[{"_id":"698e9bc6ac54d3a59f1c2c1c","id":"issdandavis/scbe-aethermoore-training-data","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:47:54.000Z","likes":2,"trendingScore":0,"private":false,"sha":"c7e4a69b189c4f28d4afe015895fa2a7ca8a065a","description":"\nStatus: canonical. Primary public training dataset for SCBE-AETHERMOORE and the most-used repo in this account. Other scbe-* dataset repos are experiment-specific slices.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE-AETHERMOORE Training Dataset\n\t\n\nSupervised fine-tuning (SFT) dataset for the SCBE-AETHERMOORE hyperbolic geometry AI safety and governance framework.\n\n\t\n\t\t\n\t\n\t\n\t\tOverview\n\t\n\nThis dataset contains 10,978 training pairs spanning the full SCBE-AETHERMOORE system: 14-layer architecture knowledge, Six Sacred… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-aethermoore-training-data.","downloads":4544,"tags":["task_categories:text-generation","language:en","license:mit","size_categories:10K<n<100K","region:us","scbe-aethermoore","ai-safety","hyperbolic-geometry","post-quantum-cryptography","isekai-game","sft","instruction-tuning","sacred-tongues","canonical"],"createdAt":"2026-02-13T03:34:30.000Z","key":""},{"_id":"6991440cfeed3f913398c1bb","id":"issdandavis/scbe-aethermoore-datasets","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:36:48.000Z","likes":0,"trendingScore":0,"private":false,"sha":"ad553a821897d680640ffddbe79ca0812ca7d32a","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tissdandavis/scbe-aethermoore-knowledge-base\n\t\n\nProgrammatic SCBE training package built from the local ledgered corpus.\n\nGenerated at: 2026-04-04T16:17:19.436108+00:00\nSource file: training/ledgered/sft_ledgered_clean.jsonl\nAudit status: ALLOW\nRows total: 15206\nTrain rows: 13685\nValidation rows: 760\nTest rows: 761\nPositive pairs: 15206\n\n\n\t\n\t\t\n\t\n\t\n\t\tFiles\n\t\n\n\ndata/all.jsonl —… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-aethermoore-datasets.","downloads":42,"tags":["size_categories:10K<n<100K","format:json","modality:tabular","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","experimental"],"createdAt":"2026-02-15T03:57:00.000Z","key":""},{"_id":"6991511e8be5bf83219eac62","id":"issdandavis/aethermoor-rag-training-data","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:47:56.000Z","likes":0,"trendingScore":0,"private":false,"sha":"9571b145368f382b93bd23d475bbe868e7d845db","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tAethermoor RAG Training Data\n\t\n\nCurated markdown knowledge corpus for SCBE-AETHERMOORE and Aethermoor ecosystem projects.\n\n\t\n\t\t\n\t\n\t\n\t\tStructure\n\t\n\n\nworldforge/*\ncharacter-sheet-system/*\nhydra-protocol/*\nstarter-pack/*\ndataset_index.jsonl\n\n\n\t\n\t\t\n\t\n\t\n\t\tTraining-ready format\n\t\n\ndataset_index.jsonl contains one JSON object per row:\n\nid\ntitle\nsource_path\ncategory\ntext\ncreated_at… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/aethermoor-rag-training-data.","downloads":34,"tags":["task_categories:text-retrieval","task_categories:question-answering","language:en","license:mit","size_categories:n<1K","format:parquet","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","scbe","aethermoore","rag","worldforge","character-sheet-system","hydra-protocol","starter-pack","experimental"],"createdAt":"2026-02-15T04:52:46.000Z","key":""},{"_id":"6996a0612d77e2b2f777276b","id":"issdandavis/UltraData-Math","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:47:57.000Z","likes":2,"trendingScore":0,"private":false,"sha":"3ce13f632a4305b7ee3df519e3b13d0ffc963707","description":"\nStatus: mirror of an upstream dataset. Not original SCBE work and not an SCBE experiment: this is a copy of the public UltraData-Math corpus (290B+ tokens, 181.2M rows, 552 GB). Kept as a pretraining source. Original SCBE data: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tUltraData-Math\n\t\n\n\n  \n\n\n\n🤗 Dataset | 💻 Source Code | 🇨🇳 中文 README\n\n\nUltraData-Math is a large-scale, high-quality mathematical pre-training dataset totaling 290B+ tokens across three progressive tiers—L1 (170.5B