cafa-ivr 1.1.0__tar.gz

cafa_ivr-1.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cafa_ivr-1.1.0/PKG-INFO

@@ -0,0 +1,203 @@
+Metadata-Version: 2.4
+Name: cafa-ivr
+Version: 1.1.0
+Summary: Reference implementation of Counterfactual ASR Failure Attribution for conversational IVR
+Author: Vijay Kumar Sridharan
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/sridharanvijaykumar/cafa-ivr
+Project-URL: Repository, https://github.com/sridharanvijaykumar/cafa-ivr
+Project-URL: Documentation, https://github.com/sridharanvijaykumar/cafa-ivr/tree/main/docs
+Project-URL: Issues, https://github.com/sridharanvijaykumar/cafa-ivr/issues
+Keywords: ASR,IVR,conversational AI,testing,WER,NLU
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Dynamic: license-file
+
+# CAFA-IVR
+
+[![CAFA-IVR CI](https://github.com/sridharanvijaykumar/cafa-ivr/actions/workflows/ci.yml/badge.svg)](https://github.com/sridharanvijaykumar/cafa-ivr/actions/workflows/ci.yml)
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](pyproject.toml)
+[![Release](https://img.shields.io/github/v/release/sridharanvijaykumar/cafa-ivr)](https://github.com/sridharanvijaykumar/cafa-ivr/releases)
+
+**Counterfactual ASR Failure Attribution for Conversational IVR**
+
+CAFA-IVR is a vendor-neutral testing framework for answering a practical question that Word Error Rate (WER) cannot answer by itself:
+
+> Did adding the speech/ASR path cause an otherwise valid conversational test to fail?
+
+## Core idea
+
+Run every semantic test through two paths:
+
+```text
+TEXT CONTROL: reference text -> NLU / agent -> task outcome
+AUDIO PATH:   audio -> ASR -> NLU / agent -> task outcome
+```
+
+CAFA-IVR then distinguishes:
+
+| Text control | Audio path | Attribution |
+|---|---|---|
+| Pass | Pass | HEALTHY |
+| Pass | Fail | SPEECH_ATTRIBUTABLE |
+| Fail | Fail | DOWNSTREAM_OR_TEST |
+| Fail | Pass | CONTEXT_OR_ORACLE |
+
+The primary metric is **ASR-IFR (ASR-Attributable Intent Failure Rate)**: the fraction of the full paired suite where the text control passes but the audio path fails.
+
+CAFA-IVR also supports:
+
+- **WER** - lexical transcription fidelity
+- **CEER** - Critical-Entity Error Rate for amounts, dates, negation, actions, etc. CEER is an **unbounded normalized error count, not a probability**: it divides critical-entity errors by the number of reference critical entities and may exceed 1.0 when a hypothesis introduces spurious entities, just as WER may exceed 1.0 under heavy insertion.
+- **CIER** - Critical-Impact Error Rate: a severity-weighted **realized-consequence** rate. Each trial with a recognized `impact_level` contributes its severity weight only when the audio-path task failed and contributes zero when it passed; trials without a recognized impact level are excluded. CIER counts realized task failures regardless of attribution. To isolate ASR-attributable consequence, restrict results to `attribution = SPEECH_ATTRIBUTABLE`.
+- condition-level summaries for clean, telephony, noise and speaking-rate tests
+- baseline-vs-candidate regression gates for CI/CD
+
+## Quick start
+
+Requires Python 3.10+.
+
+```bash
+git clone https://github.com/sridharanvijaykumar/cafa-ivr.git
+cd cafa-ivr
+python -m venv .venv
+source .venv/bin/activate
+pip install -e .
+cafa-ivr score \
+  --input examples/demo_results.csv \
+  --out demo_out
+```
+
+(If your environment blocks build isolation, use `pip install -e . --no-build-isolation`
+instead — it requires setuptools to be pre-installed: `pip install setuptools` first.)
+
+Outputs:
+
+```text
+demo_out/
+  scored_trials.csv
+  summary.csv
+  summary.json
+  report.md
+```
+
+The demo file is **illustrative only** and must not be cited as empirical evidence.
+
+To reproduce scoring on the measured 360-trial Conformer-CTC pilot included with this release:
+
+```bash
+cafa-ivr score \
+  --input empirical/conformer_360_cafa_input.csv \
+  --out measured_out
+```
+
+### What this release reproduces
+
+This release reproduces **scoring**: it recomputes the reported metrics from the decoded outputs supplied in `empirical/`. It does **not** include the audio-synthesis, ASR-decoding, perturbation, or bootstrap-resampling pipelines and therefore does not regenerate those decoded outputs. The 540 local decodes and the 5,000-sample bootstrap intervals reported in the paper are not reproducible end to end from this tag.
