# MANIFEST

Total: **48 files** (plus this MANIFEST.md), **111,471,989 bytes** (106.31 MB) of payload.

All files in this bucket except this manifest, in alphabetical order. `sha256` is a content fingerprint of the first 16 hex chars. The manifest is not self-referenced (a self-referential SHA is impossible; the verify script parses the manifest implicitly).

| path | bytes | sha256 (16) |
|---|---:|---|
| `README.md` | 10,489 | `e4ef1a33a990f44e` |
| `SOURCE.md` | 5,225 | `b8da2fc9ed54b6b4` |
| `caches/tag_features.sqlite` | 29,446,144 | `c222a35d4d370d0f` |
| `caches/tag_features_standardize_first.sqlite` | 23,920,640 | `1c02176379b5b422` |
| `outputs/filter_first/comparison/pipeline_comparison.md` | 3,537 | `e607e514540faf94` |
| `outputs/filter_first/embeddings/base_key_families.csv` | 25,935 | `ee6d02e7a8e4dc0e` |
| `outputs/filter_first/embeddings/base_key_families.xlsx` | 24,506 | `8d51370bfc54fddc` |
| `outputs/filter_first/embeddings/cluster_medoids_embeddings.csv` | 201,061 | `091b8f11d493d16e` |
| `outputs/filter_first/embeddings/cluster_memberships_embeddings.csv` | 14,054,681 | `ba49d6abef570c44` |
| `outputs/filter_first/embeddings/cluster_profile_embeddings.md` | 31,774 | `85369bb7647d390a` |
| `outputs/filter_first/embeddings/env_agri_breakdown_embeddings.md` | 4,407 | `66fc988133eadb24` |
| `outputs/filter_first/tfidf/base_key_families.csv` | 28,414 | `cccd7f6409791b15` |
| `outputs/filter_first/tfidf/base_key_families.xlsx` | 32,742 | `f8a3470029cec0d1` |
| `outputs/filter_first/tfidf/cluster_medoids.csv` | 338,589 | `f1c7d5a7c6edff8d` |
| `outputs/filter_first/tfidf/cluster_memberships.csv` | 14,118,452 | `2c9618d1e838fdb6` |
| `outputs/filter_first/tfidf/cluster_profile.md` | 34,109 | `6b581162018cb035` |
| `outputs/filter_first/tfidf/env_agri_breakdown.md` | 5,333 | `b5efb80d62fccf19` |
| `outputs/standardize_first/comparison/pipeline_comparison.md` | 3,572 | `a71d41ec945dedf4` |
| `outputs/standardize_first/embeddings/base_key_families.csv` | 25,385 | `fcdffff981d18348` |
| `outputs/standardize_first/embeddings/base_key_families.xlsx` | 41,525 | `8c00aa2d251097ea` |
| `outputs/standardize_first/embeddings/cluster_medoids_embeddings.csv` | 186,860 | `1d472860a8339c84` |
| `outputs/standardize_first/embeddings/cluster_memberships_embeddings.csv` | 14,156,797 | `f06af319b9d40762` |
| `outputs/standardize_first/embeddings/cluster_profile_embeddings.md` | 31,110 | `14f0910ee06139ae` |
| `outputs/standardize_first/embeddings/element_type_stats.csv` | 26,233 | `535344d05f970889` |
| `outputs/standardize_first/embeddings/env_agri_breakdown_embeddings.md` | 4,685 | `84f3374cdfb885bb` |
| `outputs/standardize_first/tfidf/base_key_families.csv` | 28,740 | `b24da21847f3aed6` |
| `outputs/standardize_first/tfidf/base_key_families.xlsx` | 42,476 | `41dc50a697ad7e4e` |
| `outputs/standardize_first/tfidf/cluster_medoids.csv` | 331,542 | `039660cbba8d6308` |
| `outputs/standardize_first/tfidf/cluster_memberships.csv` | 14,215,638 | `dd20a3aac2f413f5` |
| `outputs/standardize_first/tfidf/cluster_profile.md` | 34,525 | `f4de09776609c26f` |
| `outputs/standardize_first/tfidf/element_type_stats.csv` | 24,494 | `a0efebf36c155baf` |
| `outputs/stats/audit_building.csv` | 826 | `5ff0d5e1168863be` |
| `outputs/stats/global_summary.csv` | 136 | `8e904faa2a1b2c58` |
| `outputs/stats/metadata.csv` | 115 | `e6a0d64a0603843c` |
| `outputs/stats/top_10_keys.csv` | 210 | `4f5fed307d3fc5f7` |
| `outputs/stats/top_10_tags.csv` | 286 | `f4276b87c47b8fe4` |
| `reproducibility/reproduce.sh` | 2,429 | `6edb9d908c361dd7` |
| `scripts/build_cache_standardize_first.py` | 3,270 | `c217a6b549ebacc5` |
| `scripts/compare_pipelines.py` | 2,763 | `d8620913413e00ed` |
| `scripts/compare_pipelines_standardize_first.py` | 2,449 | `3c4be207a5909fc4` |
| `scripts/count_rows_after_standardization.py` | 2,261 | `bbd7b26f6038dc8b` |
| `scripts/profile_clusters.py` | 3,517 | `7f86d248dc715055` |
| `scripts/profile_clusters_embeddings.py` | 3,995 | `82adface9c1de466` |
| `scripts/profile_clusters_embeddings_standardize_first.py` | 2,956 | `77243d135590151e` |
| `scripts/profile_clusters_standardize_first.py` | 3,260 | `1e1d3e127f1a025f` |
| `scripts/save_base_key_families.py` | 1,649 | `602331a7cb23ddcf` |
| `scripts/save_base_key_families_standardize_first.py` | 1,674 | `77b8452944d0cd1f` |
| `scripts/write_env_agri_breakdown.py` | 573 | `b599bfbf1d7f6ec7` |