tokens… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/UltraData-Math.","downloads":354,"tags":["task_categories:text-generation","language:en","language:zh","license:apache-2.0","size_categories:100M<n<1B","format:parquet","modality:text","library:datasets","library:dask","library:polars","library:mlcroissant","region:us","llm","pretraining","math","data-synthesis","data-filtering","high-quality","mathematical-reasoning","mirror"],"createdAt":"2026-02-19T05:32:17.000Z","key":""},{"_id":"69b6ed8d4e42dea6fa0141a2","id":"issdandavis/scbe-webtoon-job-scripts","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:34:58.000Z","likes":0,"trendingScore":0,"private":false,"sha":"355f5e0bd5306ad279b377c7b5906dd4310f9bea","description":"\nStatus: experimental. Research artifact, not a production candidate. Canonical dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE webtoon job scripts\n\t\n\nOne file: jobs/webtoon_hf_embedded_job.py.\nThis is a script repository, not a dataset. It holds the HF Jobs entry point\nused to generate webtoon panels; there are no data rows here, so the Dataset\nViewer has nothing to show. Panel output goes to\nsix-tongues-webtoon-panels.\n","downloads":34,"tags":["license:apache-2.0","region:us","scbe","webtoon","hf-jobs","experimental"],"createdAt":"2026-03-15T17:34:05.000Z","key":""},{"_id":"69b6f17c03fb414df11d790a","id":"issdandavis/six-tongues-webtoon-panels","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:34:59.000Z","likes":0,"trendingScore":0,"private":false,"sha":"15f305ed7b85d2cc14d93625ba3bdd3829c59574","description":"\nStatus: experimental. Research artifact, not a production candidate. Canonical dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSix Tongues webtoon panels\n\t\n\nGenerated panel output. Numbers below are from\nsmoke-ch01-sdxl/run_summary.json in this repo.\n\nRun: smoke-ch01-sdxl\nModel: stabilityai/sdxl-turbo\nCorpus embedded: 38 chapters, 305 panels\nThis run: 1 chapter selected, 2 seen, 2 generated, 4.2 seconds\n\nPanels ship as smoke-ch01-sdxl/six_tongues_panels.zip. Because the images are… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/six-tongues-webtoon-panels.","downloads":33,"tags":["license:apache-2.0","region:us","scbe","six-tongues","webtoon","text-to-image","experimental"],"createdAt":"2026-03-15T17:50:52.000Z","key":""},{"_id":"69b736d46815d51abce65cfa","id":"issdandavis/six-tongues-art-style","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:34:59.000Z","likes":0,"trendingScore":0,"private":false,"sha":"34ada9c72442333e823efb376470a9924d48aaf4","description":"\nStatus: experimental. Research artifact, not a production candidate. Canonical dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSix Tongues art style reference\n\t\n\nStyle and character reference images for the Six Tongues / Aethermoore setting.\nImage files only - no annotations, captions, or metadata, so this is a reference\npack rather than a trainable image-text dataset.\nContents include a book cover, a character reference sheet\n(marcus_chen_reference_sheet.png), and exterior/interior… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/six-tongues-art-style.","downloads":41,"tags":["license:apache-2.0","size_categories:n<1K","format:imagefolder","modality:image","library:datasets","library:mlcroissant","region:us","scbe","six-tongues","art-style","reference","experimental"],"createdAt":"2026-03-15T22:46:44.000Z","key":""},{"_id":"69c39cf4d8e46e3b91bf0841","id":"issdandavis/scbe-red-team-benchmarks","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:36:52.000Z","likes":0,"trendingScore":0,"private":false,"sha":"ae96ea4693a5cca69583d511981dec91ce1ad638","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE-AETHERMOORE Red Team & Benchmark Test Suites\n\t\n\nPatent: USPTO #63/961,403 (provisional)\nAuthor: Issac Daniel Davis (ORCID: 0009-0002-3936-9369)\nLive Demos: https://aethermoorgames.com/demos/\n\n\t\n\t\t\n\t\n\t\n\t\tWhat's Here\n\t\n\n\n\t\n\t\t\n\t\n\t\n\t\tAdversarial Red Team Suite (16 files)\n\t\n\n\n91 attack prompts across 10 categories\nDirect override, indirect injection, encoding