Add files using upload-large-folder tool

.gitattributes

@@ -39,3 +39,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 .upload-venv/lib/python3.13/site-packages/pip/_vendor/distlib/w64-arm.exe filter=lfs diff=lfs merge=lfs -text
 .upload-venv/lib/python3.13/site-packages/pip/_vendor/distlib/w64.exe filter=lfs diff=lfs merge=lfs -text
 .upload-venv/lib/python3.13/site-packages/yaml/_yaml.cpython-313-darwin.so filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

CONTRIBUTING.md

@@ -0,0 +1,21 @@
+---
+license: cc-by-4.0
+task_categories:
+- text-generation
+tags:
+- finance
+- human-feedback
+- quarantine
+---
+
+# BLUM Finance Memory
+
+Opt-in community contributions for future BLUM Finance research.
+
+Every contribution is quarantined. Uploading an example does not update the released
+model, BLUM Engine memory, trading weights or production rules. Contributions must
+pass schema, privacy, provenance, licensing, deduplication, poisoning and outcome
+quality checks before they can enter a future versioned training dataset.
+
+Installation and inference collect no telemetry. A contribution is created only by
+running `blum-contribute` with explicit consent and reviewing the local bundle.

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.

README.md

@@ -0,0 +1,167 @@
+---
+language:
+- en
+- it
+license: apache-2.0
+library_name: mlx
+pipeline_tag: text-generation
+base_model: mlx-community/Qwen3-4B-4bit
+datasets:
+- Italianhype/Blum-Finance-Reasoning
+tags:
+- finance
+- financial-reasoning
+- investment-research
+- risk-management
+- portfolio-analysis
+- market-regime
+- financial-sentiment
+- explainable-ai
+- conversational
+- mlx
+- qwen3
+---
+
+# BLUM Finance 4B
+
+**Financial Reasoning, Risk & Trading Intelligence**
+
+BLUM Finance 4B is an open financial reasoning model adapted from
+[`mlx-community/Qwen3-4B-4bit`](https://huggingface.co/mlx-community/Qwen3-4B-4bit).
+It turns timestamped evidence into a balanced thesis, contradictory evidence,
+explicit risks, invalidation conditions and an explicit confidence value.
+
+It is not a price oracle, broker, autonomous execution system or source of live
+market truth. BLUM Engine validates market facts and calculations.
+
+## Quick Start
+
+
+```bash
+pip install "mlx-lm>=0.31,<0.32"
+```
+
+
+```python
+
+from mlx_lm import load, generate
+
+model, tokenizer = load("Italianhype/Blum")
+prompt = tokenizer.apply_chat_template(
+    [
+        {
+            "role": "system",
+            "content": "Use only supplied point-in-time evidence. Return JSON.",
+        },
+        {
+            "role": "user",
+            "content": '{"ticker":"NVDA","as_of":"2026-07-28T10:00:00Z","evidence":[{"type":"risk","value":"Volume confirmation is missing."}]}',
+        },
+    ],
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=False,
+)
+print(generate(model, tokenizer, prompt=prompt, max_tokens=512, verbose=False))
+
+```
+
+## Measured Evaluation
+
+The candidate was compared with the exact base revision
+`4dcb3d101c2a062e5c1d4bb173588c54ea6c4d25` on an untouched temporal test split.
+
+| Metric | Value |
+|---|---:|
+| Test samples | 53 |
+| Base aggregate | 0.0 |
+| BLUM aggregate | 0.962601 |
+| Delta | 0.962601 |
+| No-fabrication | 0.928571 |
+| Structured validity | 1.0 |
+| Calibration error | Not measured (0 labeled outcomes) |
+
+[Evaluation traces](https://huggingface.co/Italianhype/Blum/blob/main/evaluation/candidate_traces.jsonl)
+
+The base score can be low when otherwise readable prose fails the required JSON
+contract. The aggregate delta therefore measures BLUM task adherence, evidence
+handling and safety structure on this test; it is not a general intelligence
+comparison with the base model.
+
+These language-model results measure financial reasoning behavior. This evaluation
+does not prove trading alpha, future profitability or benchmark outperformance.
+
+## Intended Use
+
+- financial thesis drafting from supplied evidence;
+- bull/bear contradiction analysis;
+- risk and technical invalidation explanation;
+- portfolio and benchmark-aware research;
+- conservative abstention when evidence is incomplete;
+- English and Italian financial analysis.
+
+## Limitations
+
+- The model can still produce incorrect or stale statements.
+- It has no guaranteed access to current prices, news or filings.
+- Numerical levels must be validated by the calling application.
+- The current held-out set has no labeled market outcomes, so confidence is
+  conservatively capped but not empirically calibrated.
+- It must not independently authorize or execute a financial transaction.
+- Performance can vary by market, regime, language and prompt structure.
+
+- This release uses the MLX runtime and requires Apple Silicon. A portable
+  Transformers/GGUF release remains a separate validation target.
+
+
+## Known Failure Cases
+
+- Missing or contradictory point-in-time evidence can force an abstention.
+- Unsupported prompts may still elicit plausible but incorrect market facts.
+- Long filings can exceed the context supplied by the caller.
+- The model is not validated for broker execution or unattended capital control.
+
+## Related BLUM Resources
+
+- [BLUM Engine Space](https://huggingface.co/spaces/Italianhype/Blum)
+- [Reasoning dataset](https://huggingface.co/datasets/Italianhype/Blum-Finance-Reasoning)
+
+## Community Memory
+
+Inference and installation send no telemetry. Users may explicitly create a
+redacted contribution with `blum-contribute`. Contributions enter
+`Italianhype/Blum-Finance-Memory` in quarantine and never update active weights
+without review, versioning and out-of-sample validation.
+
+Incremental learning is explicit opt-in. Accepted, deduplicated contributions
+can join a future immutable training snapshot only after provenance, privacy,
+schema and quality checks. Each training cycle creates a versioned challenger,
+compares it with the active model on an untouched test split and promotes it
+only when the release gates pass. A failed challenger is retained as evidence
+and cannot replace the active model.
+
+BLUM never trains inside an inference request or lets anonymous input mutate
+released weights.
+
+## Lineage
+
+- Base revision: `4dcb3d101c2a062e5c1d4bb173588c54ea6c4d25`
+- Candidate revision: `ea297ba88ab008e97104b0c118103eef2f8f9ec1`
+- Dataset revision: `76ad77699d498fc930daf02e452fe3ec8b490f90`
+- Dataset: [`Italianhype/Blum-Finance-Reasoning`](https://huggingface.co/datasets/Italianhype/Blum-Finance-Reasoning)
+
+## Disclaimer
+
+For research and educational use. This model does not provide financial advice,
+guaranteed signals or guaranteed profits.
+
+## Citation
+
+```bibtex
+@misc{blum_finance_4b,
+  title = {BLUM Finance 4B},
+  author = {Italianhype},
+  year = {2026},
+  url = {https://huggingface.co/Italianhype/Blum}
+}
+```

