A small tool to view real-world ActivityPub objects as JSON! Enter a URL
or username from Mastodon or a similar service below, and we'll send a
request with
the right
Accept
header
to the server to view the underlying object.
{
"@context": [
"https://www.w3.org/ns/activitystreams",
{
"ostatus": "http://ostatus.org#",
"atomUri": "ostatus:atomUri",
"inReplyToAtomUri": "ostatus:inReplyToAtomUri",
"conversation": "ostatus:conversation",
"sensitive": "as:sensitive",
"toot": "http://joinmastodon.org/ns#",
"votersCount": "toot:votersCount",
"blurhash": "toot:blurhash",
"focalPoint": {
"@container": "@list",
"@id": "toot:focalPoint"
},
"Hashtag": "as:Hashtag"
}
],
"id": "https://mastodon.social/users/persagen/statuses/110956893568888521",
"type": "Note",
"summary": null,
"inReplyTo": null,
"published": "2023-08-26T16:37:14Z",
"url": "https://mastodon.social/@persagen/110956893568888521",
"attributedTo": "https://mastodon.social/users/persagen",
"to": [
"https://www.w3.org/ns/activitystreams#Public"
],
"cc": [
"https://mastodon.social/users/persagen/followers"
],
"sensitive": false,
"atomUri": "https://mastodon.social/users/persagen/statuses/110956893568888521",
"inReplyToAtomUri": null,
"conversation": "tag:mastodon.social,2023-08-26:objectId=522193476:objectType=Conversation",
"content": "<p>Interpretable Graph Neural Networks for Tabular Data<br /><a href=\"https://arxiv.org/abs/2308.08945\" target=\"_blank\" rel=\"nofollow noopener\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">arxiv.org/abs/2308.08945</span><span class=\"invisible\"></span></a><br />Discussion: <a href=\"https://news.ycombinator.com/item?id=37269376\" target=\"_blank\" rel=\"nofollow noopener\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">news.ycombinator.com/item?id=3</span><span class=\"invisible\">7269376</span></a></p><p>* GNN essentially deep NN black-box models<br />* IGNNet: Interpretable Graph Neural Network for tab data<br />* notable HN comment, resp. to critique: " Right, the significance of orig. article & related research is ChatGPT-like models don't handle tabular data well & there's need for things that do"</p><p><a href=\"https://mastodon.social/tags/DataProcessing\" class=\"mention hashtag\" rel=\"tag\">#<span>DataProcessing</span></a> <a href=\"https://mastodon.social/tags/GraphNeuralNetworks\" class=\"mention hashtag\" rel=\"tag\">#<span>GraphNeuralNetworks</span></a> <a href=\"https://mastodon.social/tags/GNN\" class=\"mention hashtag\" rel=\"tag\">#<span>GNN</span></a> <a href=\"https://mastodon.social/tags/TabularData\" class=\"mention hashtag\" rel=\"tag\">#<span>TabularData</span></a> <a href=\"https://mastodon.social/tags/GPT\" class=\"mention hashtag\" rel=\"tag\">#<span>GPT</span></a> <a href=\"https://mastodon.social/tags/LLM\" class=\"mention hashtag\" rel=\"tag\">#<span>LLM</span></a> <a href=\"https://mastodon.social/tags/IGNNet\" class=\"mention hashtag\" rel=\"tag\">#<span>IGNNet</span></a></p>",
"contentMap": {
"en": "<p>Interpretable Graph Neural Networks for Tabular Data<br /><a href=\"https://arxiv.org/abs/2308.08945\" target=\"_blank\" rel=\"nofollow noopener\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"\">arxiv.org/abs/2308.08945</span><span class=\"invisible\"></span></a><br />Discussion: <a href=\"https://news.ycombinator.com/item?id=37269376\" target=\"_blank\" rel=\"nofollow noopener\" translate=\"no\"><span class=\"invisible\">https://</span><span class=\"ellipsis\">news.ycombinator.com/item?id=3</span><span class=\"invisible\">7269376</span></a></p><p>* GNN essentially deep NN black-box models<br />* IGNNet: Interpretable Graph Neural Network for tab data<br />* notable HN comment, resp. to critique: " Right, the