+
+A correct reproduction yields exactly: 360 trials, 142 speech-attributable failures,
+0.648429 mean WER, 0.411111 intent/task accuracy, 0.800000 text-control accuracy, and
+0.394444 ASR-IFR.
+
+What the attribution report looks like (real output from the scorer on the illustrative
+demo file — 12 trials, so CEER exceeds 1.0 here, which is expected behavior for an
+unbounded error count):
+
+```markdown
+# CAFA-IVR Results
+
+Trials: **12**
+Mean WER: **0.1944**
+Intent/task accuracy: **0.5000**
+Text-control accuracy: **0.8333**
+ASR-IFR: **0.3333**
+CEER: **2.0000**
+CIER: **0.3458**
+
+ASR-IFR counts trials where the reference-text control passes but the audio-path task fails.
+```
+
+## CI/CD gate
+
+```bash
+cafa-ivr compare \
+  --baseline baseline/summary.csv \
+  --candidate candidate/summary.csv \
+  --max-asr-ifr-delta 0.02 \
+  --max-ceer-delta 0.01
+```
+
+The default numeric gates are examples for tooling demonstration, not universal acceptance criteria. Production teams should govern their own thresholds by risk tier and historical baseline.
+
+Every enabled gate requires a present, numeric, finite metric in both summaries and fails closed on invalid input. Datasets without critical-entity annotations must explicitly disable that optional gate with `--no-ceer-gate`.
+
+## Integration contract
+
+CAFA-IVR does not require a specific ASR, NLU, contact-center platform, or agent architecture. An adapter only needs to populate the trial-result fields described in `docs/CAFA-IVR_SPEC_v1.0.md`.
+
+Possible integrations include:
+
+- cloud or on-prem ASR
+- intent classifiers
+- LLM voice agents
+- contact-center test harnesses
+- deterministic dialogue managers
+- tool-calling agents with task-success oracles
+
+## Evidence included in this release
+
+`empirical/` contains the locally measured controlled Conformer-CTC results used in the research manuscript plus public-human-source validation metadata. Synthetic-speech measurements and public-human source validation are deliberately kept separate.
+
+### Evidence boundary
+
+CAFA-IVR is a testing and attribution framework, not an ASR model. The included 360-trial neural pilot uses controlled synthetic speech and a constrained in-domain recognizer; it should **not** be interpreted as a production-ASR benchmark. Public human-banking material is retained as source/provenance validation and is not mixed with locally executed measurements.
+
+The included 360-trial pilot exercises **ASR-IFR** and **WER** only. It carries no critical-entity annotations and no impact labels, so **CEER** and **CIER** are specified and implemented but not exercised by this dataset; the reproduced summary accordingly reports `ceer: null` and `cier: null`.
+
+## Adoption
+
+Organizations adopting the framework should record the exact CAFA-IVR version, test scope, engines, thresholds, and change-management decision. `docs/ADOPTION_EVIDENCE_LOG.md` provides a neutral template so independent use is reproducible and auditable.
+
+Want to contribute? See [CONTRIBUTING.md](CONTRIBUTING.md) — good first areas include
+platform adapters, entity normalizers, CI/CD integrations, and documentation. Please
+respect the evidence rules there: no fabricated or estimated results presented as
+measurements.
+
+## Technical manuscript
+
+See `paper/CAFA-IVR.pdf` and `paper/CAFA-IVR.tex`.
+
+The repository provides this venue-neutral technical manuscript as supporting documentation and does not represent it as accepted or published.
+
+## License
+
+Reference implementation: Apache-2.0. Dataset/audio licensing remains governed by the source dataset or organization that owns the test material.
+
+## Author
+
+Vijay Kumar Sridharan
+IEEE Senior Member
+Frisco, TX, USA
+
+## Repository adoption workflow
+
+CAFA-IVR is designed to be forked or wrapped rather than requiring teams to replace their ASR/NLU stack. A typical adoption is:
+
+```text
+existing test audio ──> existing ASR ──> existing NLU/agent ──> result adapter
+ │
+reference text ─────────────────────────> same NLU/agent ────> text control
+ │
+ v
+ CAFA-IVR scorer
+```
+
+Teams can add an adapter under `adapters/`, generate the required trial CSV, run `cafa-ivr score`, and optionally place `cafa-ivr compare` in CI/CD. Independent evaluations are welcome through the adoption-report issue template.

