{"adoption": {"forks": 179, "observed_at": "2026-08-28T04:04:10.394103+00:00", "stars": 1263}, "canonical_url": "https://ross.abutalabs.com/products/meta-pytorch-data", "card": {"archived": false, "artifact_type": "library", "description": "A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.", "domain": ["machine-learning", "deep-learning"], "enriched": true, "function": ["machine-learning", "etl", "streaming", "data-science"], "health_score": 88, "homepage": null, "language": "Python", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "active", "member_repos": ["meta-pytorch/data"], "name": "meta-pytorch/data", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-26T11:42:20+00:00", "repo": "meta-pytorch/data", "stars": 1263, "tags": ["pytorch", "dataloader", "checkpointing", "stateful-dataloader", "data-pipeline", "torchdata", "data-engineering", "gpu"], "topics": [], "urls": [], "use_cases": ["checkpoint dataloader state mid-epoch for resumable training", "replace PyTorch DataLoader with a stateful version", "build streaming data loading pipelines with composable iterators", "track RNG states and worker buffers across training restarts", "share data loading utilities across PyTorch domain libraries"], "what_it_is": "TorchData is a PyTorch library providing scalable, performant data loading utilities, including StatefulDataLoader, a drop-in replacement for torch.utils.data.DataLoader with mid-epoch checkpointing via state_dict/load_state_dict. It also offers torchdata.nodes, a library of composable iterators for building streaming data pipelines.", "when_to_avoid": ["you don't use PyTorch or its DataLoader", "you need a general-purpose ETL tool outside ML training", "you require a stable, long-frozen API since the project is still iterating"], "when_to_choose": ["you need fault-tolerant, resumable PyTorch training loops with mid-epoch checkpointing", "you want composable, streaming-style dataloading primitives in PyTorch", "you're on the PyTorch ecosystem and want the successor to torch.utils.data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/meta-pytorch-data", "repo": "meta-pytorch/data", "role": "main", "score": 67}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.394103+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:04:09.035130+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f5c96918694984d92c1afe82a70dd39c8e66c11e00aea6a7eac47e185d79c2e", "fetched_at": "2026-08-28T04:04:10.394103+00:00", "kind": "readme", "missing": false, "url": "https://github.com/meta-pytorch/data"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1939, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 67, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}