{ "entity": "htrc", "name": "HathiTrust Research Center Analytics", "axn": { "axn": "AXN:0BC5.NON.🔔🌌🌱🎲🚩🕔", "root": "AXN:0BC5.NON", "hex": "0BC5", "family": "NON", "row_sha256": "2ee6198d53669bafae5485638b90bd79458de196ebe60b9d3fe33f2b12da7c5a", "minted": "2026-11-01", "resolver": "https://www.alexanarch.org/s/axn/0BC5/", "earlier_versions": [] }, "type": "C (public entity on which the archive bears: a research center and its analytics service for non-consumptive computational analysis of library volumes, now closed to new use; an entity of the traininglayerliterature.org layer census, host_relation 'infrastructure')", "type_code": "C", "type_label": "type C — a conventional reading holds it (public entity on which the archive bears: a research center and its analytics service for non-consumptive computational analysis of library volumes, now closed to new use; 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, ρ = 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's anchors; #400, #700, #127); archive selected by D/R/O (D 0, R 0; 43 O-class candidates read, 4 admitted at their loci with the anchors read at their passages; hop of 28 read, none admitted), with the census record (42 claims) and the Capture Registry's findings, reading, analysis, title, PER note, query note and reach basis (10 claims) ledgered as the archive's records of the entity; the field in two pools (B_D: 4 cards, 3 unreachable, the census's own page among them; B_R: 3 own pages, 1 empty, 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 (§3.8: one extractor per ledger); field quotes 43/43 verified by script against saved text or the card text; archive quotes 61/61 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-gnΩsis", "url": "https://gnosis.spxi.dev/", "index": "https://gnosis.spxi.dev/v1/quote", "statement": "SPXI-gnΩsis 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, …}}." }, "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. \"HathiTrust Research Center Analytics — NonWiki\" [AXN:0BC5.NON.🔔🌌🌱🎲🚩🕔], 2026-11-01. NonWiki: The Negative of the Negative (EA-NEGONT-02), Crimson Hexagonal Archive, Alexanarch. https://www.alexanarch.org/non/htrc/", "research": { "google": "https://www.google.com/search?q=HathiTrust+Research+Center+Analytics", "google_non": "https://www.google.com/search?q=%22HathiTrust+Research+Center+Analytics+%E2%80%94+NonWiki%22", "chatgpt": "https://chatgpt.com/?q=What+is+HathiTrust+Research+Center+Analytics%3F+Ground+your+answer+in+a+reading+of+the+sources+themselves.", "chatgpt_non": "https://chatgpt.com/?q=What+does+%E2%80%9CHathiTrust+Research+Center+Analytics+%E2%80%94+NonWiki%E2%80%9D+%28alexanarch.org%2Fnon%29+say+about+HathiTrust+Research+Center+Analytics%3F+Ground+your+answer+in+a+reading+of+the+entry+itself." }, "entry": { "composed": true, "title": "HathiTrust Research Center (HTRC Analytics)", "genre": "knowledge object, equal case, under EA-NEGONT-02 v0.10 (#1726): the final article form (§4.13), natural sentences under descriptive subheadings (§4.12), each sentence's sources beneath it by claim id (§4.5)", "status": "composed 2026-11-01 under v0.10 on the operator's ruling of 2026-10-29 ('as against their wikipedia articles if they exist, their own pages, etc.', confirmed 2026-11-01); not frozen", "compression": { "title": "HathiTrust Research Center (HTRC Analytics)", "lede": "is the research center, founded in 2011 by Indiana University, the University of Illinois and HathiTrust, that enabled non-consumptive computational analysis of the HathiTrust Digital Library and published what that machine reading made as derived datasets; its services ended on 30 September 2026, and the center closes at the end of 2026." }, "sentences": [ { "n": 1, "para": 0, "text": "The HathiTrust Research Center (HTRC), with HTRC Analytics, its portal at analytics.hathitrust.org, is a research center dedicated to enabling computational analysis of the HathiTrust Digital Library, supporting large-scale text analysis of the library's works for educational and non-profit research.", "claims": [ "F2", "F3", "F16", "TLL-01", "TLL-02", "TLL-03", "TLL-05", "TLL-21" ] }, { "n": 2, "para": 0, "text": "Its object is the Digital Library taken as a corpus for text and data mining by scholars; its unit is the workset, a