obfuscation… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-red-team-benchmarks.","downloads":29,"tags":["region:us","experimental"],"createdAt":"2026-03-25T08:29:40.000Z","key":""},{"_id":"69d874c9689d8fb20a4eac35","id":"issdandavis/scbe-life-science-research-training-demo","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:36:54.000Z","likes":0,"trendingScore":0,"private":false,"sha":"d80267cf561cb99830dced396a3f7f31d300e5cf","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE Research Training Package\n\t\n\nThis package was generated from live pubmed pulls for the query protein structure prediction and is meant for\nlightweight Hugging Face dataset and SFT experiments.\n\n\t\n\t\t\n\t\n\t\n\t\tFiles\n\t\n\n\npapers.jsonl: normalized raw research records\nsft_train.jsonl: train split for instruction-style tasks\nsft_validation.jsonl: validation split… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-life-science-research-training-demo.","downloads":44,"tags":["task_categories:text-generation","task_categories:question-answering","language:en","license:mit","size_categories:n<1K","format:json","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","research","pubmed","instruction-tuning","citation-generation","experimental"],"createdAt":"2026-04-10T03:55:53.000Z","key":""},{"_id":"69dc4cccf90606f2fc706dba","id":"issdandavis/code-flow-pretraining","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:35:00.000Z","likes":0,"trendingScore":0,"private":false,"sha":"3889576aeced1e5cb904b1eb97ac46a2b07e7d1d","description":"\nStatus: experimental. Research artifact, not a production candidate. Canonical dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tCode-flow pretraining\n\t\n\nStaged pretraining data plus the generators that produced it, so each stage is\nreproducible rather than a loose dump.\nData\n\ndata/stage4_musical_code.jsonl\ndata/stage5_dense_multicoded.jsonl\n\nGenerators\n\nscripts/generate_code_flow_dataset.py\nscripts/generate_stage4_musical_code.py\nscripts/generate_stage5_dense_multicoded.py\n\nTraining… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/code-flow-pretraining.","downloads":94,"tags":["license:apache-2.0","region:us","scbe","pretraining","code","music","experimental"],"createdAt":"2026-04-13T01:54:20.000Z","key":""},{"_id":"69dc66865198e117f62862e6","id":"issdandavis/prompt-injection-bit-signatures","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:36:55.000Z","likes":1,"trendingScore":0,"private":false,"sha":"ad8dec89117464be6fb6c943a13e1b5441aa76d7","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tPrompt Injection → Bit Signatures\n\t\n\n24,254 labeled prompts from 4 public prompt-injection datasets, each mapped through the Six Sacred Tongues bijective tokenizer from the SCBE-AETHERMOORE framework into a lossless per-prompt bit signature.\nStratified 70/15/15 train/val/test split by (source, label) so every source is represented in every split with its original label… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/prompt-injection-bit-signatures.","downloads":77,"tags":["task_categories:text-classification","language:en","license:apache-2.0","size_categories:10K<n<100K","format:json","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","ai-safety","prompt-injection","jailbreak","llm-security","adversarial","scbe","sacred-tongues","bijective-tokenization","experimental"],"createdAt":"2026-04-13T03:44:06.000Z","key":""},{"_id":"69e57ed265cbe2b17a4c26fe","id":"issdandavis/scbe-drill-langues-full","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:35:01.000Z","likes":0,"trendingScore":0,"private":false,"sha":"1061452d2bc608a00b42fc5a25527caf92996a12","description":"\nStatus: experimental. Research artifact, not a production candidate. Canonical dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE langues drill (full)\n\t\n\nOne file: drill_langues_full.jsonl.\nDrill set over the six Sacred Tongues (KO, AV, RU, CA, UM, DR) used for\ntokenizer and translation practice rows. Single split, no train/eval division -\nif you need a held-out set, carve one yourself and group by semantic root so the\nsame item does not appear on both sides.