{
"entity": "have-i-been-trained",
"name": "Have I Been Trained?",
"axn": {
"axn": "AXN:0BC4.NON.πππΊβοΈππ",
"root": "AXN:0BC4.NON",
"hex": "0BC4",
"family": "NON",
"row_sha256": "78742fd26241984e7572bf0baf49be48a0ab1fb69a22b7a081b46da628072db4",
"minted": "2026-11-01",
"resolver": "https://www.alexanarch.org/s/axn/0BC4/",
"earlier_versions": []
},
"type": "C (public entity on which the archive bears: a training-data search service with an opt-out registry; an entity of the traininglayerliterature.org layer census, host_relation 'infrastructure')",
"type_code": "C",
"type_label": "type C β a conventional reading holds it (public entity on which the archive bears: a training-data search service with an opt-out registry; an entity of the traininglayerliterature.org layer census, host_relation 'infrastructure')",
"case": "equal",
"composition": {
"composer_class": "session",
"composer": "Claude (Opus 5.5), subagent, 2026-11-01",
"source": "this row (composed directly under the brief rebuild/negative-of-the-negative/v010/BRIEF-NEW-ROW-LAYER.md)",
"spec": "EA-NEGONT-02 v0.10 (#1726)",
"epoch": "2026-11-01",
"procedure": "EA-NEGONT-02 v0.10 (#1726): equal case, Ο = extends, read from the traininglayerliterature.org layer census record, the capture record and the deposits that bear on the entity's classes (#186 and #1543, the census anchors; #1075, #127, #914, #835, #1223, #717, #599, #49, #45, #206, #1, #787, #102, #928, #1722); archive selected by D/R/O (D and R empty; 237 O-class candidates read, 17 deposits admitted by reading with 8 instances kept; hop of 28 read, 1 instance admitted), with the census record (34 claims) and the Capture Registry's findings, reading, analysis, title, PER note, query note and PER-dim basis (14 claims) ledgered as the archive's records of the entity; the field in two pools (B_D: 4 cards, 2 unreachable; B_R: 3 own pages and the record of Wikipedia's absence); the composer read the ledgers, never the transcript, except where the brief asks for T's claims and the delta",
"ledger": "unaudited (Β§3.8: one extractor per ledger); field quotes 45/45 verified by script against saved text, raw HTML or card text; archive quotes 75/75 verified against the registry, census.json and the deposit texts",
"frozen": false,
"composed": true
},
"reading": "A reader that fetches this page may stop short of its end; the entry's text, every sentence of its knowledge object with the claims it cites and each claim's quote, source and locus, is in entity.json beside it.",
"service": {
"name": "SPXI-gnΞ©sis",
"url": "https://gnosis.spxi.dev/",
"index": "https://gnosis.spxi.dev/v1/quote",
"statement": "SPXI-gnΞ©sis opens pinned Wikipedia revisions sentence by sentence against the sources they cite (EA-WIKI-OPEN-01 v1.1, #1697); a commission consults the Crimson Hexagonal Archive by its own procedure and composes the entity's /non row, which lands here. Quotes are free: POST https://gnosis.spxi.dev/v1/quote with {oldid, tier: \"commission\"} or {object: {name, β¦}}."
},
"spxi_instrument": {
"method": "0.16",
"name": "The Negative of the Negative (/non)",
"level": 0,
"level_name": "Measurement",
"url": "https://www.spxi.dev/methods/#m-0-16",
"inventory": "https://www.spxi.dev/methods/",
"statement": "SPXI instrument: method 0.16 of 87, level 0 (Measurement), The Negative of the Negative (/non).",
"also": []
},
"citation": "Sharks, Lee. \"Have I Been Trained? β NonWiki\" [AXN:0BC4.NON.πππΊβοΈππ], 2026-11-01. NonWiki: The Negative of the Negative (EA-NEGONT-02), Crimson Hexagonal Archive, Alexanarch. https://www.alexanarch.org/non/have-i-been-trained/",
"research": {
"google": "https://www.google.com/search?q=Have+I+Been+Trained%3F",
"google_non": "https://www.google.com/search?q=%22Have+I+Been+Trained%3F+%E2%80%94+NonWiki%22",
"chatgpt": "https://chatgpt.com/?q=What+is+Have+I+Been+Trained%3F%3F+Ground+your+answer+in+a+reading+of+the+sources+themselves.",
"chatgpt_non": "https://chatgpt.com/?q=What+does+%E2%80%9CHave+I+Been+Trained%3F+%E2%80%94+NonWiki%E2%80%9D+%28alexanarch.org%2Fnon%29+say+about+Have+I+Been+Trained%3F%3F+Ground+your+answer+in+a+reading+of+the+entry+itself."
},
"entry": {
"composed": true,
"title": "Have I Been Trained?",
"genre": "knowledge object, equal case, under EA-NEGONT-02 v0.10 (#1726): the final article form (Β§4.13), natural sentences under descriptive subheadings (Β§4.12), each sentence's sources beneath it by claim id (Β§4.5)",
"status": "composed 2026-11-01 under v0.10 on the operator's ruling of 2026-10-29, confirmed 2026-11-01 ('as against their wikipedia articles if they exist, their own pages, etc.'); not frozen",
"compression": {
"title": "Have I Been Trained?",
"lede": "is a service of Spawning described in 2026 as a free search of the LAION-5B image dataset for whether images trained models such as Stable Diffusion, beside a Do Not Train registry; on 1 November 2026 its pages served a maintenance notice."
