lexical_taxonomy_schema
Build and validate compact WordNet-style synset and semantic-pointer taxonomies for recovery experiments.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- lexical_taxonomy_schema
- description
- Build and validate compact WordNet-style synset and semantic-pointer taxonomies for recovery experiments.
02 资源文件 2
03 SKILL.md 正文
Lexical Taxonomy Schema
Use this skill when a task needs a WordNet-style lexical graph with synsets, word senses, and typed semantic pointers. Do not use it as a substitute for the full WordNet database; it is a schema and reduced-fixture builder for mechanism-faithful experiments.
Inputs
- Synset records with
id,lemmas,pos, optionalgloss, andrelations. - Relation records with
typeandtargetsynset id.
Outputs
- Validated taxonomy dictionaries.
- Inventory counts for character strings, synsets, string-sense combinations, and semantic pointers.
- Lemma/POS lookup indexes for downstream tagging.
Workflow
- Represent each lexicalized concept as a synset rather than as a single surface word.
- Preserve many-to-many word-to-sense mappings because the paper distinguishes strings from string-sense combinations.
- Validate relation endpoints before any tagging or distance computation.
- Use typed semantic pointers such as hyponym, antonym, meronym, related, or pertains_to.
- Record inventory counts whenever a recovery claims to reproduce WordNet-like structure.
Validation
Run python tests/test_lexical_schema.py or validate the tree with validate_skill_tree.py --run-tests.
Limitations
The bundled fixture is intentionally tiny. It tests mechanism contracts only and does not contain the original WordNet database.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).