structuremappingmemory 1.0.0__tar.gz

structuremappingmemory-1.0.0/LICENSE

@@ -0,0 +1,204 @@
+
+                                 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.
+
+   Copyright 2026 Ayaz Khan and SMA-1 contributors

structuremappingmemory-1.0.0/PKG-INFO

@@ -0,0 +1,190 @@
+Metadata-Version: 2.4
+Name: structuremappingmemory
+Version: 1.0.0
+Summary: SMA-1: Structure-Mapping Agentic Memory — a structure-mapping retrieval memory that grounds language models in curated ontologies
+Author-email: Ayaz Khan <aak2259@columbia.edu>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/ayazkhan27/SMA-1
+Project-URL: Repository, https://github.com/ayazkhan27/SMA-1
+Project-URL: Issues, https://github.com/ayazkhan27/SMA-1/issues
+Keywords: structure-mapping,analogical-retrieval,ontology,retrieval-augmented-generation,abstention,novelty-detection,trustworthy-ai,knowledge-graph
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: blake3>=0.4
+Requires-Dist: fastapi>=0.110
+Requires-Dist: gradio>=4.44
+Requires-Dist: hnswlib>=0.8
+Requires-Dist: lmdb>=1.4
+Requires-Dist: numpy>=1.26
+Requires-Dist: ortools>=9.10
+Requires-Dist: pydantic>=2
+Requires-Dist: pytest>=8
+Requires-Dist: hypothesis>=6
+Requires-Dist: rank-bm25>=0.2.2
+Requires-Dist: regex>=2024.5.15
+Requires-Dist: scikit-learn>=1.5
+Requires-Dist: typer>=0.12
+Requires-Dist: zstandard>=0.22
+Provides-Extra: encoders
+Requires-Dist: drain3>=0.9.11; extra == "encoders"
+Requires-Dist: tree-sitter>=0.23; extra == "encoders"
+Requires-Dist: tree-sitter-language-pack>=0.7; extra == "encoders"
+Requires-Dist: nltk>=3.9; extra == "encoders"
+Requires-Dist: stanza>=1.8; extra == "encoders"
+Provides-Extra: eval
+Requires-Dist: langchain>=0.2; extra == "eval"
+Requires-Dist: langchain-community>=0.2; extra == "eval"
+Requires-Dist: rank-bm25>=0.2.2; extra == "eval"
+Requires-Dist: ranx>=0.3.20; extra == "eval"
+Requires-Dist: sentence-transformers>=3; extra == "eval"
+Requires-Dist: statsmodels>=0.14; extra == "eval"
+Requires-Dist: kuzu>=0.6; extra == "eval"
+Requires-Dist: networkx>=3; extra == "eval"
+Provides-Extra: local-llm
+Requires-Dist: huggingface-hub>=0.23; extra == "local-llm"
+Requires-Dist: llama-cpp-python>=0.2.90; extra == "local-llm"
+Dynamic: license-file
+
+# SMA-1: Structure-Mapping Agentic Memory
+
+[![CI](https://github.com/ayazkhan27/SMA-1/actions/workflows/ci.yml/badge.svg)](https://github.com/ayazkhan27/SMA-1/actions/workflows/ci.yml)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![HF Space](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Space-orange)](https://huggingface.co/spaces/zephyr27/SMA-1-demo)
+
+**Structure-mapping memory grounds language models in curated ontologies.** SMA is
+a retrieval *memory* that grounds a generalist LLM in a **curated,
+expert-maintained ontology**, retrieving by **logical structure** — subsumption
+(is-a) and higher-order relations — that vector RAG and knowledge graphs discard. Holding the language model and prompt fixed and swapping
+only the memory, the SMA-grounded agent becomes **more accurate, more selective,
+and more structurally attributable** than vector RAG: it cites its evidence
+structurally, abstains when nothing grounds the case, and flags novelty —
+capabilities flat retrievers structurally lack. On the real-domain benchmarks the
+measured advantage is carried by bounded is-a subsumption plus information-content
+weighting (the higher-order relational machinery is decisive only on a synthetic
+structure-only control), and it vanishes where no discriminative ontology applies.
+
+![SMA process tour](docs/assets/sma_tour.gif)
+
+> A structure-mapping memory over a curated ontology grounds a generalist LLM by
+> the subsumption hierarchy and rarity weighting that flat retrievers wash out —
+> and the structural alignment itself is what survives when there is no surface
+> signal at all.
+
+---
+
+## What it does
+
+| Capability | SMA | Vector RAG | Knowledge graph |
+|---|:--:|:--:|:--:|
+| Rare / long-tail retrieval (rarity-weighted) | ✅ | ✗ averages rarity away | ✗ |
+| Cross-vocabulary / zero-lexical-overlap match | ✅ | ✗ | partial |
+| Subsumption (is-a) reasoning | ✅ | ✗ | ✗ no ascension |
+| Structural citation (checkable provenance) | ✅ | ✗ | partial |
+| Calibrated abstention | ✅ | ✗ cosine always "high" | ✗ |
+| Novelty / expectation-violation flag | ✅ | ✗ | partial |
+
+One **universal loader** ingests any open OBO/OWL/STIX/CPC ontology (is-a hierarchy