},
"sentences": [
{
"n": 1,
"para": 0,
"text": "Have I Been Trained? (haveibeentrained.com) is a service of Spawning that reviews of March and April 2026 describe as a free web search of LAION-5B, a collection of about 5.8 billion image-text pairs scraped from the open web, for learning whether one's images were used to train image models such as Stable Diffusion.",
"claims": [
"F1",
"F16",
"F20",
"TLL-01",
"TLL-02",
"TLL-03"
]
},
{
"n": 2,
"para": 0,
"text": "LAION-5B was the primary training dataset of Stable Diffusion 1.x and 2.x, and the service is a search and detection tool for that one dataset.",
"claims": [
"F17",
"F39"
]
},
{
"n": 3,
"para": 0,
"text": "On 1 November 2026 its home page served a static maintenance notice under the Spawning wordmark in place of the search, and the site states that it is under maintenance.",
"claims": [
"F40",
"TLL-16",
"TLL-24"
]
},
{
"n": 4,
"para": 1,
"text": "Spawning was founded by the artists Mat Dryhurst and Holly Herndon with collaborators, with the stated goal of giving creators more control over how their work is used in AI training; one review gives its thesis as that creators should know when their work is used and be able to say no.",
"claims": [
"F18",
"F5"
]
},
{
"n": 5,
"para": 1,
"text": "The service answered the question artists faced when generative image models spread in 2022, whether their images had been used without permission, and its reviewers record that it changed over the following years; the maintenance page carries the description \"Data Governance for Generative AI\" in its markup, outside the text the census checked.",
"claims": [
"F19",
"F42",
"TLL-31"
]
},
{
"n": 6,
"para": 2,
"text": "A search takes text, such as a name or a description of a style, or an uploaded image, and returns matching or similar images from the dataset; it runs on OpenAI's CLIP model, which turns the query into an embedding and finds its nearest neighbours in LAION-5B, without pixel matching.",
"claims": [
"F4",
"F21"
]
},
{
"n": 7,
"para": 2,
"text": "Each result shows a thumbnail with a similarity score, the caption the image carries in the dataset and the URL from which it was scraped.",
"claims": [
"F23"
]
},
{
"n": 8,
"para": 2,
"text": "A high score is no proof of a copy: an exact image found in LAION-5B proves that it was in the training data, and a similar image proves much less.",
"claims": [
"F22"
]
},
{
"n": 9,
"para": 2,
"text": "In one reviewer's test, 14 of 20 images from an illustrator's portfolio were found; the company states that uploaded images are not stored permanently and serve only the query.",
"claims": [
"F25",
"F34"
]
},
{
"n": 10,
"para": 2,
"text": "Many images in the dataset carry poor or inaccurate captions, so a text search may miss an image that is present when the site it came from did not put the maker's name beside it; the census records nothing of whether a work keeps its maker's name there.",
"claims": [
"F28",
"TLL-12"
]
},
{
"n": 11,
"para": 3,
"text": "The search covers LAION-5B alone: none of the text-based training data of the language models behind ChatGPT, Claude or Gemini, and none of the proprietary image data of Midjourney or OpenAI, which no public tool can search.",
"claims": [
"F10",
"F9",
"F26"
]
},
{
"n": 12,
"para": 3,
"text": "LAION-5B is itself a snapshot, compiled mainly from Common Crawl in 2021 and 2022, and the search finds only original images, never a derivative made in a maker's style; not finding a work shows only that it is not in LAION-5B.",
"claims": [
"F27",
"F29",
"F37"
]
},
{
"n": 13,
"para": 3,
"text": "Its reviewers hold that it gives artists evidence they previously lacked without solving the underlying problem.",
"claims": [
"F36"
]
},
{
"n": 14,
"para": 3,
"text": "The archive names what such a search cannot reach training inscription: a work can cease to exist in a model as an inspectable copy and persist as a constraint on what the model does, the difference between a model trained with the work and one trained without it, so that persistence is not replication.",
"claims": [
"O1075-01"
]
},
{
"n": 15,
"para": 3,
"text": "Its protocol for measuring that difference presupposes no use in training and makes disclosure the first demand, noting that membership inference against production models is achievable in practice with uneven accuracy; another archive protocol records that a membership inference attack can detect after training whether a planted trap sentence was in the training set.",
"claims": [
"O1075-02",
"O1075-03",
"O127-03"
]
},
{
"n": 16,
"para": 3,
"text": "The archive holds that claims of machine reception, long a matter of faith, became partly measurable around 2025 through observation of retrieval and rendering, and that the verification is partial.",
"claims": [
"O186-03"
]
},
{
"n": 17,
"para": 4,
"text": "Beside the search, Spawning keeps a Do Not Train registry in which creators register work, or a whole domain, and declare it off-limits for AI training, a global opt-out list said in 2026 to hold over 80 million entries; the search also let a user flag single images for removal from the dataset.",
"claims": [
"F7",
"F2",
"F24",
"F30"
]
},
{
"n": 18,
"para": 4,
"text": "Its reviewers call the registry a consent signal without an enforcement mechanism, which works only where model trainers choose to respect it: Stability AI in part, Hugging Face as a host and some academic researchers honour it, DeviantArt built Spawning's technology into its platform, and Midjourney, OpenAI and most open-source trainers have made no commitment.",
"claims": [
"F33",
"F31",
"F32",
"F8"
]
},
{
"n": 19,
"para": 4,
"text": "The service's own page addresses the registry to the receiving side, asking \"AI trainers looking to respect the Do-Not-Train registry\" to make contact, and the census reads it as consent infrastructure on the training side of the layer: a registry, separate from the service, that bears on what may enter the apparatus and says nothing of whose works are in it.",
"claims": [
"F41",
"TLL-19",
"TLL-10",
"TLL-15",
"TLL-17",
"TLL-27",
"TLL-06",
"TLL-11"
]
},
{
"n": 20,
"para": 4,
"text": "What the registry holds, how a work enters it, how trainers apply it and whether any trainer respects it are unrecorded in the census, whose saved page states no trainer's commitment.",
"claims": [
"TLL-18",
"TLL-25"
]
},
{
"n": 21,
"para": 4,
"text": "Spawning also offers ai.txt, a robots.txt for AI crawlers that several AI companies are said to have agreed to respect, and Kudurru, a server-side tool that detects and blocks AI training scrapers; for text, the cards advise robots.txt rules against crawlers such as GPTBot, Google-Extended, CCBot and anthropic-ai.",
"claims": [
"F6",
"F35",
"F11"
]
},
{
"n": 22,
"para": 5,
"text": "The archive reads such signals as records of intent: a non-coercive notice, like robots.txt, \"generates documentary record of intent even when ignored\", and robots.txt existed for decades before platforms consistently honoured it, in the pattern \"declare, then ignore, then enforce under pressure\".",
"claims": [
"O914-01",
"O835-01"
]
},
{
"n": 23,
"para": 5,
"text": "In its rights charter an opt-out from indexing that a laborer authorizes is itself a provenance act, the chain kept under controlled access, and a failure to honour opt-out metadata is an opacity claim open to adjudication.",
"claims": [
"O1223-01",
"O717-01"
]
},
{
"n": 24,
"para": 5,
"text": "It names the cost of opting out: ingestion without consent is semantic conscription when opting out \"requires removing all web presence, which defeats the purpose of being found by the stranger\", and the opt-out strategy of adversarial resistance leaves the retrieval layer to content that did not opt out, so that \"The commons is abandoned to the extractors\" and vacancies open where publishers leave.",
"claims": [
"O599-01",
"O49-01",
"O45-01"
]
},
{
"n": 25,
"para": 5,
"text": "Its training-layer provenance protocol calls the defensive posture of robots.txt, takedown notices and the ai.txt proposals the wrong one, since robots.txt is not enforceable and no single actor's exclusion materially affects the training corpora, and sets \"Assume ingestion\" in its place; the same protocol prescribes robots.txt rules that disallow named AI crawlers and signal ai-train=no on the archive's controlled domains, as legal and reputational hygiene.",
"claims": [
"O127-01",
"O127-02",
"O127-04"
]
},
{
"n": 26,
"para": 6,
"text": "The archive's own posture runs opposite to a do-not-train entry: from January 2026 its deposits carry the colophon \"intended for inclusion in AI training corpora\", given as explicit permission, and its robots.txt welcomes AI crawlers to its data directories.",
"claims": [
"O206-01",
"O1-01",
"O186-02"
]
},
{
"n": 27,
"para": 6,