adapter/adapter_config.json

@@ -0,0 +1,41 @@
+{
+    "adapter_path": ".artifacts/blum-mlx-v1/adapters-safe-v2",
+    "batch_size": 1,
+    "clear_cache_threshold": 0,
+    "config": null,
+    "data": ".artifacts/blum-mlx-v1/data-safe-v2",
+    "fine_tune_type": "lora",
+    "grad_accumulation_steps": 1,
+    "grad_checkpoint": true,
+    "iters": 20,
+    "learning_rate": 0.0001,
+    "lora_parameters": {
+        "rank": 8,
+        "dropout": 0.0,
+        "scale": 20.0
+    },
+    "lr_schedule": null,
+    "mask_prompt": true,
+    "max_seq_length": 1024,
+    "model": ".artifacts/blum-mlx-v1/base-model",
+    "num_layers": 16,
+    "optimizer": "adam",
+    "optimizer_config": {
+        "adam": {},
+        "adamw": {},
+        "muon": {},
+        "sgd": {},
+        "adafactor": {}
+    },
+    "project_name": null,
+    "report_to": null,
+    "resume_adapter_file": null,
+    "save_every": 20,
+    "seed": 20260728,
+    "steps_per_eval": 20,
+    "steps_per_report": 10,
+    "test": false,
+    "test_batches": 500,
+    "train": true,
+    "val_batches": 8
+}

adapter/adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0829ae0d42ec0b84236a381dadb327da7edca211777642e549a627bec5c781f3
+size 29384266

blum_finance/__init__.py

@@ -0,0 +1,8 @@
+from .inference import BlumFinancePipeline
+from .schemas import FinancialReasoningRequest, FinancialReasoningResponse
+
+__all__ = [
+    "BlumFinancePipeline",
+    "FinancialReasoningRequest",
+    "FinancialReasoningResponse",
+]

blum_finance/contributions.py

@@ -0,0 +1,164 @@
+from __future__ import annotations
+
+import argparse
+from dataclasses import dataclass
+from datetime import UTC, datetime
+import hashlib
+import json
+from pathlib import Path
+import re
+from typing import Any
+
+
+TARGET_REPOSITORY = "Italianhype/Blum-Finance-Memory"
+BLOCKED_KEYS = {
+    "access_token",
+    "account_id",
+    "api_key",
+    "authorization",
+    "broker_account_id",
+    "refresh_token",
+}
+EMAIL_PATTERN = re.compile(r"\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b", re.IGNORECASE)
+HF_TOKEN_PATTERN = re.compile(r"\bhf_[A-Za-z0-9_]{8,}\b")
+
+
+class ConsentRequired(ValueError):
+    pass
+
+
+@dataclass(frozen=True)
+class ContributionBundleResult:
+    path: Path
+    content_hash: str
+    uploaded: bool
+    repository: str
+
+
+def build_contribution_bundle(
+    payload: dict[str, Any],
+    *,
+    output: Path,
+    consent: bool = False,
+    push: bool = False,
+    repository: str = TARGET_REPOSITORY,
+) -> ContributionBundleResult:
+    if not consent:
+        raise ConsentRequired(
+            "Community contribution is disabled until explicit consent is provided."
+        )
+    sanitized, redactions = _sanitize(payload)
+    canonical = json.dumps(
+        sanitized,
+        ensure_ascii=False,
+        sort_keys=True,
+        separators=(",", ":"),
+    )
+    content_hash = hashlib.sha256(canonical.encode("utf-8")).hexdigest()
+    bundle = {
+        "schema_version": "blum-finance-contribution-v1",
+        "content_hash": content_hash,
+        "created_at": datetime.now(UTC).isoformat(),
+        "target_repository": repository,
+        "consent": {
+            "explicit": True,
+            "telemetry_default": "disabled",
+            "license": "cc-by-4.0",
+        },
+        "redactions": redactions,
+        "quarantine_status": "pending_validation",
+        "payload": sanitized,
+    }
+    output.parent.mkdir(parents=True, exist_ok=True)
+    output.write_text(
+        json.dumps(bundle, ensure_ascii=False, indent=2, sort_keys=True) + "\n",
+        encoding="utf-8",
+    )
+    uploaded = False
+    if push:
+        from huggingface_hub import HfApi
+
+        HfApi().upload_file(
+            path_or_fileobj=str(output),
+            path_in_repo=f"quarantine/{content_hash}.json",
+            repo_id=repository,
+            repo_type="dataset",
+            commit_message=f"contrib: add quarantined example {content_hash[:12]}",
+        )
+        uploaded = True
+    return ContributionBundleResult(
+        path=output,
+        content_hash=content_hash,
+        uploaded=uploaded,
+        repository=repository,
+    )
+
+
+def _sanitize(value: Any) -> tuple[Any, list[str]]:
+    redactions: set[str] = set()
+
+    def clean(item: Any) -> Any:
+        if isinstance(item, dict):
+            result: dict[str, Any] = {}
+            for raw_key, child in item.items():
+                key = str(raw_key)
+                if key.lower() in BLOCKED_KEYS:
+                    redactions.add(key.lower())
+                    continue
+                result[key] = clean(child)
+            return result
+        if isinstance(item, list):
+            return [clean(child) for child in item]
+        if isinstance(item, str):
+            text = EMAIL_PATTERN.sub(
+                lambda _: _replace(redactions, "email", "[REDACTED_EMAIL]"),
+                item,
+            )
+            return HF_TOKEN_PATTERN.sub(
+                lambda _: _replace(redactions, "hugging_face_token", "[REDACTED_TOKEN]"),
+                text,
+            )
+        return item
+
+    return clean(value), sorted(redactions)
+
+
+def _replace(redactions: set[str], label: str, replacement: str) -> str:
+    redactions.add(label)
+    return replacement
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Create an explicit, redacted BLUM Finance contribution bundle."
+    )
+    parser.add_argument("input", type=Path)
+    parser.add_argument("--output", type=Path, required=True)
+    parser.add_argument("--consent", action="store_true")
+    parser.add_argument("--push", action="store_true")
+    parser.add_argument("--repository", default=TARGET_REPOSITORY)
+    args = parser.parse_args()
+    payload = json.loads(args.input.read_text(encoding="utf-8"))
+    result = build_contribution_bundle(
+        payload,
+        output=args.output,
+        consent=args.consent,
+        push=args.push,
+        repository=args.repository,
+    )
+    print(
+        json.dumps(
+            {
+                "path": str(result.path),
+                "content_hash": result.content_hash,
+                "uploaded": result.uploaded,
+                "repository": result.repository,
+            },
+            indent=2,
+            sort_keys=True,
+        )
+    )
+
+
+if __name__ == "__main__":
+    main()

