nulls, stability sweeps, and replay pass; live Indus Phase 4 is blocked.

01 · THE GAP NO MEASURE, NO BASELINE Every ancient-script researcher rebuilds the same baseline from scratch. The measure is never kept.

02 · MARKETS ADJACENT FORECASTS Digital humanities '30 · $3.2B Heritage digitization '30 · $8.1B Research data management '30 · $6.7B AI for archaeology '30 · $1.4B Scholarly infrastructure '30 · $5.3B Every field on this list has ancient-script work underway. None of it starts from a measured baseline.

03 · VALUE OF MARKET $8.1B Cultural-heritage digitization in 2030; research infrastructure for review and reuse, not commercial sale.

04 · INSIGHT Measure the method once. The next researcher starts from here.

05.1 · CURRENT TECH REBUILT EVERY TIME Ancient-script research has no standard scoring rig. Each lab writes its own metric, picks its own null, records its own result — then the work moves on. The next researcher starts again from zero.

05.2 · OUR TECH THE BASELINE, KEPT Morph-Bench installs from PyPI and gives a researcher a working starting point: a route scorer, a permutation null, a five-mode stability battery, and replayable records that are byte-identical across macOS and Linux Python 3.11. 37 tests pass on a fresh clone. 9 of 9 adapter clauses hold.

05.3 · BENCHMARKS PUBLIC RECEIPTS Pytest37/37public README Adapter9/9MUST clauses Lint0/6forbidden hits PyPI0.1.0wheel/sdist Pytest 37/37 Adapter 9/9 Forbidden 0/6 Status: working today. Live Indus Phase 4 rerun blocked on Phase 3c manifest.

06 · MEASUREMENT METHOD SCORING + REPLAY Every method scored. Every null kept. Every blocker named.

06.1 · COMPARATIVE PERFORMANCE · BENCHMARK SURFACE Pytest surface 37 passed Adapter 9/9 MUST clauses Lint 0/6 hits Indus BLOCKED Today's measurement is the rig itself: pytest on a fresh Python 3.11 clone, adapter contract coverage, forbidden-pattern lint, and byte-equal replay across macOS and Linux. Live Indus Phase 4 rerun and Cuneiform adapter are not in scope yet.

07 · KEY METRICS PUBLIC RECEIPTS

07.1 · PYTEST SURFACE 37/37 Fresh clone · pytest passes end to end

07.2 · ADAPTER INTERFACE 9/9 Adapter v1 · required clauses covered

07.3 · FORBIDDEN-PATTERN LINT 0/6 Repo lint · no forbidden patterns

07.4 · PYPI RELEASE 0.1.0 Public PyPI · wheel and source ready

07.5 · LIVE INDUS RERUN null Blocked · Phase 3c manifest unblocks it

08 · FIXTURE REPLAY BYTE-STABLE SCOPE Replay is byte-stable for fixture records, not rights-limited heavy data.

08.1 · WHAT REPLAYS EXACTLY FIXTURE RECORDS ONLY Smoke and replay outputs are byte-identical across documented macOS and Linux Python 3.11 environments, verified end-to-end through fresh-clone install. Replay records and SHA-256 reference-freeze helpers ship as part of the public package. That does not prove deterministic live Indus replay from repo custody, undisclosed heavy data, or cultural-heritage imagery — and it does not prove any text recovery. The unit of byte-exactness is benchmark-fixture replay, not domain-result reproduction.

08.2 · HONEST BLOCKER Honest Blocker · Live Indus Phase 4 rerun is blocked on Phase 3c manifest access. Heavy-data and image-bearing release policy is open. Cuneiform adapter is deferred to a separate contract once the first live Indus replay lands. PyPI: gnosis-morph-bench==0.1.0; no 0.1.1 until a receipt. Non-claims: no text recovery, no source identification, no data permission, no hosted service.

09 ONE BASELINE THE FIELD CAN INHERIT.

09.1 · THE AMBITION An ancient-script field that loses its scoring rig with every postdoc loses a generation of measurement. Morph-Bench is the rig the next lab installs instead of writing — a public floor for method comparison that outlives the researcher who first ran it.

09.2 · WHAT WORKS NOW Working today: 37 tests pass, adapter contract holds, fixture replay is byte-stable, public PyPI release available.

09.3 · WHAT'S STILL OPEN Still blocked: live Indus Phase 4 rerun, heavy-data release policy, and a future Cuneiform adapter.

09.4 · LABS · NEAR-TERM (12–24 MO) One installable baseline, not three rebuilds A second lab studying Indus morphology can install the same scoring rig their predecessor used, run it on their candidate method, and compare results that have a common floor. The conversation moves from "whose code" to "whose finding".

09.5 · REVIEW · NEAR-TERM (12–24 MO) Reviewers see the null beside the result A journal reviewer reading a morphology paper can ask for the permutation null and the stability sweep alongside the headline number, knowing both were produced by a public harness, not the author's private script. Skeptical review gets cheaper.

09.6 · MUSEUMS · MID-TERM (24–48 MO) Heritage archives keep the method, not just the picture When a museum funds a script-morphology study, the resulting paper can ship with a replayable run — same scoring rig, same null check, same stability battery — so the archive's investment outlives the postdoc who did the work. The method becomes part of the collection.

09.7 · CROSS-SCRIPT · MID-TERM (24–48 MO) Indus and Cuneiform share a floor Once a Cuneiform scorer sits beside the Indus one, two distant script communities can argue about results on the same scoring floor. Disagreement narrows to the data and the model — the scoring rig stays the same, so the argument finally becomes worth having.

09.8 · CONVENTION · PARADIGM (48 MO+) A standard the next generation inherits A graduate student starting in ancient-script morphology in 2030 finds the same baseline their advisor used in 2026 — installable, documented, with null results preserved. The field stops losing a generation of measurement every time the tools rot. One kept harness, many researchers.

---

Install / Developer Commands Detailed

Package Install

Installable package: python3.11 -m pip install gnosis-morph-bench. Current release: 0.1.0 on PyPI. Source: Zer0pa/Morph-Bench.

python3.11 -m pip install gnosis-morph-bench

Import smoke:

python3.11 - <<'PY'
import importlib.metadata as md
import gnosis_morph_bench

print("gnosis-morph-bench", md.version("gnosis-morph-bench"))
PY

CLI smoke:

gnosis-morph-bench-smoke --help
gnosis-morph-bench-adapter-indus-phase4 --help

Install success only proves package acquisition/import. Product scope, stale PyPI state, platform limits, and blockers remain in the front-door sections below.

Quick Start

git clone https://github.com/Zer0pa/Morph-Bench.git
cd Morph-Bench
python3.11 -m venv .venv
source .venv/bin/activate
pip install -e '.[dev]'

### repo-local pytest suite
pytest -q