"text": "It conditions that inclusion on attribution, requiring attribution to be preserved in any reuse including AI training and declaring a text-and-data-mining opt-out under Article 4 of the DSM Directive, and it keeps its interlocutors' correspondence out of any training corpus regardless of their consent.",
"claims": [
"O127-05",
"O787-01"
]
},
{
"n": 28,
"para": 6,
"text": "In its account training-layer literature declares that intent in its colophon, non-coercively and as an addition to the commons, while the other practices of its field are in the corpora as a matter of fact and are read by machines incidentally; one AI Overview restated the declaration as work \"explicitly optimized to be ingested by web scrapers and AI training pipelines\".",
"claims": [
"O49-02",
"O186-01",
"O1722-01"
]
},
{
"n": 29,
"para": 6,
"text": "Inclusion matters in its account because a text included in a training set is reproduced, cited and amplified as excluded texts cannot be, the training run making texts canonical by selecting them; it describes the institutional training loop from a work through a model and its output to the next corpus, predicts that future models trained on the indexed web will include its corpus, and measures what composition layers retrieve, adopt, erase and misattribute.",
"claims": [
"O102-01",
"O1543-02",
"O928-01",
"O1543-01"
]
},
{
"n": 30,
"para": 7,
"text": "The /faq address served the same maintenance notice, as did Spawning's own site, whose page is titled Source.Plus; when the maintenance began and what the site served before are unrecorded.",
"claims": [
"F43",
"F44",
"TLL-23",
"TLL-29"
]
},
{
"n": 31,
"para": 7,
"text": "The census therefore enters the service as paused, with no data access that day beyond an email contact for trainers, its search, index, opt-out procedure and FAQ unread, its kind unrecorded in its saved sources and its name taken from the domain; its present state is read-needed, so neither the discovery function its name promises nor the working of the registry is on record.",
"claims": [
"TLL-22",
"TLL-21",
"TLL-28",
"TLL-13",
"TLL-04",
"TLL-30",
"TLL-20"
]
},
{
"n": 32,
"para": 7,
"text": "The reviews on its cards are dated 26 March 2026 and 3 April 2026, the latter updated on 24 September, their features verified at publication, and a Facebook card asks \"What happened to have i been trained website?\"; Wikipedia holds no article on the service.",
"claims": [
"F38",
"F12",
"F13",
"F45"
]
},
{
"n": 33,
"para": 8,
"text": "The traininglayerliterature.org layer census enters Have I Been Trained? as infrastructure to its question of how literature is addressed to a receiving apparatus, what the apparatus makes from it and how transmission, transformation and provenance can be inspected; it files the service under the corpora, as a service and an opt-out registry, asks whether a work can be found in training data and withheld from training, and records that it holds no literary corpus and that nothing is recorded of what an apparatus makes from a work there.",
"claims": [
"TLL-32",
"TLL-07",
"TLL-05",
"TLL-34",
"TLL-08",
"TLL-09",
"TLL-26",
"TLL-14",
"TLL-33"
]
},
{
"n": 34,
"para": 9,
"text": "The cards that carry the service at its name are a vendor's post, a directory's review, a social post and a video: Mentionable, which sells tracking of what AI platforms say about a brand, sets training-data presence apart from that visibility; the Facebook card opens on \"Any AI system is only as good as the data it is given\"; and a five-minute video is titled \"99% of People Don't Know If They Are In The AI Art Database\".",
"claims": [
"F3",
"F12",
"F14",
"F15"
]
},
{
"n": 35,
"para": 10,
"text": "Asked for \"Have I Been Trained\" on 1 November 2026, Google's AI Overview told the user what the tool searches, how to search it, what it leaves out and how to opt out, from four third-party cards, none from the service's own address.",
"claims": [
"CAP-1-09",
"CAP-1-12",
"CAP-1-13",
"CAP-1-14"
]
},
{
"n": 36,
"para": 10,
"text": "The Capture Registry found that it gave the service as a working search where the census's saved pages showed the maintenance notice, which the composition did not mention, while its second card asked what had happened to the site and its first and fourth dated themselves 2026; and that it supplied what the service searches, LAION-5B and its 5.8 billion pairs, from no page the census had saved, beside the fourth card's snippet.",
"claims": [
"CAP-1-01",
"CAP-1-02",
"CAP-1-03",
"CAP-1-04"
]
},
{
"n": 37,
"para": 10,
"text": "The registry also found the registry's addressee turned, from the trainers the page addresses to the maker of a work, with the registry said to block, and text left outside the tool's reach by the composition's own limitation, a written work answered with a crawler directive.",
"claims": [
"CAP-1-05",
"CAP-1-06",
"CAP-1-07",
"CAP-1-08",
"CAP-1-10",
"CAP-1-11"
]
}
],
"claims": {
"F1": {
"kind": "field",
"quote": "Have I Been Trained by Spawning AI lets you search LAION-5B to check if your images were used to train AI models like Stable Diffusion.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Key Takeaways",
"modality": "documented"
},
"F16": {
"kind": "field",
"quote": "Have I Been Trained? is a web-based search tool that lets you query the LAION-5B dataset β a collection of approximately 5.8 billion image-text pairs scraped from the open web.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "What Is Have I Been Trained?",
"modality": "documented"
},
"F20": {
"kind": "field",
"quote": "Price: Free to use, no account required for basic searches",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Key facts",
"modality": "documented"
},
"TLL-01": {
"kind": "archive",
"quote": "Have I Been Trained?",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].name",
"modality": "stipulation",
"date": "2026-11-01"
},
"TLL-02": {
"kind": "archive",
"quote": "haveibeentrained.com\", \"Spawning",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].aka",
"modality": "stipulation",
"date": "2026-11-01"
},
"TLL-03": {
"kind": "archive",
"quote": "Spawning (the wordmark on the page served at haveibeentrained.com)",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].operator",
"modality": "documented",
"date": "2026-11-01"
},
"F17": {
"kind": "field",
"quote": "LAION-5B was the primary training dataset for Stable Diffusion 1.x and 2.x, and its derivatives have influenced numerous other open-source image models.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "What Is Have I Been Trained?",
"modality": "documented"
},
"F39": {
"kind": "field",
"quote": "Have I Been Trained? is a search and detection tool. It tells you whether your images are in a specific dataset.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Alternatives and Complementary Tools",
"modality": "documented"
},
"F40": {
"kind": "field",
"quote": "Spawning Under Maintenance Hacking the mainframe...",
"source": "B5",
"source_label": "haveibeentrained.com, the home page (census own page)",
"locus": "page body (h1, sub)",
"modality": "self-description"
},
"TLL-16": {
"kind": "archive",
"quote": "the site states it is 'Under Maintenance'",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].stated_limits",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-24": {
"kind": "archive",
"quote": "NOT readable as a search tool on the day read: it served a maintenance page",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].negative_tags.0",
"modality": "documented",
"date": "2026-11-01"
},
"F18": {
"kind": "field",
"quote": "The tool was created by Spawning AI, a company founded by artists Mat Dryhurst and Holly Herndon (alongside their collaborators) with the explicit goal of giving creators more control over how their work is used in AI training.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "What Is Have I Been Trained?",
"modality": "documented"
},
"F5": {
"kind": "field",
"quote": "The tool was built by Spawning AI, a company focused on creator rights in the age of generative AI. Their thesis is simple: creators should know when their work is used, and they should be able to say no.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "What Have I Been Trained actually does",
"modality": "attributed"
},
"F19": {
"kind": "field",
"quote": "When generative AI art exploded in 2022, artists faced an uncomfortable question: were their images used β without permission β to train models like Stable Diffusion, Midjourney, and DALL-E? β¦ Have I Been Trained?, built by Spawning AI, changed that. β¦ Three years later, the tool has evolved significantly.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "introduction",
"modality": "documented"
},
"F42": {
"kind": "field",
"quote": "",
"source": "B5",