+plus typed relations, no OWL reasoning); a **registry + domain router** select
+across domains. We mount eleven ontologies spanning seven knowledge areas
+(≈594,000 concepts) behind one shared retrieval core plus thin per-domain data
+adapters.
+
+![SMA system overview](docs/assets/fig1_overview.png)
+
+## Headline results (honest)
+
+On a **memory-swap benchmark** where only the retriever varies, SMA beats a strong
+RAG + KG baseline suite on the rare/long-tail slice across five domains:
+
+| Domain | SMA tail top-5 | best RAG | Δ | Holm-significant |
+|---|:--:|:--:|:--:|:--:|
+| Medicine (HPO/MONDO) | 0.949 | 0.606 | **+0.333** | yes |
+| Finance (US-GAAP) | 0.418 | 0.231 | **+0.167** | yes |
+| Genomics (GO) | 0.849 | 0.682 | **+0.156** | yes |
+| Legal (CPC, all-query) | 0.941 | 0.870 | **+0.064** | yes |
+| Cyber (ATT&CK) | 0.766 | 0.749 | +0.073 | directional* |
+
+\* Cyber survives Holm across domains but not a conservative
+Bonferroni-over-baselines selection correction (p=0.035 → 0.17); reported as
+directional. End to end (medicine, LLM-in-the-loop), the SMA-grounded agent is the
+most accurate (0.342 vs dense 0.100 vs closed-book 0.017), most faithful in
+citation, and uniquely separates known from unknown entities (grounding AUROC 0.79
+vs vector RAG's near-chance 0.55).
+
+**Where it does not help (reported, not hidden):** SMA *ties* a bespoke ontology
+information-content oracle (Phenomizer) rather than beating it; and on
+**flat single-record tabular prediction** (hospital readmission, credit-card
+fraud, the Elliptic Bitcoin graph-fraud probe) there is no discriminative
+subsumption ontology to mount, so SMA reaches only parity and a flat
+logistic-regression baseline wins. The advantage is specific to structure.
+
+## How it works
+
+![SMA architecture](docs/assets/architecture.png)
+
+1. **Adapter** — a universal loader parses any open ontology into a normalized
+   graph, **mounts** the is-a hierarchy as an *ascension lattice* (specific terms
+   match general ones with penalty ρ^dist) and the typed relations as higher-order
+   cases, and registers them behind a per-query domain router.
+2. **Matcher** — a case (functors over a subject) is screened by a certified
+   **MAC** admissible-content bound, aligned by best-first structure-mapping
+   (**FAC/SME**), and scored by a rarity-weighted **information-content** (−log₂ p)
+   surprisal scorer.
+3. **Decision** — the alignment yields a **structural citation**, a **calibrated
+   abstention**, or a **novelty flag** (SAGE expectation violation).
+
+## Quick start
+
+```bash
+python -m venv .venv && . .venv/bin/activate
+pip install -e ".[encoders,eval]"
+pytest -m "gate_G0 or gate_G1 or gate_G2 or gate_G3 or gate_G4 or gate_G5 or gate_G6"
+sma ui                       # FastAPI + Gradio demo
+```
+
+Raw datasets are not tracked. Fetch checksum-verified external data with:
+
+```bash
+python scripts/fetch_datasets.py --manifest data/manifests/datasets.json
+```
+
+Reproduce the confirmatory tables/figures from committed CSVs:
+
+```bash
+python scripts/figures_paper.py      # main-text figures
+python scripts/figures_ed.py         # Extended Data figures
+```
+
+All result numbers in the paper trace to `reports/confirmatory/*.csv`; runs are
+deterministic (`PYTHONHASHSEED=0`, paired bootstrap seeded at 12345).
+
+## Repository layout
+
+| Path | Contents |
+|---|---|
+| `sma/ontology/` | universal ontology adapter (loaders, mount, registry, router) — **frozen `adapter-v1`** |
+| `sma/eval/agentic/` | memory-swap retrieval harness + baseline arms |
+| `sma/eval/agentic_qa/` | end-to-end LLM-QA agent (pre-registration v2) |
+| `scripts/` | dataset fetch, figure/table generators, ablations |
+| `reports/confirmatory/` | all result CSVs (every paper number sources here) |
+| `paper/manuscript/` | `sma_nature_mi.tex` — the manuscript (Nature `sn-jnl` template) |
+| `release/` | model card, dataset card, HuggingFace Space |
+
+## Paper & citation
+
+The manuscript (`paper/manuscript/sma_nature_mi.tex`, intended for *Nature Machine
+Intelligence*) is built on the official Springer Nature `sn-jnl` template. To cite
+this software, see [`CITATION.cff`](CITATION.cff).
+
+## License
+
+Apache-2.0. All mounted ontologies are openly licensed and version-pinned; we
+redistribute only derived gold labels, never restricted source records (see
+Extended Data and `release/model_card.md`).

