diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md index 37a25c17..77340ec2 100644 --- a/ARCHITECTURE.md +++ b/ARCHITECTURE.md @@ -61,6 +61,7 @@ boundaries above remain the target modular MSA architecture. | `tepp_simulation` | known-truth temporal/event data generation | | `validation_core` | RMSE, bias, coverage, graph, and Monte Carlo metrics | | `tepp_api` | versioned DTO, schema, and export contracts | +| `style_source` | house-voice style residue is not unique latent content and not stopword deletion | | `stopword_deletion` | default stopword deletion is not a valid method for repeated report language | | `copy_identity` | a template copy is not the source document and not a state transition | | `intake_authorization` | untrusted intake fails closed without a grant; bounds are not authorization | diff --git a/CHANGELOG.md b/CHANGELOG.md index 18ee773b..4bdc0d0f 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,7 @@ All notable changes to TEPP are documented here. The format follows Keep a Chang ### Added +- `style_source` identity gate: house-voice style residue is not unique latent content and is not erased by a stopword list; recovered style kinds match known truth at a higher computed rate than collapsing every token to unique content (ADR 0004/0012). - `stopword_deletion` method gate: a default or global stopword list cannot erase repeated report language; recovered deletion kinds match known truth at a higher computed rate than collapsing every token treatment to stopword deletion (ADR 0004/0012). - `persistence_postgres` retention/deletion/legal-hold (migration `0007`): policy rows, legal holds that block completed deletion, evidence tombstones without raw-source restore, analysis exclusion only for `logical_revocation`/`identity_tombstone` (not `cache_export_removal`), and deletion requests bound to the cited retention policy's tenant/class/purpose. - `copy_identity` identity gate: a template or pasted copy cannot reuse the source document identity or become a state transition; recovered copy kinds match known truth at a higher computed rate than collapsing every copy to the source (ADR 0003). diff --git a/Cargo.lock b/Cargo.lock index ee47318d..8f0889cb 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -1477,6 +1477,10 @@ dependencies = [ "unicode-properties", ] +[[package]] +name = "style_source" +version = "0.1.0" + [[package]] name = "subevent_containment" version = "0.1.0" diff --git a/Cargo.toml b/Cargo.toml index 6add5026..5563462d 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -11,6 +11,7 @@ members = [ "crates/tepp_simulation", "crates/validation_core", "crates/tepp_api", + "crates/style_source", "crates/stopword_deletion", "crates/copy_identity", "crates/provider_receipt", @@ -55,6 +56,7 @@ default-members = [ "crates/tepp_simulation", "crates/validation_core", "crates/tepp_api", + "crates/style_source", "crates/stopword_deletion", "crates/copy_identity", "crates/provider_receipt", diff --git a/README.md b/README.md index 281ce609..f7fb7ab1 100644 --- a/README.md +++ b/README.md @@ -43,6 +43,7 @@ crates/corpus_split crates/tepp_simulation crates/validation_core crates/tepp_api +crates/style_source crates/stopword_deletion crates/copy_identity crates/provider_receipt diff --git a/crates/style_source/Cargo.toml b/crates/style_source/Cargo.toml new file mode 100644 index 00000000..2a185ab6 --- /dev/null +++ b/crates/style_source/Cargo.toml @@ -0,0 +1,17 @@ +[package] +name = "style_source" +description = "House-voice style residue is not unique content and not stopword deletion." +version.workspace = true +edition.workspace = true +rust-version.workspace = true +license.workspace = true +authors.workspace = true +repository.workspace = true +homepage.workspace = true +readme.workspace = true +keywords.workspace = true +categories.workspace = true +publish = false + +[lints] +workspace = true diff --git a/crates/style_source/src/error.rs b/crates/style_source/src/error.rs new file mode 100644 index 00000000..0a5efcc4 --- /dev/null +++ b/crates/style_source/src/error.rs @@ -0,0 +1,57 @@ +//! Fail-closed style-source errors. + +use std::fmt; + +/// A fail-closed style-source error. +#[derive(Clone, Copy, Debug, Eq, PartialEq)] +#[non_exhaustive] +pub enum StyleSourceError { + /// Style residue was treated as unique latent content. + StyleIsNotUniqueContent, + /// Style residue was treated as stopword deletion. + StyleIsNotStopwordDeletion, + /// A recovery slice was empty or length-mismatched. + InvalidStylePayload, +} + +impl fmt::Display for StyleSourceError { + fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result { + let message = match self { + Self::StyleIsNotUniqueContent => { + "house-voice style residue is not unique latent content" + } + Self::StyleIsNotStopwordDeletion => { + "house-voice style residue is not stopword deletion" + } + Self::InvalidStylePayload => "invalid style-source payload", + }; + formatter.write_str(message) + } +} + +impl std::error::Error for StyleSourceError {} + +#[cfg(test)] +mod tests { + use super::StyleSourceError; + + #[test] + fn error_messages_are_stable() { + for (error, message) in [ + ( + StyleSourceError::StyleIsNotUniqueContent, + "house-voice style residue is not unique latent content", + ), + ( + StyleSourceError::StyleIsNotStopwordDeletion, + "house-voice style residue is not stopword deletion", + ), + ( + StyleSourceError::InvalidStylePayload, + "invalid style-source payload", + ), + ] { + assert_eq!(error.to_string(), message); + } + } +} diff --git a/crates/style_source/src/kind.rs b/crates/style_source/src/kind.rs new file mode 100644 index 00000000..c5f40a71 --- /dev/null +++ b/crates/style_source/src/kind.rs @@ -0,0 +1,129 @@ +//! Style residue versus unique latent content. + +use crate::StyleSourceError; + +/// Closed vocabulary of style-related token treatments. +#[derive(Clone, Copy, Debug, Eq, PartialEq)] +pub enum StyleKind { + /// House-voice or style residue, not unique document meaning. + StyleResidue, + /// Token treatment reserved for unique latent content. + UniqueContent, +} + +impl StyleKind { + /// Return the stable wire kind name. + #[must_use] + pub const fn wire_name(self) -> &'static str { + match self { + Self::StyleResidue => "style", + Self::UniqueContent => "unique_content", + } + } + + /// Parse a stable wire kind name. + /// + /// # Errors + /// + /// Returns [`StyleSourceError::InvalidStylePayload`] for unrecognized names. + pub fn from_wire_name(name: &str) -> Result { + match name { + "style" => Ok(Self::StyleResidue), + "unique_content" => Ok(Self::UniqueContent), + _ => Err(StyleSourceError::InvalidStylePayload), + } + } +} + +/// Refuse to treat style residue as unique latent content. +/// +/// # Errors +/// +/// Returns [`StyleSourceError::StyleIsNotUniqueContent`] when `kind` is +/// [`StyleKind::StyleResidue`]. +pub fn refuse_style_as_unique_content(kind: StyleKind) -> Result<(), StyleSourceError> { + match kind { + StyleKind::StyleResidue => Err(StyleSourceError::StyleIsNotUniqueContent), + StyleKind::UniqueContent => Ok(()), + } +} + +/// Refuse to treat style residue as stopword deletion. +/// +/// # Errors +/// +/// Returns [`StyleSourceError::StyleIsNotStopwordDeletion`] when `kind` is +/// [`StyleKind::StyleResidue`]. +pub fn refuse_style_as_stopword_deletion(kind: StyleKind) -> Result<(), StyleSourceError> { + match kind { + StyleKind::StyleResidue => Err(StyleSourceError::StyleIsNotStopwordDeletion), + StyleKind::UniqueContent => Ok(()), + } +} + +/// Fraction of recovered style kinds that match known truth. +/// +/// # Errors +/// +/// Returns [`StyleSourceError::InvalidStylePayload`] when either slice is +/// empty or the