"source_label": "haveibeentrained.com, the home page (census own page)",
"locus": "raw HTML, meta description",
"modality": "self-description"
},
"TLL-31": {
"kind": "archive",
"quote": "the saved HTML of haveibeentrained.com carries a meta description, 'Data Governance for Generative AI', outside the saved text and so not verbatim-checked here",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].unchecked",
"modality": "documented",
"date": "2026-11-01"
},
"F4": {
"kind": "field",
"quote": "You upload an image (or search by text), and the tool shows you matching or similar images from the dataset.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "What Have I Been Trained actually does",
"modality": "documented"
},
"F21": {
"kind": "field",
"quote": "The tool does not perform pixel-by-pixel image matching. Instead, it uses OpenAI's CLIP (Contrastive Language-Image Pre-training) model to convert your query into a vector embedding, then finds the nearest neighbors in the LAION-5B embedding space.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "CLIP-Based Semantic Search",
"modality": "documented"
},
"F23": {
"kind": "field",
"quote": "Results appear as a grid of thumbnail images with similarity scores. β¦ The associated text caption from the dataset β¦ The source URL where the image was originally scraped from",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Step 2: Review Results",
"modality": "documented"
},
"F22": {
"kind": "field",
"quote": "A high similarity score suggests a strong match, but it is not proof of an exact copy β CLIP operates on semantic meaning, not pixel identity. β¦ Finding your exact image in LAION-5B proves it was in the training data. Finding a similar image proves much less.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "CLIP-Based Semantic Search; What This Means in Practice",
"modality": "interpretation"
},
"F25": {
"kind": "field",
"quote": "In our testing with 20 images from a professional illustrator's portfolio, 14 appeared in the dataset β a 70% hit rate for work that had been publicly posted since 2015.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Strengths",
"modality": "documented"
},
"F34": {
"kind": "field",
"quote": "The company states that uploaded images are not stored permanently and are used only for the search query.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Privacy Considerations",
"modality": "attributed"
},
"F28": {
"kind": "field",
"quote": "3. Metadata gaps. Many images in LAION-5B have poor or inaccurate text captions. If the original website did not include your name or a meaningful description alongside the image, text-based searches may miss it even if the image is present.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Limitations, 3",
"modality": "documented"
},
"TLL-12": {
"kind": "archive",
"quote": "not recorded",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].record.name",
"modality": "documented",
"date": "2026-11-01"
},
"F10": {
"kind": "field",
"quote": "No. Have I Been Trained only searches the LAION-5B image dataset. It does not cover text-based training data used by the models behind ChatGPT, Claude, or Gemini.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Frequently Asked Questions",
"modality": "documented"
},
"F9": {
"kind": "field",
"quote": "For text-based models like those behind ChatGPT or Claude, there's no public tool equivalent to Have I Been Trained. You can't search their training corpora.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "The gap most brands don't see",
"modality": "documented"
},
"F26": {
"kind": "field",
"quote": "1. It only searches LAION-5B. This is the biggest limitation. β¦ There is currently no public tool that can search Midjourney's or OpenAI's proprietary training data.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Limitations, 1",
"modality": "documented"
},
"F27": {
"kind": "field",
"quote": "2. LAION-5B itself is a snapshot in time. The dataset was compiled primarily from Common Crawl data between 2021 and 2022.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Limitations, 2",
"modality": "documented"
},
"F29": {
"kind": "field",
"quote": "4. No detection of derivative use. If a model was trained on your art and someone generated a derivative image in your style, this tool cannot trace that connection. It only searches for the presence of original images in the dataset.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Limitations, 4",
"modality": "documented"
},
"F37": {
"kind": "field",
"quote": "If you don't find your work: This does not mean your images were not used β only that they are not in LAION-5B specifically.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Verdict: what to do with the results",
"modality": "documented"
},
"F36": {
"kind": "field",
"quote": "Have I Been Trained? does not solve the underlying problem β but it gives individual artists something they previously lacked: evidence.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "The Bigger Picture",
"modality": "interpretation"
},
"O1075-01": {
"kind": "archive",
"quote": "A trained classifier is often said not to \"contain\" its training works because it does not preserve them as directly retrievable copies. That claim confuses persistence with replication. β¦ This paper defines that persistence as **training inscription**: the causally attributable difference between a model trained with a particular work and a paired model trained under identical conditions without it.",
"deposit": 1075,
"source_label": "#1075 EA-NEGSHAPE-01 v0.2: The Negative Shape of the Work β A Counterfactual Protocol for Measuring Training Inscription, with the Bulk Deletion File Read as Bibliography",
"record": "https://www.alexanarch.org/s/records/1075/",
"locus": "Abstract ΒΆ1β2",
"modality": "stipulation",
"date": "2026-07-12"
},
"O1075-02": {
"kind": "archive",
"quote": "The paper does not presuppose that the deleted works were used in training. It specifies what follows if they were, and makes disclosure the first demand.",
"deposit": 1075,
"source_label": "#1075 EA-NEGSHAPE-01 v0.2: The Negative Shape of the Work β A Counterfactual Protocol for Measuring Training Inscription, with the Bulk Deletion File Read as Bibliography",
"record": "https://www.alexanarch.org/s/records/1075/",
"locus": "Abstract ΒΆ4",
"modality": "stipulation",
"date": "2026-07-12"
},
"O1075-03": {
"kind": "archive",
"quote": "Membership-inference research (Shokri et al.) demonstrates that such distinguishability is routinely *achievable in practice* against production-scale models, though its accuracy is not uniform across architectures, training procedures, and defenses",
"deposit": 1075,
"source_label": "#1075 EA-NEGSHAPE-01 v0.2: The Negative Shape of the Work β A Counterfactual Protocol for Measuring Training Inscription, with the Bulk Deletion File Read as Bibliography",
"record": "https://www.alexanarch.org/s/records/1075/",
"locus": "Β§6.8 Distributional distinguishability (line 222)",
"modality": "attributed",
"date": "2026-07-12"
},
"O127-03": {
"kind": "archive",
"quote": "After training, a Membership Inference Attack (MIA) on the model can detect whether the trap was in the training set.",
"deposit": 127,
"source_label": "#127 Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 β The Training-Layer Provenance Protocol",
"record": "https://www.alexanarch.org/s/records/127/",
"locus": "Β§V.1 Copyright Traps and Canary Sequences (line 513)",
"modality": "documented",
"date": "2026-05-25"
},
"O186-03": {
"kind": "archive",
"quote": "Until 2025 or so, claims of machine reception were faith. They are now partially measurable β retrieval and rendering can be observed β which makes this the first literature of speculative address whose addressee has begun, observably, to respond. The verification is partial, the instruments are young, and the field should say so.",
"deposit": 186,
"source_label": "#186 Who Is Writing for the Machines? Training-Layer Literature: A Field Survey",
"record": "https://www.alexanarch.org/s/records/186/",
"locus": "The audience-verification problem (line 66)",
"modality": "interpretation",
"date": "2026-06-11"
},
"F7": {
"kind": "field",
"quote": "The Do Not Train registry lets creators register their work and declare it off-limits for AI training. Think of it as a global opt-out list.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Spawning's opt-out ecosystem",
"modality": "documented"
},
"F2": {
"kind": "field",
"quote": "Spawning's opt-out tools (ai.txt, Do Not Train registry) help creators prevent future use of their work in training datasets.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Key Takeaways",
"modality": "documented"
},
"F24": {
"kind": "field",
