diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md index 77340ec2..1aff5315 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 | +| `copied_text` | copied-text residue is not unique latent content and not stopword deletion | | `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 | diff --git a/CHANGELOG.md b/CHANGELOG.md index 4bdc0d0f..5d918bf4 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 +- `copied_text` identity gate: copied and boilerplate residue is not unique latent content and is not erased by a stopword list; recovered copied-text kinds match known truth at a higher computed rate than collapsing every token to unique content (ADR 0004/0012). - `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. diff --git a/Cargo.lock b/Cargo.lock index 8f0889cb..25b151bf 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -191,6 +191,10 @@ version = "0.5.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "0c9ea0ac24bc397ab3c98583a3c9ba74fa56b09a4449bbe172b9b1ddb016027a" +[[package]] +name = "copied_text" +version = "0.1.0" + [[package]] name = "copy_identity" version = "0.1.0" diff --git a/Cargo.toml b/Cargo.toml index 5563462d..0239c9ab 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -11,6 +11,7 @@ members = [ "crates/tepp_simulation", "crates/validation_core", "crates/tepp_api", + "crates/copied_text", "crates/style_source", "crates/stopword_deletion", "crates/copy_identity", @@ -56,6 +57,7 @@ default-members = [ "crates/tepp_simulation", "crates/validation_core", "crates/tepp_api", + "crates/copied_text", "crates/style_source", "crates/stopword_deletion", "crates/copy_identity", diff --git a/README.md b/README.md index f7fb7ab1..c5d73e01 100644 --- a/README.md +++ b/README.md @@ -43,6 +43,7 @@ crates/corpus_split crates/tepp_simulation crates/validation_core crates/tepp_api +crates/copied_text crates/style_source crates/stopword_deletion crates/copy_identity diff --git a/crates/copied_text/Cargo.toml b/crates/copied_text/Cargo.toml new file mode 100644 index 00000000..1cfd7b08 --- /dev/null +++ b/crates/copied_text/Cargo.toml @@ -0,0 +1,17 @@ +[package] +name = "copied_text" +description = "Copied-text 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/copied_text/src/error.rs b/crates/copied_text/src/error.rs new file mode 100644 index 00000000..d79228db --- /dev/null +++ b/crates/copied_text/src/error.rs @@ -0,0 +1,55 @@ +//! Fail-closed copied-text errors. + +use std::fmt; + +/// A fail-closed copied-text error. +#[derive(Clone, Copy, Debug, Eq, PartialEq)] +#[non_exhaustive] +pub enum CopiedTextError { + /// Copied-text residue was treated as unique latent content. + CopiedTextIsNotUniqueContent, + /// Copied-text residue was treated as stopword deletion. + CopiedTextIsNotStopwordDeletion, + /// A recovery slice was empty or length-mismatched. + InvalidCopiedPayload, +} + +impl fmt::Display for CopiedTextError { + fn fmt(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result { + let message = match self { + Self::CopiedTextIsNotUniqueContent => { + "copied-text residue is not unique latent content" + } + Self::CopiedTextIsNotStopwordDeletion => "copied-text residue is not stopword deletion", + Self::InvalidCopiedPayload => "invalid copied-text payload", + }; + formatter.write_str(message) + } +} + +impl std::error::Error for CopiedTextError {} + +#[cfg(test)] +mod tests { + use super::CopiedTextError; + + #[test] + fn error_messages_are_stable() { + for (error, message) in [ + ( + CopiedTextError::CopiedTextIsNotUniqueContent, + "copied-text residue is not unique latent content", + ), + ( + CopiedTextError::CopiedTextIsNotStopwordDeletion, + "copied-text residue is not stopword deletion", + ), + ( + CopiedTextError::InvalidCopiedPayload, + "invalid copied-text payload", + ), + ] { + assert_eq!