\n","downloads":33,"tags":["license:apache-2.0","size_categories:1K<n<10K","format:json","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","scbe","sacred-tongues","drill","sft","experimental"],"createdAt":"2026-04-20T01:18:10.000Z","key":""},{"_id":"69e5c46565cbe2b17a537fd5","id":"issdandavis/scbe-tongue-drill-sft-v1","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:36:56.000Z","likes":0,"trendingScore":0,"private":false,"sha":"f256aa842f702f259a1f2d958fc4dc470563b974","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE Tongue Drill SFT v1\n\t\n\nSupervised fine-tuning drill dataset for the SCBE Sacred Tongues table-lock system.\nEach row is a 3-turn chat (system / user / assistant) teaching the model to emit\ncanonical packets verbatim for a given (map, tongue, value) triple.\n\n\t\n\t\t\n\t\n\t\n\t\tSplits\n\t\n\n\n\t\n\t\t\nSplit\nRows\n\n\n\t\t\nall\n2630\n\n\ntrain\n2373\n\n\nholdout\n257\n\n\n\t\n\nHoldout is row_index % 10 == 0… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-tongue-drill-sft-v1.","downloads":22,"tags":["task_categories:text-generation","language:en","license:apache-2.0","size_categories:1K<n<10K","format:json","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","scbe","sacred-tongues","lora","drill","sft","experimental"],"createdAt":"2026-04-20T06:15:01.000Z","key":""},{"_id":"69e5d5d9c3f0c38f763db2ed","id":"issdandavis/scbe-codeflow-bijective-v1","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:36:58.000Z","likes":0,"trendingScore":0,"private":false,"sha":"8455e5a3a2c4ed1c5544d36f528ff5ff5d13c606","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE Codeflow Bijective v1\n\t\n\nSupervised fine-tuning corpus teaching bijective multi-tongue / multi-language\ncode editing. Each algorithm is decomposed into N semantic slots. Every slot\nis filled in all 6 Sacred Tongues. An edit at slot k in any tongue maps\ndeterministically to the parallel slot k in every other tongue. Syntactic line\ncounts may differ per tongue; semantic… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-codeflow-bijective-v1.","downloads":33,"tags":["task_categories:text-generation","language:en","license:apache-2.0","size_categories:1K<n<10K","format:json","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","scbe","sacred-tongues","bijective-coding","multi-language","code-translation","lora","sft","experimental"],"createdAt":"2026-04-20T07:29:29.000Z","key":""},{"_id":"69ee699a0621cac42ffb370e","id":"issdandavis/scbe-training-regularized-20260426","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:35:01.000Z","likes":0,"trendingScore":0,"private":false,"sha":"c99703a3a6b2dded414f368edbc61446083641d2","description":"\nStatus: experimental. Research artifact, not a production candidate. Canonical dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE training data, regularized (2026-04-26)\n\t\n\nRegularized SFT lanes, each with its own train, eval, and manifest, under\nregularized/<lane>/. Lanes present include aligned_foundations,\ncoding_model, and commerce_product.\nEvery lane follows the same shape:\nregularized/<lane>/<lane>_train.regularized.jsonl\nregularized/<lane>/<lane>_eval.regularized.jsonl… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-training-regularized-20260426.","downloads":38,"tags":["license:apache-2.0","region:us","scbe","sft","regularized","experimental"],"createdAt":"2026-04-26T19:38:02.000Z","key":""},{"_id":"69f80b715ec43b12d40d5925","id":"issdandavis/scbe-chemistry-sft","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:35:02.000Z","likes":0,"trendingScore":0,"private":false,"sha":"e1700c1dd8c79d8549f1d30a73aefaa48c62a246","description":"\nStatus: experimental. Research artifact, not a production candidate. Canonical dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE chemistry SFT\n\t\n\nChemistry adapter training data, split by purpose rather than one flat pile:\n\nchemistry_adapter_invariants_v1_{train,eval}.sft.jsonl - conservation and\ninvariant rows\nchemistry_adapter_verification_v1_{train,eval}.sft.jsonl - verification rows\nchemistry_gate_repair_v1_{train,eval}.sft.jsonl - gate-repair rows\naligned_foundations_v2_{train… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-chemistry-sft.","downloads":46,"tags":["license:apache-2.0","region:us","scbe","chemistry","sft","experimental"],"createdAt":"2026-05-04T02:58:57.000Z","key":""},{"_id":"69f92e49768eb9b0a04f3b83","id":"issdandavis/scbe-governance-receipts-v1","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T23:30:28.000Z","likes":0,"trendingScore":0,"private":false,"sha":"96b8650066d703d855b2339fabffaff4ed64cc31","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE Governance Receipts v1\n\t\n\nSchema: scbe_governed_dataset_v1\nReceipt schema: scbe_governance_receipt_v1\nBuilt: 2026-05-04T23:45:37Z\nRows: 40\nDataset ID: scbe-governance-receipts-v1\n\n\t\n\t\t\n\t\n\t\n\t\tWhat this is\n\t\n\nA governed dataset where every row carries a full 34-field SCBE\ngovernance receipt (poly-embedded JEPA fingerprint + tri-vector\ncross-braid hash + Sacred Egg ring seal… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-governance-receipts-v1.","downloads":34,"tags":["task_categories:text-classification","task_categories:other","language:en","license:cc-by-4.0","size_categories:n<1K","format:json","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","scbe","governance","hyperbolic-geometry","jepa","safety","hierarchical-jepa","experimental"],"createdAt":"2026-05-04T23:39:53.000Z","key":""},{"_id":"69f9437109d3c3b8d5bb41e9","id":"issdandavis/scbe-spine-overlay-proof-v1","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:48:03.000Z","likes":0,"trendingScore":0,"private":false,"sha":"0bde9eec0c882926fc287fe3c153229607e19272","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE Spine-Overlay Proof v1\n\t\n\nTiny demonstration bundle (18 rows = 3 domains x 6 tongues)\nproving that the SCBE 12+ lane code-packet spine handles code,\nchemistry, and mechanical motion as overlays on a single tokenizer\nsubstrate, without forking the system.\n\n\t\n\t\t\n\t\n\t\n\t\tWhy this exists\n\t\n\nEvery row carries the same baseline lanes (binary, tokenizer, transport,\nlabels… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-spine-overlay-proof-v1.","downloads":64,"tags":["language:en","license:cc-by-4.0","size_categories:n<1K","format:json","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","region:us","scbe","sacred-tongues","multi-domain","code","chemistry","robotics","motion","experimental"],"createdAt":"2026-05-05T01:10:09.000Z","key":""},{"_id":"6a02cee29729f2a0f937a8cd","id":"issdandavis/scbe-system-hygiene-training-data","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:48:04.000Z","likes":0,"trendingScore":0,"private":false,"sha":"fc4b6159cde139da2e840544c6c0326b56fdf663","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tSCBE System Hygiene Training\n\t\n\nMetadata-only SCBE cleanup training records generated at 2026-05-12T06:55:13Z.\nThis dataset teaches local-first cleanup decisions: keep harness-wired models,\nreview ambiguous model/cache state, and turn deletion candidates into scrubbed\ntraining examples before pruning local storage.\nIt does not include raw cache files, model weights, local logs… See the full description on the dataset page: https://huggingface.co/datasets/issdandavis/scbe-system-hygiene-training-data.","downloads":37,"tags":["task_categories:text-generation","task_categories:question-answering","language:en","license:cc-by-4.0","region:us","scbe","system-hygiene","training-data","metadata-only","experimental"],"createdAt":"2026-05-12T06:55:30.000Z","key":""},{"_id":"6a5bfbd1b1b34205e4196949","id":"issdandavis/github-learning-projects","author":"issdandavis","disabled":false,"gated":false,"lastModified":"2026-07-29T21:48:05.000Z","likes":0,"trendingScore":0,"private":false,"sha":"e9248e5879550ffa61932f1082284aaf6ef3d38d","description":"\nStatus: experimental. Experiment-specific slice. Primary public dataset: scbe-aethermoore-training-data.\n\n\n\t\n\t\t\n\t\n\t\n\t\tGitHub\n\t\n\nkokl\n","downloads":132,"tags":["modality:document","modality:text","region:us","experimental"],"createdAt":"2026-07-18T22:18:57.000Z","key":""}]