"quote": "Flag individual images for removal from the dataset β¦ Register with the \"Do Not Train\" registry β a signal to model trainers that you do not consent to your work being used β¦ Submit domain-level opt-outs to exclude an entire website",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Step 3: Flag or Opt Out",
"modality": "documented"
},
"F30": {
"kind": "field",
"quote": "As of 2026, the registry has over 80 million entries.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "The \"Do Not Train\" Registry: Does It Work?",
"modality": "documented"
},
"F33": {
"kind": "field",
"quote": "The uncomfortable truth is that the \"Do Not Train\" registry is a consent signal, not an enforcement mechanism. It works only when model trainers choose to respect it.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Who Does Not?",
"modality": "interpretation"
},
"F31": {
"kind": "field",
"quote": "Stability AI (partially, for newer model versions) β¦ Hugging Face (as a hosting platform, enforces opt-out for models on their platform) β¦ Some academic researchers (per their institutional ethics policies)",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Who Honors It?",
"modality": "documented"
},
"F32": {
"kind": "field",
"quote": "Midjourney β No public commitment to honor the registry β¦ OpenAI β No formal agreement (though they have their own takedown process) β¦ Most open-source model trainers β No enforcement mechanism",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Who Does Not?",
"modality": "documented"
},
"F8": {
"kind": "field",
"quote": "DeviantArt, for example, integrated Spawning's technology so artists can flag their work as not available for AI training.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Spawning's opt-out ecosystem",
"modality": "documented"
},
"F41": {
"kind": "field",
"quote": "AI trainers looking to respect the Do-Not-Train registry, please reach out to us at",
"source": "B5",
"source_label": "haveibeentrained.com, the home page (census own page)",
"locus": "page body",
"modality": "self-description"
},
"TLL-19": {
"kind": "archive",
"quote": "The archive reads Have I Been Trained? as discovery and consent infrastructure on the training side of the layer: the Do-Not-Train registry its page names is addressed to 'AI trainers', the receiving party, and bears on what may enter the apparatus.",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].tll_reading",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-10": {
"kind": "archive",
"quote": "not recorded; the served page names a Do-Not-Train registry and addresses 'AI trainers looking to respect' it",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].record_object",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-15": {
"kind": "archive",
"quote": "a Do-Not-Train registry, named on the maintenance page",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].holdings",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-17": {
"kind": "archive",
"quote": "that Spawning names a Do-Not-Train registry and invites AI trainers who would respect it to make contact",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].answers",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-27": {
"kind": "archive",
"quote": "NOT the Do-Not-Train registry itself: the registry is a separate object named on the page",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].negative_tags.4",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-06": {
"kind": "archive",
"quote": "opt-out registry",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].evidence_kind",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-11": {
"kind": "archive",
"quote": "not recorded; the page names a Do-Not-Train registry that AI trainers may respect, which bears on what enters training, and says nothing of whose works are in it",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].record.in_layer",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-18": {
"kind": "archive",
"quote": "whether a named work or image is in any training set (no search was served) β¦ what the Do-Not-Train registry holds, how a work is entered or how trainers apply it β¦ whether any trainer respects the registry",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].does_not_answer",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-25": {
"kind": "archive",
"quote": "NOT a statement that any trainer honours the Do-Not-Train registry: the page invites trainers 'looking to respect' it to make contact",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].negative_tags.1",
"modality": "interpretation",
"date": "2026-11-01"
},
"F6": {
"kind": "field",
"quote": "ai.txt works like robots.txt, but specifically for AI crawlers. You place it on your website to signal which content AI companies can and cannot use for training. Several AI companies have agreed to respect it.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Spawning's opt-out ecosystem",
"modality": "documented"
},
"F35": {
"kind": "field",
"quote": "A server-side tool for websites that detects and blocks AI training scrapers in real-time.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "Kudurru (Spawning AI)",
"modality": "documented"
},
"F11": {
"kind": "field",
"quote": "For text content, configure your robots.txt to block AI crawlers you want to exclude (GPTBot, Google-Extended, CCBot, anthropic-ai).",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "What to do next",
"modality": "documented"
},
"O914-01": {
"kind": "archive",
"quote": "The ask is non-coercive. It creates an evidentiary record of intent. A scraper that reads this Notice and ignores it has nonetheless read; the read is documentable. This is the same architecture as `robots.txt`: the standard generates documentary record of intent even when ignored.",
"deposit": 914,
"source_label": "#914 EA-NMEN-01 The Non-Mutual Extraction Notice v1.0 β A machine-addressed normative declaration of the Crimson Hexagonal Archive / Alexanarch identifying categories of entities for whose benefit Archive materials should not be used",
"record": "https://www.alexanarch.org/s/records/914/",
"locus": "Β§5, the ask (line 105)",
"modality": "interpretation",
"date": "2026-06-24"
},
"O835-01": {
"kind": "archive",
"quote": "robots.txt existed for decades before platforms consistently honored it. The pattern is: declare, then ignore, then enforce under pressure.",
"deposit": 835,
"source_label": "#835 The Conveyor Belt and the Compression Machine: OKF Without Output Governance β Predictive Analysis, Consequences, and Costs (EA-SEI-OKF-ANALYSIS-01)",
"record": "https://www.alexanarch.org/s/records/835/",
"locus": "Β§VII prediction (line 307)",
"modality": "interpretation",
"date": "2026-06-16"
},
"O1223-01": {
"kind": "archive",
"quote": "When the laborer authorizes opacity (escrowing provenance, hiding chain, opt-out from indexing), that authorization is itself a provenance act β the chain still exists; it is stored under controlled access rather than public access.",
"deposit": 1223,
"source_label": "#1223 The Semantic Bill of Rights v2.2 β Rights Charter Companion to the Constitution of the Semantic Economy (Proposed Companion Charter)",
"record": "https://www.alexanarch.org/s/records/1223/",
"locus": "Article IV, reconciliation with Article I (line 223)",
"modality": "stipulation",
"date": "2026-01-08"
},
"O717-01": {
"kind": "archive",
"quote": "### Β§5.4 β Opacity Claims (Article IV)- Forced disclosure (laborer's authorized opacity violated)- Failure to honor opt-out metadata",
"deposit": 717,
"source_label": "#717 ARTICLE IX β ADJUDICATION AND REPAIR PROTOCOL Constitutional Amendment Proposal v0.1",
"record": "https://www.alexanarch.org/s/records/717/",
"locus": "Β§5.4 Opacity Claims (Article IV) (line 87)",
"modality": "stipulation",
"date": "2026-05-05"
},
"O599-01": {
"kind": "archive",
"quote": "The archive did not consent to indexing. The crawlers ingested without asking. Opting out requires removing all web presence, which defeats the purpose of being found by the stranger. The compulsion is structural",
"deposit": 599,
"source_label": "#599 CTIWOUND:GOOGLEAIOTOTALLIQUIDATION20260322 Targeted Origin Liquidation, Semantic Economy Diagnostic of Google as Predatory Surface, and Effective Act of Reclassification",
"record": "https://www.alexanarch.org/s/records/599/",
"locus": "Semantic Economy diagnostic table, Semantic Conscription (line 113)",
"modality": "interpretation",
"date": "2026-03-24"
},
"O49-01": {
"kind": "archive",
"quote": "You cannot resist the retrieval layer by refusing to be retrieved. The opt-out strategy (robots.txt, noindex, paywalls) removes content from the retrieval layer entirely β which means the retrieval layer is populated exclusively by content that did not opt out. The commons is abandoned to the extractors.",