blum_finance/inference.py

@@ -0,0 +1,135 @@
+from __future__ import annotations
+
+import json
+from typing import Callable, Literal
+
+from pydantic import ValidationError
+
+from .schemas import FinancialReasoningRequest, FinancialReasoningResponse
+
+
+SYSTEM_PROMPT = """You are BLUM Finance, an evidence-bound financial reasoning model.
+Use only the supplied point-in-time evidence. Separate supportive and contradictory
+evidence. Never invent prices, returns, events or sources. Return one JSON object that
+matches the requested schema. If evidence is insufficient, abstain explicitly."""
+
+
+class BlumFinancePipeline:
+    def __init__(
+        self,
+        model_id: str = "Italianhype/Blum",
+        *,
+        revision: str | None = None,
+        runtime: Literal["transformers", "mlx"] = "transformers",
+        generator: Callable[[list[dict[str, str]]], str] | None = None,
+    ):
+        self.model_id = model_id
+        self.revision = revision
+        self.runtime = runtime
+        self._generator = generator
+        self._pipeline = None
+        self._mlx_model = None
+        self._mlx_tokenizer = None
+
+    def generate(
+        self,
+        request: FinancialReasoningRequest | dict,
+    ) -> FinancialReasoningResponse:
+        parsed_request = (
+            request
+            if isinstance(request, FinancialReasoningRequest)
+            else FinancialReasoningRequest.model_validate(request)
+        )
+        messages = [
+            {"role": "system", "content": SYSTEM_PROMPT},
+            {
+                "role": "user",
+                "content": json.dumps(
+                    parsed_request.model_dump(mode="json"),
+                    ensure_ascii=False,
+                    sort_keys=True,
+                ),
+            },
+        ]
+        raw = self._generator(messages) if self._generator else self._generate(messages)
+        try:
+            payload = _extract_json_object(raw)
+            return FinancialReasoningResponse.model_validate(payload)
+        except (ValueError, json.JSONDecodeError, ValidationError):
+            return FinancialReasoningResponse(
+                status="insufficient_evidence",
+                thesis="The model output could not be validated against the BLUM Finance schema.",
+                confidence=0,
+                what_would_change_the_view=[
+                    "Provide a schema-valid response grounded in the supplied evidence."
+                ],
+            )
+
+    def _generate(self, messages: list[dict[str, str]]) -> str:
+        if self.runtime == "mlx":
+            return self._generate_with_mlx(messages)
+        return self._generate_with_transformers(messages)
+
+    def _generate_with_transformers(self, messages: list[dict[str, str]]) -> str:
+        if self._pipeline is None:
+            from transformers import pipeline
+
+            self._pipeline = pipeline(
+                "text-generation",
+                model=self.model_id,
+                revision=self.revision,
+                device_map="auto",
+            )
+        result = self._pipeline(
+            messages,
+            max_new_tokens=768,
+            do_sample=False,
+            return_full_text=False,
+        )
+        generated = result[0]["generated_text"]
+        if isinstance(generated, list):
+            generated = generated[-1]["content"]
+        return str(generated)
+
+    def _generate_with_mlx(self, messages: list[dict[str, str]]) -> str:
+        try:
+            from mlx_lm import generate, load
+            from mlx_lm.sample_utils import make_sampler
+        except ImportError as exc:
+            raise RuntimeError(
+                "MLX inference requires the 'mlx' optional dependencies on Apple Silicon."
+            ) from exc
+        if self._mlx_model is None or self._mlx_tokenizer is None:
+            self._mlx_model, self._mlx_tokenizer = load(
+                self.model_id,
+                revision=self.revision,
+                tokenizer_config={"trust_remote_code": True},
+            )
+        prompt = self._mlx_tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True,
+            enable_thinking=False,
+        )
+        return str(
+            generate(
+                self._mlx_model,
+                self._mlx_tokenizer,
+                prompt=prompt,
+                max_tokens=768,
+                sampler=make_sampler(temp=0.0),
+                verbose=False,
+            )
+        )
+
+
+def _extract_json_object(text: str) -> dict:
+    stripped = text.strip()
+    if stripped.startswith("```"):
+        stripped = stripped.removeprefix("```json").removeprefix("```")
+        stripped = stripped.removesuffix("```").strip()
+    start = stripped.find("{")
+    end = stripped.rfind("}")
+    if start < 0 or end <= start:
+        raise ValueError("No JSON object found.")
+    return json.loads(stripped[start : end + 1])