lengths differ. +pub fn identity_recovery_rate( + truth: &[StyleKind], + decided: &[StyleKind], +) -> Result { + if truth.is_empty() || truth.len() != decided.len() { + return Err(StyleSourceError::InvalidStylePayload); + } + let mut matches = 0_u32; + for (truth_kind, decided_kind) in truth.iter().zip(decided) { + if truth_kind == decided_kind { + matches += 1; + } + } + Ok(f64::from(matches) / truth.len() as f64) +} + +#[cfg(test)] +mod tests { + use super::{ + StyleKind, identity_recovery_rate, refuse_style_as_stopword_deletion, + refuse_style_as_unique_content, + }; + use crate::StyleSourceError; + + #[test] + fn local_branches_cover_kinds_payloads_and_wire_names() { + assert_eq!( + refuse_style_as_unique_content(StyleKind::StyleResidue), + Err(StyleSourceError::StyleIsNotUniqueContent) + ); + assert_eq!( + refuse_style_as_stopword_deletion(StyleKind::StyleResidue), + Err(StyleSourceError::StyleIsNotStopwordDeletion) + ); + refuse_style_as_unique_content(StyleKind::UniqueContent).expect("unique"); + refuse_style_as_stopword_deletion(StyleKind::UniqueContent).expect("unique"); + for kind in [StyleKind::StyleResidue, StyleKind::UniqueContent] { + assert_eq!( + StyleKind::from_wire_name(kind.wire_name()).expect("round-trip"), + kind + ); + } + assert_eq!( + StyleKind::from_wire_name("stopword"), + Err(StyleSourceError::InvalidStylePayload) + ); + let matched = + identity_recovery_rate(&[StyleKind::StyleResidue], &[StyleKind::StyleResidue]) + .expect("rate"); + assert!((matched - 1.0).abs() < f64::EPSILON); + assert_eq!( + identity_recovery_rate(&[], &[]), + Err(StyleSourceError::InvalidStylePayload) + ); + assert_eq!( + identity_recovery_rate(&[StyleKind::StyleResidue], &[]), + Err(StyleSourceError::InvalidStylePayload) + ); + } +} diff --git a/crates/style_source/src/lib.rs b/crates/style_source/src/lib.rs new file mode 100644 index 00000000..0b5b1cd3 --- /dev/null +++ b/crates/style_source/src/lib.rs @@ -0,0 +1,22 @@ +#![forbid(unsafe_code)] +#![deny(missing_docs)] +#![allow(clippy::cast_precision_loss)] +//! House-voice style residue is not unique latent content. +//! +//! Style and house-voice stay explicit method/background structure. They +//! are not unique document meaning and are not erased by a stopword list +//! (ADR 0004/0012). + +mod error; +mod kind; + +/// Fail-closed style-source errors. +pub use error::StyleSourceError; +/// Closed vocabulary of style-related token treatments. +pub use kind::StyleKind; +/// Fraction of recovered style kinds that match known truth. +pub use kind::identity_recovery_rate; +/// Refuse to treat style residue as stopword deletion. +pub use kind::refuse_style_as_stopword_deletion; +/// Refuse to treat style residue as unique latent content. +pub use kind::refuse_style_as_unique_content; diff --git a/crates/style_source/tests/crate_contract.rs b/crates/style_source/tests/crate_contract.rs new file mode 100644 index 00000000..10210e4b --- /dev/null +++ b/crates/style_source/tests/crate_contract.rs @@ -0,0 +1,7 @@ +//! Integration contract for the `style_source` package identity. + +#[test] +fn package_identity_is_stable() { + let observed = std::hint::black_box(env!("CARGO_PKG_NAME")); + assert_eq!(observed, "style_source"); +} diff --git a/crates/style_source/tests/style_source_contract.rs b/crates/style_source/tests/style_source_contract.rs new file mode 100644 index 00000000..c50f89d1 --- /dev/null +++ b/crates/style_source/tests/style_source_contract.rs @@ -0,0 +1,67 @@ +//! House-voice style residue is not unique content and not stopword deletion. + +use style_source::{ + StyleKind, StyleSourceError, identity_recovery_rate, refuse_style_as_stopword_deletion, + refuse_style_as_unique_content, +}; + +#[test] +fn style_residue_cannot_become_unique_content_or_stopword_deletion() { + assert_eq!