structuremappingmemory-1.0.0/README.md

@@ -0,0 +1,136 @@
+# SMA-1: Structure-Mapping Agentic Memory
+
+[![CI](https://github.com/ayazkhan27/SMA-1/actions/workflows/ci.yml/badge.svg)](https://github.com/ayazkhan27/SMA-1/actions/workflows/ci.yml)
+[![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![HF Space](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Space-orange)](https://huggingface.co/spaces/zephyr27/SMA-1-demo)
+
+**Structure-mapping memory grounds language models in curated ontologies.** SMA is
+a retrieval *memory* that grounds a generalist LLM in a **curated,
+expert-maintained ontology**, retrieving by **logical structure** — subsumption
+(is-a) and higher-order relations — that vector RAG and knowledge graphs discard. Holding the language model and prompt fixed and swapping
+only the memory, the SMA-grounded agent becomes **more accurate, more selective,
+and more structurally attributable** than vector RAG: it cites its evidence
+structurally, abstains when nothing grounds the case, and flags novelty —
+capabilities flat retrievers structurally lack. On the real-domain benchmarks the
+measured advantage is carried by bounded is-a subsumption plus information-content
+weighting (the higher-order relational machinery is decisive only on a synthetic
+structure-only control), and it vanishes where no discriminative ontology applies.
+
+![SMA process tour](docs/assets/sma_tour.gif)
+
+> A structure-mapping memory over a curated ontology grounds a generalist LLM by
+> the subsumption hierarchy and rarity weighting that flat retrievers wash out —
+> and the structural alignment itself is what survives when there is no surface
+> signal at all.
+
+---
+
+## What it does
+
+| Capability | SMA | Vector RAG | Knowledge graph |
+|---|:--:|:--:|:--:|
+| Rare / long-tail retrieval (rarity-weighted) | ✅ | ✗ averages rarity away | ✗ |
+| Cross-vocabulary / zero-lexical-overlap match | ✅ | ✗ | partial |
+| Subsumption (is-a) reasoning | ✅ | ✗ | ✗ no ascension |
+| Structural citation (checkable provenance) | ✅ | ✗ | partial |
+| Calibrated abstention | ✅ | ✗ cosine always "high" | ✗ |
+| Novelty / expectation-violation flag | ✅ | ✗ | partial |
+
+One **universal loader** ingests any open OBO/OWL/STIX/CPC ontology (is-a hierarchy
+plus typed relations, no OWL reasoning); a **registry + domain router** select
+across domains. We mount eleven ontologies spanning seven knowledge areas
+(≈594,000 concepts) behind one shared retrieval core plus thin per-domain data
+adapters.
+
+![SMA system overview](docs/assets/fig1_overview.png)
+
+## Headline results (honest)
+
+On a **memory-swap benchmark** where only the retriever varies, SMA beats a strong
+RAG + KG baseline suite on the rare/long-tail slice across five domains:
+
+| Domain | SMA tail top-5 | best RAG | Δ | Holm-significant |
+|---|:--:|:--:|:--:|:--:|
+| Medicine (HPO/MONDO) | 0.949 | 0.606 | **+0.333** | yes |
+| Finance (US-GAAP) | 0.418 | 0.231 | **+0.167** | yes |
+| Genomics (GO) | 0.849 | 0.682 | **+0.156** | yes |
+| Legal (CPC, all-query) | 0.941 | 0.870 | **+0.064** | yes |
+| Cyber (ATT&CK) | 0.766 | 0.749 | +0.073 | directional* |
+
+\* Cyber survives Holm across domains but not a conservative
+Bonferroni-over-baselines selection correction (p=0.035 → 0.17); reported as
+directional. End to end (medicine, LLM-in-the-loop), the SMA-grounded agent is the