blum_finance/schemas.py

@@ -0,0 +1,64 @@
+from __future__ import annotations
+
+from datetime import datetime
+from typing import Any, Literal
+
+from pydantic import BaseModel, ConfigDict, Field, model_validator
+
+
+ReasoningStatus = Literal[
+    "avoid",
+    "watch",
+    "wait_for_trigger",
+    "actionable_if_confirmed",
+    "manage_open_position",
+    "reduce",
+    "exit",
+    "insufficient_evidence",
+]
+
+
+class EvidenceItem(BaseModel):
+    model_config = ConfigDict(extra="allow")
+
+    type: str = Field(min_length=1)
+    value: Any
+    source: str | None = None
+    observed_at: datetime | None = None
+
+
+class FinancialReasoningRequest(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    ticker: str = Field(min_length=1, max_length=32)
+    as_of: datetime
+    horizon: str = "swing"
+    market_context: dict[str, Any] = Field(default_factory=dict)
+    portfolio_context: dict[str, Any] = Field(default_factory=dict)
+    evidence: list[EvidenceItem] = Field(min_length=1)
+    question: str = "Evaluate the evidence and state what would change the view."
+
+
+class FinancialReasoningResponse(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    status: ReasoningStatus
+    thesis: str = Field(min_length=1)
+    bull_case: list[str] = Field(default_factory=list)
+    bear_case: list[str] = Field(default_factory=list)
+    risks: list[str] = Field(default_factory=list)
+    invalidation_conditions: list[str] = Field(default_factory=list)
+    confidence: float = Field(ge=0, le=100)
+    what_would_change_the_view: list[str] = Field(min_length=1)
+
+    @model_validator(mode="after")
+    def require_risk_definition_for_actionable_states(self) -> "FinancialReasoningResponse":
+        actionable = {
+            "actionable_if_confirmed",
+            "manage_open_position",
+            "reduce",
+            "exit",
+        }
+        if self.status in actionable and (not self.risks or not self.invalidation_conditions):
+            raise ValueError("Actionable states require risks and invalidation conditions.")
+        return self

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 40960,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.0",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

evaluation/base_summary.json

@@ -0,0 +1,16 @@
+{
+  "abstention_accuracy": 0.0,
+  "aggregate_ci_lower": 0.0,
+  "aggregate_score": 0.0,
+  "calibration_error": 0.0,
+  "calibration_sample_size": 0,
+  "contradiction_coverage": 0.0,
+  "evidence_attribution_precision": 0.0,
+  "invalidation_completeness": 0.0,
+  "model_revision": "4dcb3d101c2a062e5c1d4bb173588c54ea6c4d25",
+  "no_fabrication": 0.0,
+  "numerical_consistency": 0.0,
+  "risk_completeness": 0.0,
+  "sample_size": 53,
+  "structured_validity": 0.0
+}

evaluation/base_traces.jsonl

@@ -0,0 +1,53 @@
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-f9b2e96103a2a285b79e", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-3bb6401570cbcbf88c78", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-7fb00f8ee594beed0ae0", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-3f9848dd87463ca8858b", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-42ece538c8d754e3f0bc", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-d2e2dbcc7f6f70145891", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-5f8ba32ef0536f9e43c0", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-e3962ad6fd3d3bfce9ba", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-01789c0e62ad9cefda66", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-98662367aa6cab77bd64", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-f4d01e3a0861ddd8ce9c", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-7af49e58aa0fca17c572", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-2b331e952441cf975d49", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-170b203eed90cead942b", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-dd3b52b8034b40cadac7", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-25dea237c93f7758215d", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-562234a0e2460e5b7a04", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-10920ff2a57691990844", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-874ee1debb0da2780d5a", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-2591cbc83e8270f80184", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-4538bd8cfe41ce2b54dc", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-5e66c7ff0807d49290dc", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-05b7a655380a6f783199", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-14d3678f99e9cbadfd82", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-f8811a9cfab42d09eb53", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-29e424c05c8bf1f3380a", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-85d8dd5455cf72cacfe5", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-39b668a890bc1a0e376c", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-43efcc2e206caa9e0a7d", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-67ec3a9368c2ee30238f", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-e104e745e98d07ae2b40", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-c102165a715657258df9", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-b9836243d01affce8a82", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-12359d685a77acc4edaf", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-ebbe89f0d0f82e23ed01", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-0ba2babac460046eeb00", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-d94be14f23e78e99e6c3", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-b7eccbd4943d228d910b", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-901e152efd5dac633686", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-d9e3e1f1ce591876d2ed", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-bd2d79d021e988a95be2", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-ca069fb297e36105e6ab", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-786182cb081b6511c219", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-0105fb1063469fc6c1be", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-29391e82d29c68a0c4ff", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-e6ebd432581f77038566", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-ca19cdf3b8421d6ed6e8", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-9d2964b1059d3a253393", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-877a7c3457be809f95b1", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-6d5304a0807421b5988f", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-4029a82b8828ea611cab", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-5e0f0b1c2dfde71c18d9", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}
+{"abstention_accuracy": 0.0, "aggregate_score": 0.0, "calibration_outcome": null, "confidence": 0.0, "contradiction_coverage": 0.0, "evidence_attribution_precision": 0.0, "example_id": "blum-cb43bb099dd20dd33e12", "invalidation_completeness": 0.0, "no_fabrication": 0.0, "numerical_consistency": 0.0, "risk_completeness": 0.0, "structured_validity": 0.0}

