admin
950284e236
Stabilize Meeting Lab pipeline for RC1 evaluation
...
This commit significantly improves the robustness and determinism of the Meeting Lab processing pipeline and establishes the first Release Candidate baseline for end-to-end evaluation.
Highlights
- BUG-009
- Implement deterministic responsible-party validation
- Normalize participant aliases using Meeting Context
- Reject invalid responsible values (dates, locations, technical terms, projects, products, unknown entities)
- Record structured responsibility validation metadata
- Add focused regression tests
- BUG-010
- Implement adaptive num_predict estimation for Semantic Consolidator
- Eliminate JSON truncation caused by fixed output limits
- Add deterministic source coverage repair
- Preserve strict post-repair validation
- Add regression tests
- BUG-011
- Implement Working Protocol V2 renderer contract enforcement
- Preserve raw renderer responses
- Reject invalid protocol output instead of accepting malformed documents
- Add deterministic cleanup for harmless formatting deviations
- Add focused renderer regression tests
- Meeting Context
- Validate Meeting Context V1
- Integrate authoritative participant alias normalization
- Documentation
- Update architecture documentation
- Update output documentation
- Update regression bug tracker
The pipeline now fails safely instead of silently accepting invalid intermediate or final artifacts.
Remaining work focuses primarily on extraction quality and semantic classification (decisions, action items, protocol faithfulness), rather than pipeline robustness.
2026-08-04 13:11:54 +02:00
admin
60a8acae91
Add second real-life reference meeting (Progeo)
...
- add second real-life Whisper transcript
- add cleaned transcript
- add Meeting Context scaffold
- document evaluation characteristics
- prepare reusable reference dataset
2026-08-03 16:11:46 +02:00
admin
06f0e7e651
Implement Meeting Context V1 and extraction improvements
...
Introduce Meeting Context V1 with YAML schema, validation and template.
Support optional --meeting-context during chunk extraction.
Inject authoritative Meeting Context into extraction prompts.
Record Meeting Context provenance in extraction output.
Activate todos.md in shared prompt assembly.
Strengthen responsibility attribution and decision/todo boundaries.
Add focused Gold scenarios and validation tests.
Update architecture and pipeline documentation.
2026-08-01 16:49:48 +02:00
admin
40f390ebfe
Evaluate Working Protocol Renderer with Semantic Consolidator V0
...
- evaluate Working Protocol renderer using Semantic Consolidator V0 output
- preserve benchmark artifacts for later comparison
- confirm Semantic Consolidator V0 integrates successfully with renderer
- establish baseline before renderer improvements
2026-07-31 11:52:29 +02:00
admin
90aa34d5d0
Implement Semantic Consolidator V0
...
- add deterministic canonicalization support for extraction items
- add facts-only semantic consolidation using local Ollama
- preserve source evidence and validate complete fact coverage
- add conservative merge rules and non-LLM tests
- record the first validated real-life consolidation benchmark
- document current scope, limitations and next evaluation step
2026-07-31 11:25:46 +02:00
admin
6e34334506
Add real-life reference meeting sample
...
- add reproducible real-world meeting sample
- store meeting audio using Git LFS
- include raw and cleaned Whisper transcripts
- add manifest with SHA-256 checksums
- document sample usage and confidentiality
- intentionally exclude generated pipeline artifacts
2026-07-31 10:13:52 +02:00
admin
23bbc744f7
Document canonicalization and consolidation milestone
...
- preserve Working Protocol Synthesizer V0 as comparison baseline
- introduce deterministic canonicalization stage
- define semantic consolidator responsibilities
- clarify Canonical Meeting Knowledge generation
- document source-language output policy
- align roadmap, architecture and experiment log
2026-07-31 09:32:12 +02:00
admin
1a6d731d21
Add windowed segmentation pipeline and review tooling
2026-07-22 16:15:02 +02:00