+most accurate (0.342 vs dense 0.100 vs closed-book 0.017), most faithful in
+citation, and uniquely separates known from unknown entities (grounding AUROC 0.79
+vs vector RAG's near-chance 0.55).
+
+**Where it does not help (reported, not hidden):** SMA *ties* a bespoke ontology
+information-content oracle (Phenomizer) rather than beating it; and on
+**flat single-record tabular prediction** (hospital readmission, credit-card
+fraud, the Elliptic Bitcoin graph-fraud probe) there is no discriminative
+subsumption ontology to mount, so SMA reaches only parity and a flat
+logistic-regression baseline wins. The advantage is specific to structure.
+
+## How it works
+
+![SMA architecture](docs/assets/architecture.png)
+
+1. **Adapter** — a universal loader parses any open ontology into a normalized
+   graph, **mounts** the is-a hierarchy as an *ascension lattice* (specific terms
+   match general ones with penalty ρ^dist) and the typed relations as higher-order
+   cases, and registers them behind a per-query domain router.
+2. **Matcher** — a case (functors over a subject) is screened by a certified
+   **MAC** admissible-content bound, aligned by best-first structure-mapping
+   (**FAC/SME**), and scored by a rarity-weighted **information-content** (−log₂ p)
+   surprisal scorer.
+3. **Decision** — the alignment yields a **structural citation**, a **calibrated
+   abstention**, or a **novelty flag** (SAGE expectation violation).
+
+## Quick start
+
+```bash
+python -m venv .venv && . .venv/bin/activate
+pip install -e ".[encoders,eval]"
+pytest -m "gate_G0 or gate_G1 or gate_G2 or gate_G3 or gate_G4 or gate_G5 or gate_G6"
+sma ui                       # FastAPI + Gradio demo
+```
+
+Raw datasets are not tracked. Fetch checksum-verified external data with:
+
+```bash
+python scripts/fetch_datasets.py --manifest data/manifests/datasets.json
+```
+
+Reproduce the confirmatory tables/figures from committed CSVs:
+
+```bash
+python scripts/figures_paper.py      # main-text figures
+python scripts/figures_ed.py         # Extended Data figures
+```
+
+All result numbers in the paper trace to `reports/confirmatory/*.csv`; runs are
+deterministic (`PYTHONHASHSEED=0`, paired bootstrap seeded at 12345).
+
+## Repository layout
+
+| Path | Contents |
+|---|---|
+| `sma/ontology/` | universal ontology adapter (loaders, mount, registry, router) — **frozen `adapter-v1`** |
+| `sma/eval/agentic/` | memory-swap retrieval harness + baseline arms |
+| `sma/eval/agentic_qa/` | end-to-end LLM-QA agent (pre-registration v2) |
+| `scripts/` | dataset fetch, figure/table generators, ablations |
+| `reports/confirmatory/` | all result CSVs (every paper number sources here) |
+| `paper/manuscript/` | `sma_nature_mi.tex` — the manuscript (Nature `sn-jnl` template) |
+| `release/` | model card, dataset card, HuggingFace Space |
+
+## Paper & citation
+
+The manuscript (`paper/manuscript/sma_nature_mi.tex`, intended for *Nature Machine
+Intelligence*) is built on the official Springer Nature `sn-jnl` template. To cite
+this software, see [`CITATION.cff`](CITATION.cff).
+
+## License
+
+Apache-2.0. All mounted ontologies are openly licensed and version-pinned; we
+redistribute only derived gold labels, never restricted source records (see
+Extended Data and `release/model_card.md`).