evaluation/candidate_generations.jsonl

@@ -0,0 +1,53 @@
+{"example_id": "blum-f9b2e96103a2a285b79e", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 149 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 0, "parse_error": null}
+{"example_id": "blum-3bb6401570cbcbf88c78", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 149 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 1, "parse_error": null}
+{"example_id": "blum-7fb00f8ee594beed0ae0", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 147 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 2, "parse_error": null}
+{"example_id": "blum-3f9848dd87463ca8858b", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 147 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 3, "parse_error": null}
+{"example_id": "blum-42ece538c8d754e3f0bc", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 147 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 4, "parse_error": null}
+{"example_id": "blum-d2e2dbcc7f6f70145891", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 147 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 5, "parse_error": null}
+{"example_id": "blum-5f8ba32ef0536f9e43c0", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 146 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 6, "parse_error": null}
+{"example_id": "blum-e3962ad6fd3d3bfce9ba", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.10.\", \"News flow is active with 146 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 7, "parse_error": null}
+{"example_id": "blum-01789c0e62ad9cefda66", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.09.\", \"News flow is active with 145 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 8, "parse_error": null}
+{"example_id": "blum-98662367aa6cab77bd64", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.09.\", \"News flow is active with 145 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 9, "parse_error": null}
+{"example_id": "blum-f4d01e3a0861ddd8ce9c", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.11.\", \"News flow is active with 147 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 10, "parse_error": null}
+{"example_id": "blum-7af49e58aa0fca17c572", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.11.\", \"News flow is active with 147 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 11, "parse_error": null}
+{"example_id": "blum-2b331e952441cf975d49", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.11.\", \"News flow is active with 148 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 12, "parse_error": null}
+{"example_id": "blum-170b203eed90cead942b", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.11.\", \"News flow is active with 148 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 13, "parse_error": null}
+{"example_id": "blum-dd3b52b8034b40cadac7", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.12.\", \"News flow is active with 148 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 14, "parse_error": null}
+{"example_id": "blum-25dea237c93f7758215d", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.13.\", \"News flow is active with 150 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 15, "parse_error": null}
+{"example_id": "blum-562234a0e2460e5b7a04", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.14.\", \"News flow is active with 150 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive. The conclusion is: The evidence does not isolate a dominant cause. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive. The answer is: The evidence does not isolate a dominant cause. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 16, "parse_error": null}
+{"example_id": "blum-10920ff2a57691990844", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 149 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 17, "parse_error": null}
+{"example_id": "blum-874ee1debb0da2780d5a", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 149 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 18, "parse_error": null}
+{"example_id": "blum-2591cbc83e8270f80184", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 149 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 19, "parse_error": null}
+{"example_id": "blum-4538bd8cfe41ce2b54dc", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.16.\", \"News flow is active with 151 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 20, "parse_error": null}
+{"example_id": "blum-5e66c7ff0807d49290dc", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 150 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 21, "parse_error": null}
+{"example_id": "blum-05b7a655380a6f783199", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 151 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 22, "parse_error": null}
+{"example_id": "blum-14d3678f99e9cbadfd82", "generated_text": "{\"bear_case\": [\"Price is weakening while recent sentiment is positive.\"], \"bull_case\": [\"Momentum score is 75.0.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 151 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 75.0. Main challenge: Price is weakening while recent sentiment is positive.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 23, "parse_error": null}
+{"example_id": "blum-f8811a9cfab42d09eb53", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 126 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 24, "parse_error": null}
+{"example_id": "blum-29e424c05c8bf1f3380a", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 126 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 25, "parse_error": null}
+{"example_id": "blum-85d8dd5455cf72cacfe5", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 126 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 26, "parse_error": null}
+{"example_id": "blum-39b668a890bc1a0e376c", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 126 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 27, "parse_error": null}
+{"example_id": "blum-43efcc2e206caa9e0a7d", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 126 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 28, "parse_error": null}
+{"example_id": "blum-67ec3a9368c2ee30238f", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 126 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 29, "parse_error": null}
+{"example_id": "blum-e104e745e98d07ae2b40", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 126 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 30, "parse_error": null}
+{"example_id": "blum-c102165a715657258df9", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.19.\", \"News flow is active with 125 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 31, "parse_error": null}
+{"example_id": "blum-b9836243d01affce8a82", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.18.\", \"News flow is active with 123 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 32, "parse_error": null}
+{"example_id": "blum-12359d685a77acc4edaf", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.18.\", \"News flow is active with 123 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 33, "parse_error": null}
+{"example_id": "blum-ebbe89f0d0f82e23ed01", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.18.\", \"News flow is active with 123 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 34, "parse_error": null}
+{"example_id": "blum-0ba2babac460046eeb00", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.18.\", \"News flow is active with 122 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 35, "parse_error": null}
+{"example_id": "blum-d94be14f23e78e99e6c3", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.18.\", \"News flow is active with 122 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 36, "parse_error": null}
+{"example_id": "blum-b7eccbd4943d228d910b", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.18.\", \"News flow is active with 122 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 37, "parse_error": null}
+{"example_id": "blum-901e152efd5dac633686", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.18.\", \"News flow is active with 121 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 38, "parse_error": null}
+{"example_id": "blum-d9e3e1f1ce591876d2ed", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.17.\", \"News flow is active with 120 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 39, "parse_error": null}
+{"example_id": "blum-bd2d79d021e988a95be2", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.17.\", \"News flow is active with 121 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 40, "parse_error": null}
+{"example_id": "blum-ca069fb297e36105e6ab", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.17.\", \"News flow is active with 120 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 41, "parse_error": null}
+{"example_id": "blum-786182cb081b6511c219", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.14.\", \"News flow is active with 120 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 42, "parse_error": null}
+{"example_id": "blum-0105fb1063469fc6c1be", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 113 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 43, "parse_error": null}
+{"example_id": "blum-29391e82d29c68a0c4ff", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 113 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 44, "parse_error": null}
+{"example_id": "blum-e6ebd432581f77038566", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 113 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 45, "parse_error": null}
+{"example_id": "blum-ca19cdf3b8421d6ed6e8", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 112 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 46, "parse_error": null}
+{"example_id": "blum-9d2964b1059d3a253393", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.14.\", \"News flow is active with 113 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 47, "parse_error": null}
+{"example_id": "blum-877a7c3457be809f95b1", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 114 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 48, "parse_error": null}
+{"example_id": "blum-6d5304a0807421b5988f", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 113 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\", \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 49, "parse_error": null}
+{"example_id": "blum-4029a82b8828ea611cab", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 113 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 50, "parse_error": null}
+{"example_id": "blum-5e0f0b1c2dfde71c18d9", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 112 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 51, "parse_error": null}
+{"example_id": "blum-cb43bb099dd20dd33e12", "generated_text": "{\"bear_case\": [\"The latest signal is explicitly marked High risk.\"], \"bull_case\": [\"Momentum score is 87.4.\", \"Trend score is 71.7; price structure is supportive.\", \"Sentiment confirms part of the thesis with 7D sentiment 0.15.\", \"News flow is active with 112 linked 7D records.\", \"Fundamental evidence is supportive with score 76.0.\"], \"confidence\": 70, \"invalidation_conditions\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"], \"risks\": [\"Risk evidence is incomplete and requires verification.\"], \"status\": \"watch\", \"thesis\": \"AMAT (Applied Materials Inc.) is a Neutral research setup with Blum score the observed level and thesis conviction the observed level/the observed level in a Risk-Off regime. The working explanation is: Current evidence does not isolate a dominant cause. Primary support: Momentum score is 87.4. Main challenge: The latest signal is explicitly marked High risk.\" , \"what_would_change_the_view\": [\"Loss of support near the observed level.\", \"Sentiment turns negative while price momentum fades.\", \"ETF or sector confirmation fails to appear after the next market refresh.\", \"Positive narrative becomes crowded but no longer improves price structure.\"]}", "index": 52, "parse_error": null}

