the whole object this page is drawn from, as JSON · Open JSON {
"id": "atm_site_6abb5344c8abd7418666",
"kind": "Website",
"name": "11 Billion Clues in 800 Million Documents: A Web Research Corpus Annotated with",
"parent_id": null,
"depth": null,
"facts": {
"url": "https://googleresearch.blogspot.com/",
"host": "googleresearch.blogspot.com",
"forms": 0,
"marin": false,
"pages": 1,
"listings": 0,
"site_kind": "unknown",
"found_from": "https://blog.bigml.com/list-of-public-data-sources-fit-for-machine-learning/"
},
"source_id": "src_5ad3cc6df1d1e72a55ad",
"updated_at": "2026-10-13T10:54:29.043Z",
"type": "Feature",
"geometry": null,
"links": {
"self": "https://miscsubjects.com/atlas/atoms/atm_site_6abb5344c8abd7418666",
"children": "https://miscsubjects.com/atlas/atoms/atm_site_6abb5344c8abd7418666/children",
"descendants": "https://miscsubjects.com/atlas/atoms/atm_site_6abb5344c8abd7418666/descendants",
"inside": "https://miscsubjects.com/atlas/atoms/atm_site_6abb5344c8abd7418666/inside",
"graph": "https://miscsubjects.com/atlas/graph?start=atm_site_6abb5344c8abd7418666"
},
"ancestors": [],
"children_by_kind": [],
"edges_out": [],
"edges_in": [
{
"rel": "links_to",
"id": "atm_site_5be262a36de98d0bc041",
"kind": "Website",
"name": "Space Time Mind",
"share": 1
},
{
"rel": "links_to",
"id": "atm_site_6785fdb1ff452c8e545c",
"kind": "Website",
"name": "Steve Blank",
"share": 1
},
{
"rel": "links_to",
"id": "atm_site_961c8499cf75ac5f5d49",
"kind": "Website",
"name": "The Official Blog of BigML.com",
"share": 1
}
],
"edges_in_total": 3,
"external_ids": [],
"source": {
"id": "src_5ad3cc6df1d1e72a55ad",
"url": null,
"license": "public web pages, robots.txt honoured",
"read_at": "2026-10-13T23:21:09.844Z",
"sha256": "208b3244e04e88f503da63917fd963b3f4f5a70528be355db4d5f625a8a28164"
},
"observations": [],
"edges_out_total": 0
}