structuremappingmemory-1.0.0/pyproject.toml

@@ -0,0 +1,91 @@
+[build-system]
+requires = ["setuptools>=69", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+# PyPI distribution name (the import name stays `sma`); `sma` is taken on PyPI.
+name = "structuremappingmemory"
+version = "1.0.0"
+description = "SMA-1: Structure-Mapping Agentic Memory — a structure-mapping retrieval memory that grounds language models in curated ontologies"
+readme = "README.md"
+requires-python = ">=3.10"
+license = {text = "Apache-2.0"}
+authors = [{name = "Ayaz Khan", email = "aak2259@columbia.edu"}]
+keywords = ["structure-mapping", "analogical-retrieval", "ontology", "retrieval-augmented-generation", "abstention", "novelty-detection", "trustworthy-ai", "knowledge-graph"]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+  "blake3>=0.4",
+  "fastapi>=0.110",
+  "gradio>=4.44",
+  "hnswlib>=0.8",
+  "lmdb>=1.4",
+  "numpy>=1.26",
+  "ortools>=9.10",
+  "pydantic>=2",
+  "pytest>=8",
+  "hypothesis>=6",
+  "rank-bm25>=0.2.2",
+  "regex>=2024.5.15",
+  "scikit-learn>=1.5",
+  "typer>=0.12",
+  "zstandard>=0.22"
+]
+
+[project.optional-dependencies]
+encoders = [
+  "drain3>=0.9.11",
+  "tree-sitter>=0.23",
+  "tree-sitter-language-pack>=0.7",
+  "nltk>=3.9",
+  "stanza>=1.8"
+]
+eval = [
+  "langchain>=0.2",
+  "langchain-community>=0.2",
+  "rank-bm25>=0.2.2",
+  "ranx>=0.3.20",
+  "sentence-transformers>=3",
+  "statsmodels>=0.14",
+  "kuzu>=0.6",
+  "networkx>=3"
+]
+local-llm = [
+  "huggingface-hub>=0.23",
+  "llama-cpp-python>=0.2.90"
+]
+
+[project.urls]
+Homepage = "https://github.com/ayazkhan27/SMA-1"
+Repository = "https://github.com/ayazkhan27/SMA-1"
+Issues = "https://github.com/ayazkhan27/SMA-1/issues"
+
+[project.scripts]
+sma = "sma.cli:main"
+
+[tool.setuptools.packages.find]
+include = ["sma*"]
+
+[tool.pytest.ini_options]
+addopts = "-q"
+testpaths = ["tests"]
+markers = [
+  "gate_G0: bootstrap and artifact checks",
+  "gate_G1: IR and store checks",
+  "gate_G2: matcher checks",
+  "gate_G3: encoder checks",
+  "gate_G4: retrieval checks",
+  "gate_G5: API and provenance policy checks",
+  "gate_G6: SAGE checks",
+  "slow: long-running checks"
+]
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"

structuremappingmemory-1.0.0/setup.cfg

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

structuremappingmemory-1.0.0/sma/__init__.py

@@ -0,0 +1,5 @@
+"""SMA-1: Structure-Mapping Agentic Memory MVP."""
+
+__all__ = ["__version__"]
+__version__ = "0.1.0"
+

structuremappingmemory-1.0.0/sma/__main__.py

@@ -0,0 +1,5 @@
+from .cli import main
+
+if __name__ == "__main__":
+    main()
+

structuremappingmemory-1.0.0/sma/agent/__init__.py

@@ -0,0 +1,5 @@
+from .policies import reject_free_text_facts, require_provenance
+from .service import MemoryService
+
+__all__ = ["MemoryService", "reject_free_text_facts", "require_provenance"]
+