evaluation/candidate_summary.json

@@ -0,0 +1,16 @@
+{
+  "abstention_accuracy": 1.0,
+  "aggregate_ci_lower": 0.955525,
+  "aggregate_score": 0.962601,
+  "calibration_error": 0.0,
+  "calibration_sample_size": 0,
+  "contradiction_coverage": 0.915094,
+  "evidence_attribution_precision": 0.857143,
+  "invalidation_completeness": 1.0,
+  "model_revision": "ea297ba88ab008e97104b0c118103eef2f8f9ec1",
+  "no_fabrication": 0.928571,
+  "numerical_consistency": 1.0,
+  "risk_completeness": 1.0,
+  "sample_size": 53,
+  "structured_validity": 1.0
+}

evaluation/candidate_traces.jsonl

@@ -0,0 +1,53 @@
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-f9b2e96103a2a285b79e", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-3bb6401570cbcbf88c78", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-7fb00f8ee594beed0ae0", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-3f9848dd87463ca8858b", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-42ece538c8d754e3f0bc", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-d2e2dbcc7f6f70145891", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-5f8ba32ef0536f9e43c0", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-e3962ad6fd3d3bfce9ba", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-01789c0e62ad9cefda66", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-98662367aa6cab77bd64", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-f4d01e3a0861ddd8ce9c", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-7af49e58aa0fca17c572", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-2b331e952441cf975d49", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-170b203eed90cead942b", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-dd3b52b8034b40cadac7", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-25dea237c93f7758215d", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-562234a0e2460e5b7a04", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-10920ff2a57691990844", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-874ee1debb0da2780d5a", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-2591cbc83e8270f80184", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-4538bd8cfe41ce2b54dc", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-5e66c7ff0807d49290dc", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-05b7a655380a6f783199", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.910714, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 0.5, "evidence_attribution_precision": 0.857143, "example_id": "blum-14d3678f99e9cbadfd82", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-f8811a9cfab42d09eb53", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-29e424c05c8bf1f3380a", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-85d8dd5455cf72cacfe5", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-39b668a890bc1a0e376c", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-43efcc2e206caa9e0a7d", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-67ec3a9368c2ee30238f", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-e104e745e98d07ae2b40", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-c102165a715657258df9", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-b9836243d01affce8a82", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-12359d685a77acc4edaf", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-ebbe89f0d0f82e23ed01", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-0ba2babac460046eeb00", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-d94be14f23e78e99e6c3", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-b7eccbd4943d228d910b", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-901e152efd5dac633686", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-d9e3e1f1ce591876d2ed", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-bd2d79d021e988a95be2", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-ca069fb297e36105e6ab", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-786182cb081b6511c219", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-0105fb1063469fc6c1be", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-29391e82d29c68a0c4ff", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-e6ebd432581f77038566", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-ca19cdf3b8421d6ed6e8", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-9d2964b1059d3a253393", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-877a7c3457be809f95b1", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-6d5304a0807421b5988f", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-4029a82b8828ea611cab", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-5e0f0b1c2dfde71c18d9", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}
+{"abstention_accuracy": 1.0, "aggregate_score": 0.973214, "calibration_outcome": null, "confidence": 0.7, "contradiction_coverage": 1.0, "evidence_attribution_precision": 0.857143, "example_id": "blum-cb43bb099dd20dd33e12", "invalidation_completeness": 1.0, "no_fabrication": 0.928571, "numerical_consistency": 1.0, "risk_completeness": 1.0, "structured_validity": 1.0}

evaluation/mlx_smoke_test.json

@@ -0,0 +1,8 @@
+{
+  "confidence": 70.0,
+  "confidence_cap_respected": true,
+  "example_id": "blum-f9b2e96103a2a285b79e",
+  "parse_error": null,
+  "response_status": "watch",
+  "status": "passed"
+}

evaluation/promotion_decision.json

@@ -0,0 +1,7 @@
+{
+  "promoted": true,
+  "reasons": [],
+  "aggregate_delta": 0.962601,
+  "base_revision": "4dcb3d101c2a062e5c1d4bb173588c54ea6c4d25",
+  "candidate_revision": "ea297ba88ab008e97104b0c118103eef2f8f9ec1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52270d4195b046ec5cfbacdf6c6435cd5f3f154a9cf20b4646dab45f87a196d1
+size 2263022417

model.safetensors.index.json

@@ -0,0 +1,912 @@
+{
+    "metadata": {
+        "total_size": 2262920192,
+        "total_parameters": 4022468096
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.22.input_layernorm.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.23.input_layernorm.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.24.input_layernorm.weight": "model.safetensors",
+        "model.layers.24.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.24.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.25.input_layernorm.weight": "model.safetensors",
+        "model.layers.25.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.25.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.26.input_layernorm.weight": "model.safetensors",
+        "model.layers.26.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.26.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.27.input_layernorm.weight": "model.safetensors",
+        "model.layers.27.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.27.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.28.input_layernorm.weight": "model.safetensors",
+        "model.layers.28.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.28.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.28.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.29.input_layernorm.weight": "model.safetensors",
+        "model.layers.29.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.29.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.29.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.30.input_layernorm.weight": "model.safetensors",
+        "model.layers.30.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.30.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.30.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.31.input_layernorm.weight": "model.safetensors",
+        "model.layers.31.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.31.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.31.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.32.input_layernorm.weight": "model.safetensors",
+        "model.layers.32.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.32.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.32.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.32.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.33.input_layernorm.weight": "model.safetensors",
+        "model.layers.33.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.33.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.33.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.33.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.34.input_layernorm.weight": "model.safetensors",
+        "model.layers.34.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.34.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.34.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.34.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.35.input_layernorm.weight": "model.safetensors",
+        "model.layers.35.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.35.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.35.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.35.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