(error.to_string(), message); + } + } +} diff --git a/crates/copied_text/src/kind.rs b/crates/copied_text/src/kind.rs new file mode 100644 index 00000000..fc94428d --- /dev/null +++ b/crates/copied_text/src/kind.rs @@ -0,0 +1,128 @@ +//! Copied-text residue versus unique latent content. + +use crate::CopiedTextError; + +/// Closed vocabulary of copied-text token treatments. +#[derive(Clone, Copy, Debug, Eq, PartialEq)] +pub enum CopiedKind { + /// Copied or boilerplate residue, not unique document meaning. + CopiedText, + /// Token treatment reserved for unique latent content. + UniqueContent, +} + +impl CopiedKind { + /// Return the stable wire kind name. + #[must_use] + pub const fn wire_name(self) -> &'static str { + match self { + Self::CopiedText => "copied_text", + Self::UniqueContent => "unique_content", + } + } + + /// Parse a stable wire kind name. + /// + /// # Errors + /// + /// Returns [`CopiedTextError::InvalidCopiedPayload`] for unrecognized names. + pub fn from_wire_name(name: &str) -> Result { + match name { + "copied_text" => Ok(Self::CopiedText), + "unique_content" => Ok(Self::UniqueContent), + _ => Err(CopiedTextError::InvalidCopiedPayload), + } + } +} + +/// Refuse to treat copied-text residue as unique latent content. +/// +/// # Errors +/// +/// Returns [`CopiedTextError::CopiedTextIsNotUniqueContent`] when `kind` is +/// [`CopiedKind::CopiedText`]. +pub fn refuse_copied_text_as_unique_content(kind: CopiedKind) -> Result<(), CopiedTextError> { + match kind { + CopiedKind::CopiedText => Err(CopiedTextError::CopiedTextIsNotUniqueContent), + CopiedKind::UniqueContent => Ok(()), + } +} + +/// Refuse to treat copied-text residue as stopword deletion. +/// +/// # Errors +/// +/// Returns [`CopiedTextError::CopiedTextIsNotStopwordDeletion`] when `kind` is +/// [`CopiedKind::CopiedText`]. +pub fn refuse_copied_text_as_stopword_deletion(kind: CopiedKind) -> Result<(), CopiedTextError> { + match kind { + CopiedKind::CopiedText => Err(CopiedTextError::CopiedTextIsNotStopwordDeletion), + CopiedKind::UniqueContent => Ok(()), + } +} + +/// Fraction of recovered copied-text kinds that match known truth. +/// +/// # Errors +/// +/// Returns [`CopiedTextError::InvalidCopiedPayload`] when either slice is +/// empty or the lengths differ. +pub fn identity_recovery_rate( + truth: &[CopiedKind], + decided: &[CopiedKind], +) -> Result { + if truth.is_empty() || truth.len() != decided.len() { + return Err(CopiedTextError::InvalidCopiedPayload); + } + 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::{ + CopiedKind, identity_recovery_rate, refuse_copied_text_as_stopword_deletion, + refuse_copied_text_as_unique_content, + }; + use crate::CopiedTextError; + + #[test] + fn local_branches_cover_kinds_payloads_and_wire_names() { + assert_eq!( + refuse_copied_text_as_unique_content(CopiedKind::CopiedText), + Err(CopiedTextError::CopiedTextIsNotUniqueContent) + ); + assert_eq!( + refuse_copied_text_as_stopword_deletion(CopiedKind::CopiedText), + Err(CopiedTextError::CopiedTextIsNotStopwordDeletion) + ); + refuse_copied_text_as_unique_content(CopiedKind::UniqueContent).expect("unique"); + refuse_copied_text_as_stopword_deletion(CopiedKind::UniqueContent).expect("unique"); + for kind in [CopiedKind::CopiedText, CopiedKind::UniqueContent] { + assert_eq!( + CopiedKind::from_wire_name(kind.wire_name()).expect("round-trip"), + kind + ); + } + assert_eq!( + CopiedKind::from_wire_name("stopword"), + Err(CopiedTextError::InvalidCopiedPayload) + ); + let matched = identity_recovery_rate(&[CopiedKind::CopiedText], &[CopiedKind::CopiedText]) + .expect("rate"); + assert!((matched - 1.0).abs() < f64::EPSILON); + assert_eq!( + identity_recovery_rate(&[], &[]), + Err(CopiedTextError::InvalidCopiedPayload) + ); + assert_eq!