[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79862WD7Z2CVXEXEGWC4RFH":3,"skill-same:01M79862WD7Z2CVXEXEGWC4RFH":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M79862WD7Z2CVXEXEGWC4RFH","pairwise_similarity_preservation",null,"Compute DDPM-PA pairwise cosine-softmax distributions and adapted-to-source KL preservation loss.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fddpm_pairwise_adaptation\u002Fpairwise_similarity_preservation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pairwise_similarity_preservation\ndescription: Compute DDPM-PA pairwise cosine-softmax distributions and adapted-to-source KL preservation loss.\n---\n\n# Pairwise Similarity Preservation\n\nUse this skill when implementing the DDPM-PA relative-distance preservation term. It compares the geometry of source and adapted generated samples by converting pairwise cosine similarities into per-anchor probability distributions and minimizing KL divergence.\n\nDo not use this skill to compare images to target training images directly. It preserves relative geometry between source and adapted predictions, while target-detail matching belongs to the high-frequency module.\n\n## Inputs\n\n- Source samples or features shaped as a batch of equally shaped numeric vectors, images, or nested lists.\n- Adapted samples or features with identical batch size and compatible flattened dimension.\n- Optional numerical epsilon and softmax temperature.\n\n## Outputs\n\n- Per-anchor source distributions over non-self samples.\n- Per-anchor adapted distributions over non-self samples.\n- Scalar KL preservation loss using `KL(p_adapted || p_source)`.\n\n## Workflow\n\n1. Flatten each batch element and L2-normalize it with epsilon protection.\n2. Compute cosine similarities for every ordered anchor\u002Fneighbor pair.\n3. Exclude self-pairs before softmax.\n4. Convert similarities to probability distributions.\n5. Sum or average adapted-to-source KL divergence across anchors.\n6. Return diagnostics so recovery can prove self-pair exclusion and finite loss.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fpairwise_loss.py --smoke\npython -m pytest tests\n```\n\nThe tests check zero loss for identical geometry, positive loss for changed geometry, and no self-index in neighbor lists.\n\n## Limitations\n\nThe included implementation is deterministic and standard-library only. For tensor frameworks, keep the same anchor-wise exclusion and KL direction; changing either changes the paper mechanism.\n","# Pairwise Similarity Preservation\n\nUse this skill when implementing the DDPM-PA relative-distance preservation term. It compares the geometry of source and adapted generated samples by converting pairwise cosine similarities into per-anchor probability distributions and minimizing KL divergence.\n\nDo not use this skill to compare images to target training images directly. It preserves relative geometry between source and adapted predictions, while target-detail matching belongs to the high-frequency module.\n\n## Inputs\n\n- Source samples or features shaped as a batch of equally shaped numeric vectors, images, or nested lists.\n- Adapted samples or features with identical batch size and compatible flattened dimension.\n- Optional numerical epsilon and softmax temperature.\n\n## Outputs\n\n- Per-anchor source distributions over non-self samples.\n- Per-anchor adapted distributions over non-self samples.\n- Scalar KL preservation loss using `KL(p_adapted || p_source)`.\n\n## Workflow\n\n1. Flatten each batch element and L2-normalize it with epsilon protection.\n2. Compute cosine similarities for every ordered anchor\u002Fneighbor pair.\n3. Exclude self-pairs before softmax.\n4. Convert similarities to probability distributions.\n5. Sum or average adapted-to-source KL divergence across anchors.\n6. Return diagnostics so recovery can prove self-pair exclusion and finite loss.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fpairwise_loss.py --smoke\npython -m pytest tests\n```\n\nThe tests check zero loss for identical geometry, positive loss for changed geometry, and no self-index in neighbor lists.\n\n## Limitations\n\nThe included implementation is deterministic and standard-library only. For tensor frameworks, keep the same anchor-wise exclusion and KL direction; changing either changes the paper mechanism.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fddpm_pairwise_adaptation\u002Fpairwise_similarity_preservation",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill pairwise_similarity_preservation",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill pairwise_similarity_preservation",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill pairwise_similarity_preservation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fddpm_pairwise_adaptation\u002Fpairwise_similarity_preservation\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fpairwise_loss.py","SCRIPT","脚本",2640,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fddpm_pairwise_adaptation\u002Fpairwise_similarity_preservation\u002Fscripts\u002Fpairwise_loss.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_pairwise_loss.py",932,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbridging-data-gaps\u002Fskill\u002Fddpm_pairwise_adaptation\u002Fpairwise_similarity_preservation\u002Ftests\u002Ftest_pairwise_loss.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp 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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","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()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert 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.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch 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).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]