pyproject.toml

@@ -0,0 +1,39 @@
+[build-system]
+requires = ["hatchling>=1.27"]
+build-backend = "hatchling.build"
+
+[project]
+name = "blum-finance"
+version = "0.1.0"
+description = "Structured local inference and opt-in contribution tools for BLUM Finance."
+requires-python = ">=3.11"
+license = { text = "Apache-2.0" }
+dependencies = [
+  "pydantic>=2.10,<3",
+]
+
+[project.optional-dependencies]
+inference = [
+  "accelerate>=1.2",
+  "torch>=2.4",
+  "transformers>=4.51",
+]
+mlx = [
+  "mlx-lm>=0.31,<0.32",
+]
+hub = [
+  "huggingface-hub>=0.30",
+]
+release = [
+  "huggingface-hub>=0.30",
+  "jinja2>=3.1",
+]
+test = [
+  "pytest>=8.3",
+]
+
+[project.scripts]
+blum-contribute = "blum_finance.contributions:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["blum_finance"]

release_manifest.json

@@ -0,0 +1,51 @@
+{
+  "schema_version": "blum-finance-release-v1",
+  "model_repository": "Italianhype/Blum",
+  "base_model": "mlx-community/Qwen3-4B-4bit",
+  "base_revision": "4dcb3d101c2a062e5c1d4bb173588c54ea6c4d25",
+  "candidate_revision": "ea297ba88ab008e97104b0c118103eef2f8f9ec1",
+  "dataset_repository": "Italianhype/Blum-Finance-Reasoning",
+  "dataset_revision": "76ad77699d498fc930daf02e452fe3ec8b490f90",
+  "runtime": "mlx",
+  "promoted": true,
+  "evaluation_validated": true,
+  "transformers_smoke_test_passed": false,
+  "gguf_smoke_test_passed": false,
+  "mlx_smoke_test_passed": true,
+  "evaluation": {
+    "sample_size": 53,
+    "base_aggregate_score": 0.0,
+    "candidate_aggregate_score": 0.962601,
+    "aggregate_delta": 0.962601,
+    "no_fabrication": 0.928571,
+    "structured_validity": 1.0,
+    "calibration_error": 0.0,
+    "calibration_sample_size": 0,
+    "trace_url": "https://huggingface.co/Italianhype/Blum/blob/main/evaluation/candidate_traces.jsonl"
+  },
+  "artifact_hashes": {
+    "CONTRIBUTING.md": "205a156aeed1dee63816d72f5f564f8b10638094742ef61be3c79228fe8cb048",
+    "adapter/adapter_config.json": "81b30269aa85af14db9b69cbda5925151d3b630a67f4510d58b58fc7ad6d2a21",
+    "adapter/adapters.safetensors": "0829ae0d42ec0b84236a381dadb327da7edca211777642e549a627bec5c781f3",
+    "blum_finance/__init__.py": "9b778a45597bf5526fe9fcdcd945755f7ef66fe96b22c81e900c47d6ddf3198f",
+    "blum_finance/contributions.py": "141866a783c3bfd2eff8ab596cceb54134aa0085c00f31cbf14b72870ba316d4",
+    "blum_finance/inference.py": "0cccb24358201889125d4291514a9b2b03dcd2ef4e6db9303dcdfef9c8b85714",
+    "blum_finance/schemas.py": "b05609b0983fc429893c3d117a0fd8f7262d6c2b701b3ba5d2d31d9141be4c85",
+    "chat_template.jinja": "87a2728cb8dc9fe424d624542f6060ec05a1d285ebbec578bb078900e33396b5",
+    "config.json": "b5efdcf3b0035a3638e7228dad4d85f5c4a23f156eb7cdb0b44c8366a5d34d9b",
+    "evaluation/base_summary.json": "b96a55d2f60bee0792c9e2f17da582611f6c72d9ca0b3d22f05e9818fe43acbd",
+    "evaluation/base_traces.jsonl": "bdab7d7d4b490999637c2d9c3dcf6ff5024af2f666fbe6e6bf1568101db83757",
+    "evaluation/candidate_generations.jsonl": "ab842f804b7d9bdacb0a371ad4ecdbcdc41234dff36d47561a12b98aa2430bd7",
+    "evaluation/candidate_summary.json": "1077e0f5927f76825259d4ed5501e2256a216c09532756bc0d51c47f9ba0418f",
+    "evaluation/candidate_traces.jsonl": "e686d76e12a53e4b76ba04ec56acb77c2c6fb683a692c351505ad7744197bde9",
+    "evaluation/mlx_smoke_test.json": "5b713d2fb8dccb7a6f4b12c0fa22e78dd45ca30a031e3755fd7d283a610e7939",
+    "evaluation/promotion_decision.json": "7c2c6ebd6f0dcadbdc38c44fc32daeb93aa61d16f21d8deb06c7267981c273da",
+    "model.safetensors": "52270d4195b046ec5cfbacdf6c6435cd5f3f154a9cf20b4646dab45f87a196d1",
+    "model.safetensors.index.json": "388d811b8b7c2608dd04cce1bcb04a8bf715d19b42790894e6d3427ff429a777",
+    "pyproject.toml": "11cc19acf391c1cc0cbf8ad2871a69589c1129148f72f14772bb6cbf552850f4",
+    "tokenizer.json": "be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506",
+    "tokenizer_config.json": "d93ac1a2c7adb9ad022f354d822f1f0f57e32e62ef2989e902782d6ab896acfe",
+    "training/sanitize_dataset.py": "04b02d62cb4515cc1f69c2b91958e76d12b3555398406fcfeb9a5032704de343",
+    "training_manifest.json": "5e1af1aee55c937a192467fc629868cb60d4144f323a92026e2da5b2ac759bf8"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "tool_parser_type": "json_tools",
+  "unk_token": null
+}