( + identity_recovery_rate(&[CopiedKind::CopiedText], &[]), + Err(CopiedTextError::InvalidCopiedPayload) + ); + } +} diff --git a/crates/copied_text/src/lib.rs b/crates/copied_text/src/lib.rs new file mode 100644 index 00000000..4ad05c52 --- /dev/null +++ b/crates/copied_text/src/lib.rs @@ -0,0 +1,22 @@ +#![forbid(unsafe_code)] +#![deny(missing_docs)] +#![allow(clippy::cast_precision_loss)] +//! Copied-text residue is not unique latent content. +//! +//! Copied and boilerplate passages 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 copied-text errors. +pub use error::CopiedTextError; +/// Closed vocabulary of copied-text token treatments. +pub use kind::CopiedKind; +/// Fraction of recovered copied-text kinds that match known truth. +pub use kind::identity_recovery_rate; +/// Refuse to treat copied-text residue as stopword deletion. +pub use kind::refuse_copied_text_as_stopword_deletion; +/// Refuse to treat copied-text residue as unique latent content. +pub use kind::refuse_copied_text_as_unique_content; diff --git a/crates/copied_text/tests/copied_text_contract.rs b/crates/copied_text/tests/copied_text_contract.rs new file mode 100644 index 00000000..f1c7d2ee --- /dev/null +++ b/crates/copied_text/tests/copied_text_contract.rs @@ -0,0 +1,67 @@ +//! Copied-text residue is not unique content and not stopword deletion. + +use copied_text::{ + CopiedKind, CopiedTextError, identity_recovery_rate, refuse_copied_text_as_stopword_deletion, + refuse_copied_text_as_unique_content, +}; + +#[test] +fn copied_text_cannot_become_unique_content_or_stopword_deletion() { + assert_eq!( + refuse_copied_text_as_unique_content(CopiedKind::CopiedText), + Err(CopiedTextError::CopiedTextIsNotUniqueContent) + ); + assert_eq!( + refuse_copied_text_as_stopword_deletion(CopiedKind::CopiedText), + Err(CopiedTextError::CopiedTextIsNotStopwordDeletion) + ); + refuse_copied_text_as_unique_content(CopiedKind::UniqueContent).expect("unique"); + refuse_copied_text_as_stopword_deletion(CopiedKind::UniqueContent).expect("unique"); +} + +#[test] +fn recovered_kinds_match_known_truth_better_than_a_unique_content_collapse() { + let truth = [ + CopiedKind::CopiedText, + CopiedKind::UniqueContent, + CopiedKind::CopiedText, + ]; + let recovered = truth; + let collapsed = [ + CopiedKind::UniqueContent, + CopiedKind::UniqueContent, + CopiedKind::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(CopiedTextError::InvalidCopiedPayload) + ); + assert_eq!( + identity_recovery_rate(&[CopiedKind::CopiedText], &[]), + Err(CopiedTextError::InvalidCopiedPayload) + ); + assert_eq!( + identity_recovery_rate( + &[CopiedKind::CopiedText, CopiedKind::UniqueContent], + &[CopiedKind::CopiedText] + ), + Err(CopiedTextError::InvalidCopiedPayload) + ); +} diff --git a/crates/copied_text/tests/crate_contract.rs b/crates/copied_text/tests/crate_contract.rs new file mode 100644 index 00000000..5dcedc2b --- /dev/null +++ b/crates/copied_text/tests/crate_contract.rs @@ -0,0 +1,7 @@ +//! Integration contract for the `copied_text` package identity. + +#[test] +fn package_identity_is_stable() { + let observed = std::hint::black_box(env!("CARGO_PKG_NAME")); + assert_eq!(observed, "copied_text"); +} diff --git a/docs/TRACEABILITY.md b/docs/TRACEABILITY.md index 144a5178..2cec0d97 100644 --- a/docs/TRACEABILITY.md +++ b/docs/TRACEABILITY.md @@ -25,7 +25,7 @@ The full APA 7th standards/literature register remains `docs/research/standards- | 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 | 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 | +| report template/section/copied/style/modality method effects | ADR 0004/0012; PRD/TRD | simulation truth factors implemented; `copied_text` copied-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 02d347f8..bb53160e 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 — copied-versus-unique-content identity in `copied_text` on the active PR; shared-space estimators remain accepted-target **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 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 d58291b9..e7330296 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 — copied-versus-unique-content identity in `copied_text` on the active PR; estimator-side method model remains accepted-target **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 diff --git a/docs/adr/README.md b/docs/adr/README.md index 59273110..fd3d6877 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 | Copied-versus-unique-content identity is `copied_text` 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 | 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. | @@ -54,6 +55,7 @@ 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 | Copied-versus-unique-content identity is `copied_text` 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 | 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. | diff --git a/docs/research/copied-text-identity.md b/docs/research/copied-text-identity.md new file mode 100644 index 00000000..dfcef5cd --- /dev/null +++ b/docs/research/copied-text-identity.md @@ -0,0 +1,34 @@ +# Copied-text residue is not unique content (doctoring) + +## Scope + +`copied_text` keeps copied and boilerplate passages 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`, `style_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 + +Kohlschütter, Fankhauser, and Nejdl (2010) separate boilerplate and +copied residue from unique page content using shallow text features. +Copied wording is structure, not the unique latent meaning TEPP must +keep distinct. + +Kohlschütter, C., Fankhauser, P., & Nejdl, W. (2010). Boilerplate +detection using shallow text features. In *Proceedings of the Third ACM +International Conference on Web Search and Data Mining* (pp. 441–450). +Association for Computing Machinery. +https://doi.org/10.1145/1718487.1718542 diff --git a/docs/research/standards-and-literature.md b/docs/research/standards-and-literature.md index 562acc48..edc368a1 100644 --- a/docs/research/standards-and-literature.md +++ b/docs/research/standards-and-literature.md @@ -36,7 +36,9 @@ 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. -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). +Kohlschütter, C., Fankhauser, P., & Nejdl, W. (2010). Boilerplate detection using shallow text features. In *Proceedings of the Third ACM International Conference on Web Search and Data Mining* (pp. 441–450). Association for Computing Machinery. https://doi.org/10.1145/1718487.1718542 + +TEPP retains a logistic-normal CPU reference while allowing adapter backends that satisfy shared-latent, posterior, temporal, relational, and measurement-invariance contracts. Copied and boilerplate residue is modeled as explicit structure, not unique latent content and not a stopword deletion (Kohlschütter et al., 2010). ## Topic-model evaluation and LLM judges diff --git a/docs/validation/temporal-event-foundation.md b/docs/validation/temporal-event-foundation.md index e2452a59..c15acafb 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 | +| Copied-versus-unique-content identity | `copied_text` | accepted-target | active PR | refuse copied-text-as-unique/stopword + recovery vs unique-content collapse | ADR 0004/0012 | | 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 | diff --git a/scripts/check_workspace_contract.py b/scripts/check_workspace_contract.py index edbb3f99..f8cbbb5d 100644 --- a/scripts/check_workspace_contract.py +++ b/scripts/check_workspace_contract.py @@ -23,6 +23,7 @@ "tepp_simulation", "validation_core", "tepp_api", + "copied_text", "style_source", "stopword_deletion", "copy_identity",