significance of orig. article & related research is ChatGPT-like models don't handle tabular data well & there's need for things that do"</p><p><a href=\"https://mastodon.social/tags/DataProcessing\" class=\"mention hashtag\" rel=\"tag\">#<span>DataProcessing</span></a> <a href=\"https://mastodon.social/tags/GraphNeuralNetworks\" class=\"mention hashtag\" rel=\"tag\">#<span>GraphNeuralNetworks</span></a> <a href=\"https://mastodon.social/tags/GNN\" class=\"mention hashtag\" rel=\"tag\">#<span>GNN</span></a> <a href=\"https://mastodon.social/tags/TabularData\" class=\"mention hashtag\" rel=\"tag\">#<span>TabularData</span></a> <a href=\"https://mastodon.social/tags/GPT\" class=\"mention hashtag\" rel=\"tag\">#<span>GPT</span></a> <a href=\"https://mastodon.social/tags/LLM\" class=\"mention hashtag\" rel=\"tag\">#<span>LLM</span></a> <a href=\"https://mastodon.social/tags/IGNNet\" class=\"mention hashtag\" rel=\"tag\">#<span>IGNNet</span></a></p>"
},
"attachment": [
{
"type": "Document",
"mediaType": "image/png",
"url": "https://files.mastodon.social/media_attachments/files/110/956/885/942/887/760/original/e058bc58031ef027.png",
"name": "Interpretable Graph Neural Networks for Tabular Data\n\nFigure 1: An overview of our proposed approach. Each data instance is represented as a graph by embedding the feature values into a higher dimensionality, and the edge between two features (nodes) is the correlation value. Multiple iterations of message passing are then applied. Finally, the learned node representation is projected into a single value, and a whole graph representation is obtained by concatenating the projected values.\n\nFigure 2: IGNNet default architecture. It starts with the embedding layer, a linear transformation from one dimension to 64 dimensions. A Relu activation function follows each message-passing layer and each green block as well. The feedforward network at the end has no activation functions between layers to ensure a linear transformation into a single value. A sigmoid activation function follows the feedforward network to obtain the final value for each feature between 0 and 1.\n\nArticle: https://arxiv.org/pdf/2308.08945.pdf\n\nDiscussion (Hacker News): https://news.ycombinator.com/item?id=37269376\n\n",
"blurhash": "U8S6PkRixuWC?boMxukCD%ozt6ay~qt6afV[",
"focalPoint": [
-0.03,
0.58
],
"width": 1319,
"height": 916
}
],
"tag": [
{
"type": "Hashtag",
"href": "https://mastodon.social/tags/dataprocessing",
"name": "#dataprocessing"
},
{
"type": "Hashtag",
"href": "https://mastodon.social/tags/graphneuralnetworks",
"name": "#graphneuralnetworks"
},
{
"type": "Hashtag",
"href": "https://mastodon.social/tags/gnn",
"name": "#gnn"
},
{
"type": "Hashtag",
"href": "https://mastodon.social/tags/tabulardata",
"name": "#tabulardata"
},
{
"type": "Hashtag",
"href": "https://mastodon.social/tags/gpt",
"name": "#gpt"
},
{
"type": "Hashtag",
"href": "https://mastodon.social/tags/llm",
"name": "#llm"
},
{
"type": "Hashtag",
"href": "https://mastodon.social/tags/ignnet",
"name": "#ignnet"
}
],
"replies": {
"id": "https://mastodon.social/users/persagen/statuses/110956893568888521/replies",
"type": "Collection",
"first": {
"type": "CollectionPage",
"next": "https://mastodon.social/users/persagen/statuses/110956893568888521/replies?only_other_accounts=true&page=true",
"partOf": "https://mastodon.social/users/persagen/statuses/110956893568888521/replies",
"items": []
}
},
"likes": {
"id": "https://mastodon.social/users/persagen/statuses/110956893568888521/likes",
"type": "Collection",
"totalItems": 3
},
"shares": {
"id": "https://mastodon.social/users/persagen/statuses/110956893568888521/shares",
"type": "Collection",
"totalItems": 3
}
}