Editorial Statement (ratio edendi)

Cicero, Divinatio in Q. Caecilium · urn:cts:latinLit:phi0474.phi004 · 73 §§, 6903 tokens.

Base text: cicero-reader phi004.json (Perseus phi0474.phi004-lat2). Tokenizer: deterministic, reproducible (GATE 7). Tagset: frozen coarse v1.2 (GATE 5).

Interpretive layers. valid-but-heuristic: the semantic/pragmatic/rhetoric/move layers are transparent RULE-SETS, not learned models (GATE 6). Coverage measures analysis, not accuracy.

Constitutio scope. §1 = reviewed unit (candidate gold + 26 Watson-model corrections + §§1-3 IAA pass). §§2-3 = candidate (agent-panel IAA consensus). §§4-73 = machine-assisted, unreviewed heuristic exploration.

IAA caveat (load-bearing). Inter-annotator agreement was produced by a panel of LLM specialist agents that SHARED the Watson commentary and a common base model; it is a PROXY for human IAA (errors may correlate). A human / Watson-blind calibration is REQUIRED before any 'edition' claim. See CALIBRATION-PROTOCOL.md.

Human calibration on file: False — until true, no section may be branded an edition.

Sigla

multidimQuality	siglum	resp	cert	gloss
seeded-gold	[G]	#human-source-aligned	high	gold, source-aligned (§1)
watson-reviewed	[R]	#panel-watson	high	reviewed against Watson 2025
watson-enriched	[E]	#panel-watson	medium	enriched, Watson-grounded
watson-contested	[C]	#panel-watson	low	contested — editors disagree
seeded	[s]	#machine-seed	low	machine seed, §1 only
heuristic	∇	#machine	unknown	machine-assisted, unreviewed
watson-fullfix	[F]	#machine-rule	low	deterministic corpus rule-fix (not human gold)

Defensible citation

Divinatio Wave Lab (build ): a reviewed proof-of-concept annotation of Cicero, Divinatio in Q. Caecilium §1, with a transparent machine-assisted heuristic scaffold and an open review queue over §§2-73. A methods/tooling/data contribution, NOT a digital critical edition.

Cite this (the brand travels with the quotation)

§1 (reviewed unit)

Divinatio Wave Lab (build 2026-06-23T04:00:00Z). Cicero, Divinatio in Q. Caecilium §1 — reviewed unit (candidate gold; 26 Watson-model corrections; agent-panel inter-annotator agreement, a PROXY for human IAA). Accessed [date].

§§2-3 (candidate)

Divinatio Wave Lab (build 2026-06-23T04:00:00Z). Cicero, Div. Caec. §§2-3 — candidate annotation; agent-panel IAA consensus (a proxy for human IAA; not human-calibrated). NOT a critical edition. Accessed [date].

§§4-73 (machine-assisted exploration)

Divinatio Wave Lab (build 2026-06-23T04:00:00Z). Cicero, Div. Caec. §§N — machine-assisted, unreviewed heuristic exploration; transparent rule-sets, no human review. NOT a critical edition. Accessed [date].

NOT defensible

'a digital critical edition of the Divinatio' (only §1 is reviewed, and even §1 is candidate)
'per-word measurement of the speech' (4 of 5 layers are heuristic rule-sets; positional-encoding is metric only for the linear-position layer)
presenting agent-panel kappa (Macro 0.85 / Micro 0.97) as human inter-annotator agreement
coverage figures as accuracy (role 'coverage' is 0.55% real / 28.6% incl. scaffold)

Versioned by build_provenance.json. Gates applied: 0 honesty, 1 rhetoric-provenance, 2 punctuation, 3 scope-labels, 4 pipeline+orchestrator, 5 IAA §§1-3, 6 layer-validity, 7 scaling, 8 publishability.