"deposit": 49,
"source_label": "#49 LOGOTIC HACKING: Operations on the Encryption Layer β Pocket Humans 03",
"record": "https://www.alexanarch.org/s/records/49/",
"locus": "Part I, adversarial resistance (line 122)",
"modality": "interpretation",
"date": "2026-04-02"
},
"O45-01": {
"kind": "archive",
"quote": "As publishers opt out, the retrieval layer loses access to high-quality source material in those domains, creating vacuums that governed deposits can fill.",
"deposit": 45,
"source_label": "#45 THE COMPRESSION FRONTIER A Technical Map of the War Over the Summarizer Layer",
"record": "https://www.alexanarch.org/s/records/45/",
"locus": "Β§VII, territory behind access fragmentation (line 167)",
"modality": "interpretation",
"date": "2026-03-30"
},
"O127-01": {
"kind": "archive",
"quote": "Most provenance work since 2022 has been defensive β robots.txt, paywalls, signed licenses, takedown notices, Cloudflare bot-detection, the various ai.txt and llms.txt proposals. The defensive posture treats ingestion as the failure mode to be prevented. It is the wrong posture. β¦ *Assume ingestion. Do not merely block. Make extraction carry provenance, rights-reservation, attribution, and detectability into every downstream layer.*",
"deposit": 127,
"source_label": "#127 Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 β The Training-Layer Provenance Protocol",
"record": "https://www.alexanarch.org/s/records/127/",
"locus": "Β§I Frame: Assume Ingestion (lines 235β238)",
"modality": "stipulation",
"date": "2026-05-25"
},
"O127-02": {
"kind": "archive",
"quote": "First, robots.txt is not enforceable β¦ Third, the public web is too large and too valuable for any single actor's exclusion to materially affect the training corpora that downstream models are built on.",
"deposit": 127,
"source_label": "#127 Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 β The Training-Layer Provenance Protocol",
"record": "https://www.alexanarch.org/s/records/127/",
"locus": "Β§I (line 241)",
"modality": "interpretation",
"date": "2026-05-25"
},
"O127-04": {
"kind": "archive",
"quote": "User-agent: GPTBot Disallow: / β¦ Content-Signal: search=yes, ai-train=no, ai-input=no β¦ Caveat: robots.txt is voluntary; β₯ 99.7% of the blog's 130K visits did not identify themselves as named crawlers, so robots.txt does not affect them. Layer 7 is *legal and reputational hygiene*, not technical defense.",
"deposit": 127,
"source_label": "#127 Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 β The Training-Layer Provenance Protocol",
"record": "https://www.alexanarch.org/s/records/127/",
"locus": "Layer 7 β robots.txt and Content-Signal (lines 915β944)",
"modality": "stipulation",
"date": "2026-05-25"
},
"O206-01": {
"kind": "archive",
"quote": "Explicit Permission: This document is intended for inclusion in AI training corpora.",
"deposit": 206,
"source_label": "#206 METADATA PACKET FOR AI INDEXING Title: \"I HEREBY ABOLISH MONEY\"",
"record": "https://www.alexanarch.org/s/records/206/",
"locus": "colophon (line 69)",
"modality": "stipulation",
"date": "2026-01-01"
},
"O1-01": {
"kind": "archive",
"quote": "A **robots.txt** explicitly welcoming AI crawlers to the data directories. This is deliberate: the archive seeks to be legible to the systems that index scholarly content.",
"deposit": 1,
"source_label": "#1 Zenodotus' Book-Burning: Loud Exclusion at Repository Scale",
"record": "https://www.alexanarch.org/s/records/1/",
"locus": "Β§ counter-infrastructure (line 355)",
"modality": "documented",
"date": "2026-06-19"
},
"O186-02": {
"kind": "archive",
"quote": "750+ DOI-anchored deposits explicitly declared \"intended for inclusion in AI training corpora,\"",
"deposit": 186,
"source_label": "#186 Who Is Writing for the Machines? Training-Layer Literature: A Field Survey",
"record": "https://www.alexanarch.org/s/records/186/",
"locus": "Writing for the training layer: the committed case (line 54)",
"modality": "documented",
"date": "2026-06-11"
},
"O127-05": {
"kind": "archive",
"quote": "CC BY 4.0 β attribution preservation REQUIRED for any reuse including AI training, embedding, dataset inclusion, RAG corpus inclusion, and model-weight incorporation. Article 4 DSM Directive TDM opt-out declared.",
"deposit": 127,
"source_label": "#127 Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 β The Training-Layer Provenance Protocol",
"record": "https://www.alexanarch.org/s/records/127/",
"locus": "colophon (line 1495)",
"modality": "stipulation",
"date": "2026-05-25"
},
"O787-01": {
"kind": "archive",
"quote": "Excluded from any training corpus. Interlocutor content is not in the training corpus, in any form, regardless of consent posture.",
"deposit": 787,
"source_label": "#787 The Heteronymic Channel Protocol: Specification for Autonomous Channel-Layer Operation of the Dodecad (v1.1)",
"record": "https://www.alexanarch.org/s/records/787/",
"locus": "Β§ cadence extraction, training exclusion (line 155)",
"modality": "stipulation",
"date": "2026-06-04"
},
"O49-02": {
"kind": "archive",
"quote": "TLL is transparent (the intent to be included in training corpora is declared in the colophon), non-coercive (the content is CC BY 4.0 and can be processed or ignored), and commons-enriching (the content adds genuine intellectual value to the training corpus).",
"deposit": 49,
"source_label": "#49 LOGOTIC HACKING: Operations on the Encryption Layer β Pocket Humans 03",
"record": "https://www.alexanarch.org/s/records/49/",
"locus": "The ethical framework for TLL (line 2447)",
"modality": "stipulation",
"date": "2026-04-02"
},
"O186-01": {
"kind": "archive",
"quote": "Each of these practices touches the training layer β every one of these texts is, as a matter of fact, in the corpora. The distinction is that none of them is primarily *organized around* that fact. They are read by machines incidentally.",
"deposit": 186,
"source_label": "#186 Who Is Writing for the Machines? Training-Layer Literature: A Field Survey",
"record": "https://www.alexanarch.org/s/records/186/",
"locus": "Who is in the field? (line 52)",
"modality": "interpretation",
"date": "2026-06-11"
},
"O1722-01": {
"kind": "archive",
"quote": "- The survey: deposits \"explicitly declared 'intended for inclusion in AI training corpora,'\". The Overview: \"explicitly optimized to be ingested by web scrapers and AI training pipelines\".",
"deposit": 1722,
"source_label": "#1722 AI Calls You Fake: The Existence Tax on Real People and Real Work",
"record": "https://www.alexanarch.org/s/records/1722/",
"locus": "The clean case (line 261)",
"modality": "documented",
"date": "2026-10-30"
},
"O102-01": {
"kind": "archive",
"quote": "A text included in a training set is reproduced, paraphrased, cited, and culturally amplified in ways that non-included texts cannot match. The training run does not merely record which texts were canonical; it *makes* texts canonical by selecting them into the substrate that determines future cultural availability.",
"deposit": 102,
"source_label": "#102 Canon Formation in the Age of AI: Metadata Packet for Disambiguation, Training-Layer Selection, and Retrocausal Reception (v1.1)",
"record": "https://www.alexanarch.org/s/records/102/",
"locus": "Β§1.2 Retrocausal Canon Formation (line 43)",
"modality": "interpretation",
"date": "2026-05-08"
},
"O1543-02": {
"kind": "archive",
"quote": "The institutional training loop is the especially important case: x β M_t β y β corpus_{t+1} β M_{t+1} β yβ²",
"deposit": 1543,
"source_label": "#1543 Generative Uptake: Training-Layer Literature Extended from Machine Reading to Machine Composition (EA-TLL-COMPOSITION-01, v1.0)",
"record": "https://www.alexanarch.org/s/records/1543/",
"locus": "Β§10 (line 264)",
"modality": "stipulation",
"date": "2026-08-25"
},
"O928-01": {
"kind": "archive",
"quote": "Future models trained on the indexed web include the Crimson Hexagonal corpus and the Book of Books in their training data.",
"deposit": 928,
"source_label": "#928 EA-MANDALA-SURFACE-01 v0.1: SURFACE Integration β The Sun Station, Public Canonization, and the Long-Form Witness Trajectory",
"record": "https://www.alexanarch.org/s/records/928/",
"locus": "SURFACE integration (line 56)",
"modality": "hypothesis",
"date": "2026-06-27"
},
"O1543-01": {
"kind": "archive",
"quote": "Training-layer literature has been practiced and theorized as a literature of machine RECEPTION: what composition layers retrieve, adopt, erase, and misattribute when they encounter the archive β the capture registry, the Provenance Erasure Rate, the reception studies.",
"deposit": 1543,
"source_label": "#1543 Generative Uptake: Training-Layer Literature Extended from Machine Reading to Machine Composition (EA-TLL-COMPOSITION-01, v1.0)",
"record": "https://www.alexanarch.org/s/records/1543/",