( + refuse_style_as_unique_content(StyleKind::StyleResidue), + Err(StyleSourceError::StyleIsNotUniqueContent) + ); + assert_eq!( + refuse_style_as_stopword_deletion(StyleKind::StyleResidue), + Err(StyleSourceError::StyleIsNotStopwordDeletion) + ); + refuse_style_as_unique_content(StyleKind::UniqueContent).expect("unique"); + refuse_style_as_stopword_deletion(StyleKind::UniqueContent).expect("unique"); +} + +#[test] +fn recovered_kinds_match_known_truth_better_than_a_unique_content_collapse() { + let truth = [ + StyleKind::StyleResidue, + StyleKind::UniqueContent, + StyleKind::StyleResidue, + ]; + let recovered = truth; + let collapsed = [ + StyleKind::UniqueContent, + StyleKind::UniqueContent, + StyleKind::UniqueContent, + ]; + let recovered_rate = identity_recovery_rate(&truth, &recovered).expect("recovered"); + let collapsed_rate = identity_recovery_rate(&truth, &collapsed).expect("collapsed"); + let expected = { + let mut matches = 0_u32; + for (truth_kind, decided_kind) in truth.iter().zip(recovered.iter()) { + if truth_kind == decided_kind { + matches += 1; + } + } + f64::from(matches) / f64::from(u32::try_from(truth.len()).expect("len")) + }; + assert!((recovered_rate - expected).abs() < f64::EPSILON); + assert!(recovered_rate > collapsed_rate); +} + +#[test] +fn empty_or_mismatched_kind_payloads_fail_closed() { + assert_eq!( + identity_recovery_rate(&[], &[]), + Err(StyleSourceError::InvalidStylePayload) + ); + assert_eq!( + identity_recovery_rate(&[StyleKind::StyleResidue], &[]), + Err(StyleSourceError::InvalidStylePayload) + ); + assert_eq!( + identity_recovery_rate( + &[StyleKind::StyleResidue, StyleKind::UniqueContent], + &[StyleKind::StyleResidue] + ), + Err(StyleSourceError::InvalidStylePayload) + ); +} diff --git a/docs/TRACEABILITY.md b/docs/TRACEABILITY.md index 9fd291e7..144a5178 100644 --- a/docs/TRACEABILITY.md +++ b/docs/TRACEABILITY.md @@ -24,8 +24,8 @@ The full APA 7th standards/literature register remains `docs/research/standards- | multilingual shared latent semantic space | PRD; ADR 0004 | future semantic/concept/topic crates | accepted-target | | TRSL-TM temporal/relational topic posterior and backend compatibility | ADR 0012; ADR 0004 | future `topic_measurement` | accepted-target | | global P0 topic identity with activity/dormancy/reactivation | ADR 0012 | future topic lineage/activity state | accepted-target | -| no default stopword deletion / no TF-IDF-BM25 inferential weighting | ADR 0004/0012; PRD/TRD | `stopword_deletion` default-list refusal on the active PR; TF-IDF/BM25 inferential-weight refusal remains accepted-target | partial | -| report template/section/copied/style/modality method effects | ADR 0004/0012; PRD/TRD | simulation truth factors implemented; estimator-side method model remains future | partial | +| no default stopword deletion / no TF-IDF-BM25 inferential weighting | ADR 0004/0012; PRD/TRD | future semantic/method-source model | accepted-target | +| report template/section/copied/style/modality method effects | ADR 0004/0012; PRD/TRD | simulation truth factors implemented; `style_source` style-versus-unique-content identity on the active PR; estimator-side method model remains future | partial | | candidate K statistical/Pareto gates + blinded LLM review | ADR 0012; research | future `model_selection` | accepted-target | | compositional topic correlation / stable clustering | ADR 0005/0012; research | future `network_analysis` | accepted-target | | posterior ESEM / longitudinal invariance / DSEM | ADR 0005 | `psychometric_fit` ESEM loading and DSEM lag gates on the active PR; `psychometric_core` input gates remain #49; invariance/multilevel remain accepted-target | active-PR | diff --git a/docs/adr/0004-shared-multilingual-latent-space.md b/docs/adr/0004-shared-multilingual-latent-space.md index 06f42ada..02d347f8 100644 --- a/docs/adr/0004-shared-multilingual-latent-space.md +++ b/docs/adr/0004-shared-multilingual-latent-space.md @@ -1,6 +1,7 @@ # ADR 0004 — Shared multilingual latent semantic space **Decision status:** Accepted +**Implementation maturity:** accepted-target — style-versus-unique-content identity in `style_source` on the active PR; shared-space estimators remain accepted-target **Implementation maturity:** partial — default stopword-deletion refusal is `stopword_deletion` on the active PR; shared-space estimators, language profiles, and TF-IDF/BM25 inferential-weight refusal remain accepted-target **Date:** 2026-08-05 **Supersedes:** None. ADR 0012 governs the complete topic-estimator/backend/global-topic contract built on this multilingual measurement decision. diff --git a/docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md b/docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md index e3b70c71..d58291b9 100644 --- a/docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md +++ b/docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md @@ -1,6 +1,7 @@ # ADR 0012 — Temporal Relational Shared-Latent Topic Measurement **Decision status:** Accepted +**Implementation maturity:** accepted-target — style-versus-unique-content identity in `style_source` on the active PR; estimator-side method model remains accepted-target **Implementation maturity:** partial — default stopword-deletion refusal is `stopword_deletion` on the active PR; topic estimator, global topic identity, method-effect model, and TF-IDF/BM25 inferential-weight refusal remain accepted-target **Implementation maturity:** active-PR — `topic_lineage` keeps one P0 identity across active/dormant/reactivated states; remaining TRSL-TM estimator, method effects, and backend interchange remain accepted-target **Implementation maturity:** active-PR — `network_analysis` refuses raw-simplex Euclidean geometry and scores cluster pair precision/recall; remaining TRSL-TM estimator, global topic identity, method effects, and backend interchange remain accepted-target diff --git a/docs/adr/README.md b/docs/adr/README.md index 058f5472..59273110 100644 --- a/docs/adr/README.md +++ b/docs/adr/README.md @@ -25,6 +25,7 @@ Read [`ADR_POLICY.md`](ADR_POLICY.md) first. **Decision status and implementatio | [0002](0002-six-clock-temporal-semantics.md) | Six-clock temporal semantics and fail-closed historical leakage prevention | Accepted | active-PR | Typed clocks/intervals are implemented-main; `document_clocks` refuses omitted assertion/document time on the active PR. Later graph/split enforcement remains target work. | | [0002](0002-six-clock-temporal-semantics.md) | Six-clock temporal semantics and fail-closed historical leakage prevention | Accepted | active-PR | Provenance-vs-transition gate in `citation_edge` on the active PR; remaining graph/split enforcement stays accepted-target. | | [0003](0003-relational-event-multiple-membership.md) | Relational event ontology and time-varying cross-classified multiple membership | Accepted | partial | Weighted time-varying membership network/roles are active-PR (PR #12); full multilevel estimators, graph ontology, and persistence remain accepted-target. ADR 0016 owns event-intelligence tasks. | +| [0004](0004-shared-multilingual-latent-space.md) | One shared multilingual latent space with explicit invariance status | Accepted | accepted-target | Style-versus-unique-content identity is `style_source` on the active PR; ADR 0012 owns the full topic-estimator contract. | | [0004](0004-shared-multilingual-latent-space.md) | One shared multilingual latent space with explicit invariance status | Accepted | partial | Default stopword-deletion refusal is `stopword_deletion` on the active PR; ADR 0012 owns the full topic-estimator/backend/global-topic contract. | | [0005](0005-posterior-esem-dsem.md) | Posterior-aware ESEM/DSEM and valid compositional coordinates | Accepted | accepted-target | Downstream psychometric authority; upstream topic/network model is clarified by ADR 0012. | | [0002](0002-six-clock-temporal-semantics.md) | Six-clock temporal semantics and fail-closed historical leakage prevention | Accepted | partial | Typed clocks/intervals (merged PR #8) and Allen/path-consistency (merged PR #9) are implemented-main; superseded PRs #5/#6 are historical lineage only. Downstream estimator and remaining persistence-policy uses stay with their owning ADRs. | @@ -53,6 +54,7 @@ Read [`ADR_POLICY.md`](ADR_POLICY.md) first. **Decision status and implementatio | [0010](0010-adaptive-llm-orchestration.md) | Adaptive LLM orchestration and test-time compute | Accepted | partial | `tepp_api` router/ablation/orchestrator binding implemented-main; evidence-bounded `interpretation_gateway` is on the active PR; live NIM execution and production ablation evidence remain accepted-target. | | [0010](0010-adaptive-llm-orchestration.md) | Adaptive LLM orchestration and test-time compute | Accepted | partial | `tepp_api` router/ablation/orchestrator binding implemented-main; live NIM execution and production ablation evidence remain accepted-target. | | [0011](0011-standalone-modular-msa-boundary.md) | Standalone operation and modular CWL MSA boundary | Accepted | partial | Owns cross-service persistence/credential/API authority; no direct cross-service application-table coupling. | +| [0012](0012-temporal-relational-shared-latent-topic-measurement.md) | Temporal Relational Shared-Latent Topic Measurement (TRSL-TM) | Accepted | accepted-target | Style-versus-unique-content identity is `style_source` on the active PR; estimator-side method model, backend, and K gates remain accepted-target. | | [0012](0012-temporal-relational-shared-latent-topic-measurement.md) | Temporal Relational Shared-Latent Topic Measurement (TRSL-TM) | Accepted | partial | Default stopword-deletion refusal is `stopword_deletion` on the active PR; topic backend, global topic identity, method effects, K/model-selection, and TF-IDF/BM25 inferential-weight refusal remain accepted-target. | | [0013](0013-bitemporal-persistence-reproducibility-and-split-authority.md) | Bitemporal persistence, reproducibility manifests, and relation-aware split authority | Accepted | partial | Owns PostgreSQL adapter semantics, immutable run/split manifests, leakage-safe partitions, and recovery identity; optional `live-sqlx` `PgPool`, live PG CI, tenant RLS, and `0006` membership implemented-main; `0007` retention/deletion/legal-hold on the active PR; remaining physical ERD/backup accepted-target. | | [0012](0012-temporal-relational-shared-latent-topic-measurement.md) | Temporal Relational Shared-Latent Topic Measurement (TRSL-TM) | Accepted | accepted-target | Owns topic backend compatibility, global topic identity, method effects, K/model-selection prerequisites, and compositional topic coordinates. | diff --git a/docs/research/standards-and-literature.md b/docs/research/standards-and-literature.md index 36dffe08..562acc48 100644 --- a/docs/research/standards-and-literature.md +++ b/docs/research/standards-and-literature.md @@ -36,9 +36,7 @@ Bianchi, F., Terragni, S., Hovy, D., Nozza, D., & Fersini, E. (2021). Cross-ling Nguyen, T. P., Minh, N. V., Nguyen, T., Van, L. N., Nguyen, D. A., Sang, D. V., & Le, T. (2025). XTRA: Cross-lingual topic modeling with topic and representation alignments. In *Findings of the Association for Computational Linguistics: EMNLP 2025*. Association for Computational Linguistics. -Schofield, A., Magnusson, M., & Mimno, D. (2017). Pulling out the stops: Rethinking stopword removal for topic models. In *Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers* (pp. 432–436). Association for Computational Linguistics. https://doi.org/10.18653/v1/E17-2069 - -TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. Default or global stopword deletion is not a valid method for removing repeated report language; `stopword_deletion` refuses that treatment so boilerplate stays explicit method/background structure (Schofield, Magnusson, & Mimno, 2017). +TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. House-voice style residue is modeled as explicit structure, not unique latent content and not a stopword deletion (Roberts et al., 2019). ## Topic-model evaluation and LLM judges diff --git a/docs/research/style-source-identity.md b/docs/research/style-source-identity.md new file mode 100644 index 00000000..3e489be7 --- /dev/null +++ b/docs/research/style-source-identity.md @@ -0,0 +1,30 @@ +# House-voice style residue is not unique content (doctoring) + +## Scope + +`style_source` keeps house-voice and style residue out of unique latent +content and out of global stopword deletion. Recovery is the computed +share of recovered kinds that match known truth. + +This slice does not persist method sources, allocate migration `0008`, +or replace `method_effects`, `section_source`, or `stopword_deletion`. + +## Authority + +### Normative TEPP contract + +- `docs/adr/0004-shared-multilingual-latent-space.md` and + `docs/adr/0012-temporal-relational-shared-latent-topic-measurement.md` + — template, section, copied-text, style, modality, and + corpus-background sources are modeled explicitly and are not + inferential topic weights or stopword deletions. + +### Supporting literature + +Roberts, Stewart, and Tingley (2019) treat style and other +document-level covariates as explicit structure in a structural topic +model, not as tokens to delete. + +Roberts, M. E., Stewart, B. M., & Tingley, D. (2019). stm: An R package +for structural topic models. *Journal of Statistical Software, 91*(2), +1–40. https://doi.org/10.18637/jss.v091.i02 diff --git a/docs/validation/temporal-event-foundation.md b/docs/validation/temporal-event-foundation.md index c5de91ed..e2452a59 100644 --- a/docs/validation/temporal-event-foundation.md +++ b/docs/validation/temporal-event-foundation.md @@ -36,6 +36,7 @@ This report tracks exact-head scientific and engineering evidence required befor | Mention-confidence Brier score | `event_core` | active-PR | calibration vs binary truth | perfect 0 / half 0.25 RMSE | ADR 0003; `docs/research/mention-confidence-brier.md` | | Checkpoint is not the estimator | `checkpoint_authority` | accepted-target | active PR | refuse checkpoint-as-estimator + unvalidated artifact + recovery vs estimator collapse | ADR 0001/0014 | | Versioned API/export contracts | `tepp_api` | implemented-main | naruon HTTP interchange | unknown-field/version/limit + naruon HTTPS interchange tests | Task 12 / PR #21; live HTTP service remaining | +| Style-versus-unique-content identity | `style_source` | accepted-target | active PR | refuse style-as-unique/stopword + recovery vs unique-content collapse | ADR 0004/0012 | | Untrusted intake grant presence | `intake_authorization` | accepted-target | active PR | refuse missing grant + refuse bounds-as-authorization + recovery vs accept-all | ADR 0009; AGENTS.md | | Untrusted payload identity/provenance/size/depth | `payload_bound` | accepted-target | active PR | refuse missing identity/provenance and oversize/over-deep payloads + recovery vs accept-all | AGENTS.md untrusted-boundary | | System-clock identity | `system_clock` | active-PR | this PR | recovered system flags vs event-time stand-in | ADR 0002 | diff --git a/scripts/check_workspace_contract.py b/scripts/check_workspace_contract.py index e3dfb8db..edbb3f99 100644 --- a/scripts/check_workspace_contract.py +++ b/scripts/check_workspace_contract.py @@ -23,6 +23,7 @@ "tepp_simulation", "validation_core", "tepp_api", + "style_source", "stopword_deletion", "copy_identity", "provider_receipt",