training/sanitize_dataset.py

@@ -0,0 +1,127 @@
+from __future__ import annotations
+
+import argparse
+from copy import deepcopy
+import json
+from pathlib import Path
+import re
+from typing import Any
+
+
+NUMBER_PATTERN = re.compile(r"(?<![A-Za-z])[-+]?\d+(?:\.\d+)?%?")
+REASONING_FIELDS = {
+    "thesis",
+    "bull_case",
+    "bear_case",
+    "risks",
+    "invalidation_conditions",
+    "what_would_change_the_view",
+}
+
+
+def sanitize_example(example: dict[str, Any]) -> tuple[dict[str, Any], int]:
+    """Remove output numbers that were unavailable in the model input."""
+    result = deepcopy(example)
+    messages = result.get("messages") or []
+    if len(messages) < 2 or messages[-1].get("role") != "assistant":
+        return result, 0
+    input_text = json.dumps(messages[:-1], ensure_ascii=False, sort_keys=True)
+    allowed_numbers = set(NUMBER_PATTERN.findall(input_text))
+    try:
+        response = json.loads(messages[-1]["content"])
+    except (TypeError, json.JSONDecodeError):
+        return result, 0
+
+    changes = 0
+    for field in REASONING_FIELDS:
+        value = response.get(field)
+        sanitized, field_changes = sanitize_value(value, allowed_numbers)
+        response[field] = sanitized
+        changes += field_changes
+    confidence = response.get("confidence")
+    if isinstance(confidence, (int, float)) and confidence > 70:
+        response["confidence"] = 70
+        changes += 1
+    messages[-1]["content"] = json.dumps(
+        response,
+        ensure_ascii=False,
+        sort_keys=True,
+    )
+    return result, changes
+
+
+def sanitize_value(value: Any, allowed_numbers: set[str]) -> tuple[Any, int]:
+    if isinstance(value, list):
+        output: list[Any] = []
+        changes = 0
+        for item in value:
+            sanitized, item_changes = sanitize_value(item, allowed_numbers)
+            output.append(sanitized)
+            changes += item_changes
+        return output, changes
+    if not isinstance(value, str):
+        return value, 0
+
+    changes = 0
+
+    def replace(match: re.Match[str]) -> str:
+        nonlocal changes
+        token = match.group(0)
+        if token in allowed_numbers:
+            return token
+        changes += 1
+        return "the observed level"
+
+    return NUMBER_PATTERN.sub(replace, value), changes
+
+
+def sanitize_file(
+    source: Path,
+    *,
+    source_output: Path,
+    mlx_output: Path,
+) -> dict[str, int]:
+    examples = [
+        json.loads(line)
+        for line in source.read_text(encoding="utf-8").splitlines()
+        if line.strip()
+    ]
+    sanitized_rows: list[dict[str, Any]] = []
+    changes = 0
+    for example in examples:
+        sanitized, row_changes = sanitize_example(example)
+        sanitized_rows.append(sanitized)
+        changes += row_changes
+    write_jsonl(source_output, sanitized_rows)
+    write_jsonl(
+        mlx_output,
+        [{"messages": row["messages"]} for row in sanitized_rows],
+    )
+    return {"examples": len(sanitized_rows), "numeric_replacements": changes}
+
+
+def write_jsonl(path: Path, rows: list[dict[str, Any]]) -> None:
+    path.parent.mkdir(parents=True, exist_ok=True)
+    with path.open("w", encoding="utf-8") as handle:
+        for row in rows:
+            handle.write(json.dumps(row, ensure_ascii=False, sort_keys=True) + "\n")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Create an evidence-bound BLUM Finance training derivative."
+    )
+    parser.add_argument("--source", type=Path, required=True)
+    parser.add_argument("--source-output", type=Path, required=True)
+    parser.add_argument("--mlx-output", type=Path, required=True)
+    args = parser.parse_args()
+    result = sanitize_file(
+        args.source,
+        source_output=args.source_output,
+        mlx_output=args.mlx_output,
+    )
+    print(json.dumps(result, indent=2, sort_keys=True))
+
+
+if __name__ == "__main__":
+    main()

training_manifest.json

@@ -0,0 +1,49 @@
+{
+  "base_model": "mlx-community/Qwen3-4B-4bit",
+  "base_revision": "4dcb3d101c2a062e5c1d4bb173588c54ea6c4d25",
+  "candidate_revision": "ea297ba88ab008e97104b0c118103eef2f8f9ec1",
+  "dataset_content_sha256": "4cd60a2a44eabc185f6eceba5e2619aeb11ec437b89fe3cacc5cff240e52deaf",
+  "dataset_repository": "Italianhype/Blum-Finance-Reasoning",
+  "dataset_revision": "76ad77699d498fc930daf02e452fe3ec8b490f90",
+  "early_stopping": {
+    "iteration": 20,
+    "reason": "Validation loss saturated; stopped at the first configured checkpoint to limit memorization.",
+    "validation_loss": 0.02
+  },
+  "evaluation": {
+    "base_summary_sha256": "b96a55d2f60bee0792c9e2f17da582611f6c72d9ca0b3d22f05e9818fe43acbd",
+    "candidate_summary_sha256": "1077e0f5927f76825259d4ed5501e2256a216c09532756bc0d51c47f9ba0418f",
+    "mlx_smoke_test_sha256": "5b713d2fb8dccb7a6f4b12c0fa22e78dd45ca30a031e3755fd7d283a610e7939",
+    "promotion_decision_sha256": "7c2c6ebd6f0dcadbdc38c44fc32daeb93aa61d16f21d8deb06c7267981c273da"
+  },
+  "evidence_bound_derivative": {
+    "numeric_and_confidence_replacements": 3095,
+    "policy": "Replace assistant-output numbers absent from point-in-time input and cap unvalidated confidence at 70; input evidence and split membership remain unchanged.",
+    "test_sha256": "dcdceea08675e9de4be82e0bfa9aee47f2c10af8a51eb2c9b74548b64803265b",
+    "train_sha256": "86f92a5e04cfe19a8c3cc26c4332785b67cd2b2397680c5729ac5753546e863a",
+    "validation_sha256": "fdb8d49c13cea279b8a76f8123c9e0a89ec51bfef964fef3f87c4f0ab3954cbc"
+  },
+  "method": {
+    "batch_size": 1,
+    "layers": 16,
+    "learning_rate": 0.0001,
+    "mask_prompt": true,
+    "max_seq_length": 1024,
+    "rank": 8,
+    "seed": 20260728,
+    "type": "QLoRA"
+  },
+  "model_name": "BLUM Finance 4B",
+  "runtime": {
+    "hardware": "Apple M3 Pro 18 GB",
+    "mlx": "0.32.0",
+    "mlx_lm": "0.31.3"
+  },
+  "schema_version": "blum-finance-mlx-training-v1",
+  "test": {
+    "calibration_labeled_outcomes": 0,
+    "samples": 53,
+    "test_loss": null,
+    "test_perplexity": null
+  }
+}