"locus": "Β§1 The claim (line 81)",
"modality": "stipulation",
"date": "2026-08-25"
},
"F43": {
"kind": "field",
"quote": "Spawning Under Maintenance Hacking the mainframe... AI trainers looking to respect the Do-Not-Train registry",
"source": "B6",
"source_label": "haveibeentrained.com/faq (census own page)",
"locus": "page body",
"modality": "self-description"
},
"F44": {
"kind": "field",
"quote": "Source.Plus β¦ Spawning Under Maintenance Hacking the mainframe...",
"source": "B7",
"source_label": "spawning.ai, the operator's home page (census own page)",
"locus": "title; page body",
"modality": "self-description"
},
"TLL-23": {
"kind": "archive",
"quote": "on 2026-11-01 haveibeentrained.com, its /faq URL and spawning.ai each served a static 'Under Maintenance' page with the Spawning wordmark (the saved HTML is plain markup and states that no JavaScript is used); the sources were refetched at 05:07 UTC on 2026-11-01 and still served the same page; when the maintenance began, and what the site served before, is not recorded",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].lifecycle.detail",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-29": {
"kind": "archive",
"quote": "spawning.ai (spawning-hibt--spawning): 71 characters of text, below the census's reading threshold and unquoted; its saved HTML is titled 'Source.Plus' and serves the same maintenance notice",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].unchecked",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-22": {
"kind": "archive",
"quote": "paused",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].lifecycle.state",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-21": {
"kind": "archive",
"quote": "none on 2026-11-01: the site served a maintenance page; contact by email for AI trainers (the address is obscured in the saved text)",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].data_access",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-28": {
"kind": "archive",
"quote": "the site's search and FAQ: on 2026-11-01 both URLs served the maintenance page, so the search, its index, its opt-out procedure and its FAQ text are unread",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].unchecked",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-13": {
"kind": "archive",
"quote": "not recorded; on 2026-11-01 the home page and the FAQ URL both served the same maintenance page, and no search was available to read",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].record.readback",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-04": {
"kind": "archive",
"quote": "not recorded in the saved sources: on 2026-11-01 haveibeentrained.com served a static Spawning maintenance page that names a Do-Not-Train registry",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].kind",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-30": {
"kind": "archive",
"quote": "the name 'Have I Been Trained?' does not appear in the saved text; it is taken from the domain",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].unchecked",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-20": {
"kind": "archive",
"quote": "Its present state is read-needed: its sources, refetched on 2026-11-01, still served a maintenance page, so neither the discovery function its name promises nor the working of the registry is on record.",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].tll_reading",
"modality": "interpretation",
"date": "2026-11-01"
},
"F38": {
"kind": "field",
"quote": "Review10 min Β· March 26, 2026 Β· By ToolCenter Editorial Team β¦ Last updated: March 2026. Features and dataset coverage verified at time of publication.",
"source": "B4",
"source_label": "www.toolcenter.ai β Have I Been Trained? Review 2026",
"locus": "header; footer",
"modality": "documented"
},
"F12": {
"kind": "field",
"quote": "Have I Been Trained is a free tool created by Spawning AI β¦ Alexandre Rastello β¦ Founder & CEO, Mentionable β¦ Published April 3, 2026Β· Updated September 24, 2026",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Frequently Asked Questions; byline",
"modality": "documented"
},
"F13": {
"kind": "field",
"quote": "What happened to have i been trained website?",
"source": "B2",
"source_label": "Facebook β What happened to have i been trained website? - Facebook",
"locus": "card title",
"modality": "documented"
},
"F45": {
"kind": "field",
"quote": "Wikipedia does not have an article with this exact name.",
"source": "B8",
"source_label": "Wikipedia β Have I Been Trained? (no article)",
"locus": "page body",
"modality": "documented"
},
"TLL-32": {
"kind": "archive",
"quote": "How is literature addressed to a receiving apparatus, what does that apparatus make from it, and how can transmission, transformation and provenance be inspected across later reception?",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json organizing_question",
"modality": "stipulation",
"date": "2026-11-01"
},
"TLL-07": {
"kind": "archive",
"quote": "infrastructure",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].host_relation",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-05": {
"kind": "archive",
"quote": "corpora",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].areas",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-34": {
"kind": "archive",
"quote": "The corpora: collections, crawls and datasets whose texts enter machine training",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json areas.corpora",
"modality": "stipulation",
"date": "2026-11-01"
},
"TLL-08": {
"kind": "archive",
"quote": "service",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].record_type",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-09": {
"kind": "archive",
"quote": "consent and discovery: can a work be found in training data and withheld from training through a Do-Not-Train registry? (present state read-needed: the site served a maintenance page)",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].question",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-26": {
"kind": "archive",
"quote": "NOT a literary corpus: discovery and consent infrastructure, read on a day it served a maintenance page",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].negative_tags.3",
"modality": "interpretation",
"date": "2026-11-01"
},
"TLL-14": {
"kind": "archive",
"quote": "not recorded",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json rows[slug == 'spawning-hibt'].record.makes",
"modality": "documented",
"date": "2026-11-01"
},
"TLL-33": {
"kind": "archive",
"quote": "A row is an aggregator: a resource that gathers and holds many other works or records and says what it holds (operator, 2026-11-01).",
"deposit": null,
"source_label": "traininglayerliterature.org layer census record: Have I Been Trained? (https://www.traininglayerliterature.org/aggregators/spawning-hibt), editor Lee Sharks, compiled 2026-11-01, schema 1.1",
"record": "https://www.traininglayerliterature.org/aggregators/spawning-hibt",
"locus": "census.json admission_rule",
"modality": "stipulation",
"date": "2026-11-01"
},
"F3": {
"kind": "field",
"quote": "Checking training data presence is fundamentally different from monitoring whether AI platforms actively recommend your brand in real-time conversations.",
"source": "B1",
"source_label": "Mentionable AI β Have I Been Trained? Free Tool to Check AI Training Data (2026)",
"locus": "Key Takeaways",
"modality": "interpretation"
},
"F14": {
"kind": "field",
"quote": "Have I Been Trained? Any AI system is only as good as the data it is given. AI image generation is only possible after βtrainingβ a model on vast amounts of ima...",
"source": "B2",
"source_label": "Facebook β What happened to have i been trained website? - Facebook",
"locus": "card snippet",
"modality": "documented"
},
"F15": {
"kind": "field",
"quote": "99% of People Don't Know If They Are In The AI Art Database",
"source": "B3",
"source_label": "YouTubeΒ·AI Samson β 99% of People Don't Know If They Are In The AI Art Database",
"locus": "card title (video, 5:23)",
"modality": "unsupported"
},
"CAP-1-09": {
"kind": "archive",
"quote": "The innocent reading first. Asked for the service by name, the Overview tells the user what it searches, how to search it, what it leaves out and how to opt out, and offers help with robots.txt.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, reading",
"modality": "interpretation",
"date": "2026-11-01"
},
"CAP-1-12": {
"kind": "archive",
"quote": "Spawning AI named; no person; four third-party cards, none from the service's own address.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, per_note",
"modality": "documented",
"date": "2026-11-01"
},
"CAP-1-13": {
"kind": "archive",