cafa_ivr-1.1.0/README.md

@@ -0,0 +1,181 @@
+# CAFA-IVR
+
+[![CAFA-IVR CI](https://github.com/sridharanvijaykumar/cafa-ivr/actions/workflows/ci.yml/badge.svg)](https://github.com/sridharanvijaykumar/cafa-ivr/actions/workflows/ci.yml)
+[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python](https://img.shields.io/badge/python-3.10%2B-blue.svg)](pyproject.toml)
+[![Release](https://img.shields.io/github/v/release/sridharanvijaykumar/cafa-ivr)](https://github.com/sridharanvijaykumar/cafa-ivr/releases)
+
+**Counterfactual ASR Failure Attribution for Conversational IVR**
+
+CAFA-IVR is a vendor-neutral testing framework for answering a practical question that Word Error Rate (WER) cannot answer by itself:
+
+> Did adding the speech/ASR path cause an otherwise valid conversational test to fail?
+
+## Core idea
+
+Run every semantic test through two paths:
+
+```text
+TEXT CONTROL: reference text -> NLU / agent -> task outcome
+AUDIO PATH:   audio -> ASR -> NLU / agent -> task outcome
+```
+
+CAFA-IVR then distinguishes:
+
+| Text control | Audio path | Attribution |
+|---|---|---|
+| Pass | Pass | HEALTHY |
+| Pass | Fail | SPEECH_ATTRIBUTABLE |
+| Fail | Fail | DOWNSTREAM_OR_TEST |
+| Fail | Pass | CONTEXT_OR_ORACLE |
+
+The primary metric is **ASR-IFR (ASR-Attributable Intent Failure Rate)**: the fraction of the full paired suite where the text control passes but the audio path fails.
+
+CAFA-IVR also supports:
+
+- **WER** - lexical transcription fidelity
+- **CEER** - Critical-Entity Error Rate for amounts, dates, negation, actions, etc. CEER is an **unbounded normalized error count, not a probability**: it divides critical-entity errors by the number of reference critical entities and may exceed 1.0 when a hypothesis introduces spurious entities, just as WER may exceed 1.0 under heavy insertion.
+- **CIER** - Critical-Impact Error Rate: a severity-weighted **realized-consequence** rate. Each trial with a recognized `impact_level` contributes its severity weight only when the audio-path task failed and contributes zero when it passed; trials without a recognized impact level are excluded. CIER counts realized task failures regardless of attribution. To isolate ASR-attributable consequence, restrict results to `attribution = SPEECH_ATTRIBUTABLE`.
+- condition-level summaries for clean, telephony, noise and speaking-rate tests
+- baseline-vs-candidate regression gates for CI/CD
+
+## Quick start
+
+Requires Python 3.10+.
+
+```bash
+git clone https://github.com/sridharanvijaykumar/cafa-ivr.git
+cd cafa-ivr
+python -m venv .venv
+source .venv/bin/activate
+pip install -e .
+cafa-ivr score \
+  --input examples/demo_results.csv \
+  --out demo_out
+```
+
+(If your environment blocks build isolation, use `pip install -e . --no-build-isolation`
+instead — it requires setuptools to be pre-installed: `pip install setuptools` first.)
+
+Outputs:
+
+```text
+demo_out/
+  scored_trials.csv
+  summary.csv
+  summary.json
+  report.md
+```
+
+The demo file is **illustrative only** and must not be cited as empirical evidence.
+
+To reproduce scoring on the measured 360-trial Conformer-CTC pilot included with this release:
+
+```bash
+cafa-ivr score \
+  --input empirical/conformer_360_cafa_input.csv \
+  --out measured_out
+```
+
+### What this release reproduces
+
+This release reproduces **scoring**: it recomputes the reported metrics from the decoded outputs supplied in `empirical/`. It does **not** include the audio-synthesis, ASR-decoding, perturbation, or bootstrap-resampling pipelines and therefore does not regenerate those decoded outputs. The 540 local decodes and the 5,000-sample bootstrap intervals reported in the paper are not reproducible end to end from this tag.
+
+A correct reproduction yields exactly: 360 trials, 142 speech-attributable failures,
+0.648429 mean WER, 0.411111 intent/task accuracy, 0.800000 text-control accuracy, and
+0.394444 ASR-IFR.
+
+What the attribution report looks like (real output from the scorer on the illustrative
+demo file — 12 trials, so CEER exceeds 1.0 here, which is expected behavior for an
+unbounded error count):
+
+```markdown
+# CAFA-IVR Results
+
+Trials: **12**
+Mean WER: **0.1944**
+Intent/task accuracy: **0.5000**
+Text-control accuracy: **0.8333**
+ASR-IFR: **0.3333**
+CEER: **2.0000**
+CIER: **0.3458**
+
+ASR-IFR counts trials where the reference-text control passes but the audio-path task fails.
+```
+
+## CI/CD gate
+
+```bash
+cafa-ivr compare \
+  --baseline baseline/summary.csv \
+  --candidate candidate/summary.csv \
+  --max-asr-ifr-delta 0.02 \
+  --max-ceer-delta 0.01
+```
+
+The default numeric gates are examples for tooling demonstration, not universal acceptance criteria. Production teams should govern their own thresholds by risk tier and historical baseline.
+
+Every enabled gate requires a present, numeric, finite metric in both summaries and fails closed on invalid input. Datasets without critical-entity annotations must explicitly disable that optional gate with `--no-ceer-gate`.
+
+## Integration contract
+
+CAFA-IVR does not require a specific ASR, NLU, contact-center platform, or agent architecture. An adapter only needs to populate the trial-result fields described in `docs/CAFA-IVR_SPEC_v1.0.md`.
+
+Possible integrations include:
+
+- cloud or on-prem ASR
+- intent classifiers
+- LLM voice agents
+- contact-center test harnesses
+- deterministic dialogue managers
+- tool-calling agents with task-success oracles
+
+## Evidence included in this release
+
+`empirical/` contains the locally measured controlled Conformer-CTC results used in the research manuscript plus public-human-source validation metadata. Synthetic-speech measurements and public-human source validation are deliberately kept separate.
+
+### Evidence boundary
+
+CAFA-IVR is a testing and attribution framework, not an ASR model. The included 360-trial neural pilot uses controlled synthetic speech and a constrained in-domain recognizer; it should **not** be interpreted as a production-ASR benchmark. Public human-banking material is retained as source/provenance validation and is not mixed with locally executed measurements.
+
+The included 360-trial pilot exercises **ASR-IFR** and **WER** only. It carries no critical-entity annotations and no impact labels, so **CEER** and **CIER** are specified and implemented but not exercised by this dataset; the reproduced summary accordingly reports `ceer: null` and `cier: null`.
+
+## Adoption
+
+Organizations adopting the framework should record the exact CAFA-IVR version, test scope, engines, thresholds, and change-management decision. `docs/ADOPTION_EVIDENCE_LOG.md` provides a neutral template so independent use is reproducible and auditable.
+
+Want to contribute? See [CONTRIBUTING.md](CONTRIBUTING.md) — good first areas include
+platform adapters, entity normalizers, CI/CD integrations, and documentation. Please
+respect the evidence rules there: no fabricated or estimated results presented as
+measurements.
+
+## Technical manuscript
+
+See `paper/CAFA-IVR.pdf` and `paper/CAFA-IVR.tex`.
+
+The repository provides this venue-neutral technical manuscript as supporting documentation and does not represent it as accepted or published.
+
+## License
+
+Reference implementation: Apache-2.0. Dataset/audio licensing remains governed by the source dataset or organization that owns the test material.
+
+## Author
+
+Vijay Kumar Sridharan
+IEEE Senior Member
+Frisco, TX, USA
+
+## Repository adoption workflow
+
+CAFA-IVR is designed to be forked or wrapped rather than requiring teams to replace their ASR/NLU stack. A typical adoption is:
+
+```text
+existing test audio ──> existing ASR ──> existing NLU/agent ──> result adapter
+ │
+reference text ─────────────────────────> same NLU/agent ────> text control
+ │
+ v
+ CAFA-IVR scorer
+```
+
+Teams can add an adapter under `adapters/`, generate the required trial CSV, run `cafa-ivr score`, and optionally place `cafa-ivr compare` in CI/CD. Independent evaluations are welcome through the adoption-report issue template.