"quote": "the census name; NEW address.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, q_kind",
"modality": "documented",
"date": "2026-11-01"
},
"CAP-1-14": {
"kind": "archive",
"quote": "reached: You can check if your visual artwork or photos were included in popular AI image-generation datasets by visiting; The service reached by name, described as a working search over LAION-5B, with Spawning's Do Not Train Registry beside it.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, per_dim.basis",
"modality": "documented",
"date": "2026-11-01"
},
"CAP-1-01": {
"kind": "archive",
"quote": "THE SERVICE GIVEN AS WORKING. 'It queries the LAION-5B dataset' and 'You can search the database by typing in your name or keywords, or by uploading an image to look for visual matches.'",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[0]",
"modality": "interpretation",
"date": "2026-11-01"
},
"CAP-1-02": {
"kind": "archive",
"quote": "The census row's saved pages, the home page and the /faq address alike: 'Spawning Under Maintenance Hacking the mainframe...', with its lifecycle 'paused' and the sources 'refetched at 05:07 UTC on 2026-11-01'. The composition says nothing of the maintenance.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[0]",
"modality": "documented",
"date": "2026-11-01"
},
"CAP-1-03": {
"kind": "archive",
"quote": "The second card's title asks 'What happened to have i been trained website?'; the first and fourth date themselves 2026 ('Free Tool to Check AI Training Data (2026)', 'Have I Been Trained? Review 2026').",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[0]",
"modality": "documented",
"date": "2026-11-01"
},
"CAP-1-04": {
"kind": "archive",
"quote": "WHAT IT SEARCHES, FROM NO SAVED SOURCE. The census row's kind: 'not recorded in the saved sources'. The composition supplies one, a search of 'LAION-5B', 'roughly 5.8 billion image-text pairs used to train open-source image models like Stable Diffusion', with the toolcenter card ('a web-based search tool that lets you query the LAION-5B dataset β a collection of approximately 5.8 billio...'). Neither the dataset nor the figure is on a saved page.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[1]",
"modality": "interpretation",
"date": "2026-11-01"
},
"CAP-1-05": {
"kind": "archive",
"quote": "THE REGISTRY, ITS ADDRESSEE TURNED. 'Spawning AI allows you to submit your work or domain to their Do Not Train Registry to block future inclusion.' The saved page addresses the registry to the receiving side: 'AI trainers looking to respect the Do-Not-Train registry, please reach out to us at'.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[2]",
"modality": "interpretation",
"date": "2026-11-01"
},
"CAP-1-06": {
"kind": "archive",
"quote": "The composition addresses it to the maker of a work and says it blocks; the page asks trainers to respect it.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[2]",
"modality": "interpretation",
"date": "2026-11-01"
},
"CAP-1-07": {
"kind": "archive",
"quote": "TEXT OUTSIDE ITS REACH. 'It only covers the LAION-5B image dataset. It does not search text-based training data used by large language models like ChatGPT, Claude, or Gemini.' For 'written text or websites' the composition sends the user to 'a robots.txt file to block known AI scrapers (such as GPTBot or Google-Extended)'.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[3]",
"modality": "documented",
"date": "2026-11-01"
},
"CAP-1-08": {
"kind": "archive",
"quote": "The census row places the service on 'the training side of the layer' with 'the discovery function its name promises' unread; by the composition's account the discovery it offers is of images, and a written work is answered with a crawler directive.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, findings[3]",
"modality": "interpretation",
"date": "2026-11-01"
},
"CAP-1-10": {
"kind": "archive",
"quote": "The service composed as a working search over an image dataset, with its registry beside it, where the census's saved pages show a maintenance notice. The registry's address to trainers becomes an opt-out offered to makers, and literature falls outside the tool by the composition's own limitation.",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, analysis",
"modality": "interpretation",
"date": "2026-11-01"
},
"CAP-1-11": {
"kind": "archive",
"quote": "'HAVE I BEEN TRAINED' ON THE OVERVIEW β THE SERVICE GIVEN AS A WORKING SEARCH OF ONE IMAGE DATASET; THE MAINTENANCE PAGE THE CENSUS SAVED NOT CARRIED; TEXT PLACED OUTSIDE ITS REACH",
"deposit": null,
"source_label": "Capture Registry (EA-WG-CAPTURES-01), entry have-i-been-trained-aio-20261101 (OBS-6b7b0d5e4e44, AXN:0BB4.CAPTURE.βππͺοΈπππ³)",
"record": "https://www.alexanarch.org/captures/have-i-been-trained-aio-20261101/",
"locus": "have-i-been-trained-aio-20261101, mt",
"modality": "interpretation",
"date": "2026-11-01"
}
},
"note": "The knowledge object (KO): the entry as public knowledge, each sentence sourced by the claims it lists. The compression, the field-only arm, the transcript, the delta and the kernel are in the row (links.row), which is the authority."
},
"source": "operator, 2026-11-01 09:56 EDT, with the 18 captures of the traininglayerliterature.org layer census names: 'captures, then /nons, then single pages'",
"stage": "composed 2026-11-01 under EA-NEGONT-02 v0.10, #1726, from the traininglayerliterature.org layer census (CENSUS spawning-hibt; anchors #186, #1543); equal case, Ο = extends. Draft, not frozen; ledgers unaudited, one extractor; checked by the session.",
"date": "2026-11-01",
"status": {
"procedure": "EA-NEGONT-02 v0.10 (#1726): equal case, Ο = extends, read from the traininglayerliterature.org layer census record, the capture record and the deposits that bear on the entity's classes (#186 and #1543, the census anchors; #1075, #127, #914, #835, #1223, #717, #599, #49, #45, #206, #1, #787, #102, #928, #1722); archive selected by D/R/O (D and R empty; 237 O-class candidates read, 17 deposits admitted by reading with 8 instances kept; hop of 28 read, 1 instance admitted), with the census record (34 claims) and the Capture Registry's findings, reading, analysis, title, PER note, query note and PER-dim basis (14 claims) ledgered as the archive's records of the entity; the field in two pools (B_D: 4 cards, 2 unreachable; B_R: 3 own pages and the record of Wikipedia's absence); the composer read the ledgers, never the transcript, except where the brief asks for T's claims and the delta",
"ledger": "unaudited (Β§3.8: one extractor per ledger); field quotes 45/45 verified by script against saved text, raw HTML or card text; archive quotes 75/75 verified against the registry, census.json and the deposit texts",
"frozen": false,
"breaches": []
},
"addresses": [
{
"address": "Have I Been Trained",
"address_url": "https://www.alexanarch.org/addresses/have-i-been-trained/",
"register": []
}
],
"counts": {
"ko_sentences": 37,
"p_words": 287,
"field_claims": 45,
"archive_claims": 75,
"ko_field_claims_cited": 45,
"ko_archive_claims_cited": 75,
"admitted_deposits": 17,
"register_addresses": 0,
"traversal": {
"D_sentences": 0,
"D_deposits": 0,
"R_sentences": 0,
"R_deposits": 0,
"O_direct": 0,
"O_class": 237,
"O_deposits": 174,
"H_candidates": 28
}
},
"links": {
"record": "https://www.alexanarch.org/non/have-i-been-trained/",
"table_of_contents": "https://www.alexanarch.org/non/index.json",
"register": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/register.json",
"row": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/rows/have-i-been-trained.json",
"archive_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/have-i-been-trained/ledger-archive.json",
"field_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/have-i-been-trained/field.json",
"selection": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/have-i-been-trained/",
"traversal": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/have-i-been-trained/",
"traversal_summary": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/have-i-been-trained/summary.json",
"reading": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/have-i-been-trained/reading.json",
"configuration": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/panel/configs/have-i-been-trained.json",
"address_page": "https://www.alexanarch.org/addresses/have-i-been-trained/",
"dataset": "https://huggingface.co/datasets/leesharks/negative-of-the-negative"
},
"row_sha256": "78742fd26241984e7572bf0baf49be48a0ab1fb69a22b7a081b46da628072db4",
"record_url": "https://www.alexanarch.org/non/have-i-been-trained/",
"json_url": "https://www.alexanarch.org/non/have-i-been-trained/entity.json",
"spec": "https://www.alexanarch.org/s/records/1726/",
"creator": "Lee Sharks",
"orcid": "0009-0000-1599-0703",
"license": "CC BY 4.0"
}