cafa_ivr-1.1.0/pyproject.toml

@@ -0,0 +1,37 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cafa-ivr"
+version = "1.1.0"
+description = "Reference implementation of Counterfactual ASR Failure Attribution for conversational IVR"
+readme = "README.md"
+requires-python = ">=3.10"
+authors = [{name = "Vijay Kumar Sridharan"}]
+license = {text = "Apache-2.0"}
+keywords = ["ASR", "IVR", "conversational AI", "testing", "WER", "NLU"]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "License :: OSI Approved :: Apache Software License",
+  "Intended Audience :: Developers",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+[project.scripts]
+cafa-ivr = "cafa_ivr.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[project.optional-dependencies]
+dev = ["pytest>=8"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[project.urls]
+Homepage = "https://github.com/sridharanvijaykumar/cafa-ivr"
+Repository = "https://github.com/sridharanvijaykumar/cafa-ivr"
+Documentation = "https://github.com/sridharanvijaykumar/cafa-ivr/tree/main/docs"
+Issues = "https://github.com/sridharanvijaykumar/cafa-ivr/issues"

cafa_ivr-1.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

cafa_ivr-1.1.0/src/cafa_ivr/__init__.py

@@ -0,0 +1,2 @@
+__version__ = "1.1.0"
+from .core import attribution, cafa_score_row, critical_entity_error_rate, word_error_rate

cafa_ivr-1.1.0/src/cafa_ivr/__main__.py

@@ -0,0 +1,3 @@
+from .cli import main
+if __name__ == "__main__":
+    main()