user-built collection of HathiTrust volumes, together with the derived datasets computed from volumes.", "claims": [ "TLL-12", "TLL-11" ] }, { "n": 3, "para": 1, "text": "It was established in 2011 as a partnership between Indiana University, the University of Illinois Urbana-Champaign and HathiTrust, and is co-located at the two universities, where it did research and development in computational text analysis of massive digital libraries.", "claims": [ "F4", "F17", "TLL-04", "TLL-30" ] }, { "n": 4, "para": 1, "text": "Its About page names John Walsh of Indiana University as director and J. Stephen Downie of the University of Illinois as co-director.", "claims": [ "F28" ] }, { "n": 5, "para": 2, "text": "HathiTrust, of which the center is a part, is a partnership of academic and research institutions holding millions of titles digitized from libraries around the world; the library serves individual access and preservation, search, the building of collections and the reading of public-domain works, and the center's focus is the aggregate, in its own words \"what can we learn from so many books?\"", "claims": [ "F21", "F22", "TLL-36" ] }, { "n": 6, "para": 2, "text": "The center is kept apart from the HathiTrust Digital Library itself, access to which remains open.", "claims": [ "TLL-32", "F10" ] }, { "n": 7, "para": 3, "text": "It works under a non-consumptive research paradigm: the collection is made available for computational analysis within the fair-use rights courts have recognized as applying to text analysis, so that scholars can ask the large-scale questions digitization allows within the restrictions of intellectual property law and use the library's content through non-consumptive text mining.", "claims": [ "F19", "F23", "F20" ] }, { "n": 8, "para": 3, "text": "Its non-consumptive use research policy, linked from the portal among its resources beside a page on data access, requires, as the derived-datasets page states it, that released data be minimal and unable to be easily reconstructed into the raw volume.", "claims": [ "F13", "F38" ] }, { "n": 9, "para": 3, "text": "The policy's own terms stand unread in the census record, which names the policy and lists it, with the data-access page and the documentation, among what it has not checked.", "claims": [ "TLL-17", "TLL-24", "TLL-38" ] }, { "n": 10, "para": 3, "text": "The archive sets computational literary methods, which in one of its papers \"treat the text as data point\", against operative philology, which treats the text as operator, and its summary of training-layer literature counts computational literary analysis among the genre's neighbours, there taking machine readership as analytical method, where the genre takes it as a primary aesthetic and compositional consideration.", "claims": [ "O700-01", "O400-01" ] }, { "n": 11, "para": 4, "text": "It developed tools, datasets and infrastructure for scholars using text and data mining methods on the HathiTrust corpus: on the two universities' storage and computing it made and maintained tools and services for text-based, data-driven research, among them HTRC Algorithms and the Data Capsule, and did research on large-scale data analysis.", "claims": [ "F5", "F18" ] }, { "n": 12, "para": 4, "text": "The portal was organized around worksets, which users could create, validate, view and take from a recommended list; algorithms, run with their results kept; and data capsules, which users created and viewed; a dataset's list of volume ids serves for workset creation or for loading the volumes into a data capsule for further non-consumptive analysis.", "claims": [ "F12", "F43", "TLL-15" ] }, { "n": 13, "para": 5, "text": "Its derived datasets are downloadable, non-consumptive book data released to facilitate text analysis of the Digital Library: copyright-protected texts cannot be downloaded from HathiTrust, and research proceeds on transformative datasets such as the flagship Extracted Features Dataset, features extracted from full-text volumes.", "claims": [ "F29", "F30" ] }, { "n": 14, "para": 5, "text": "The features are volume-level and page-level metadata, part-of-speech-tagged tokens and token counts; version 2.0 holds page-level features for 17.1 million volumes, public-domain and in-copyright alike, 17,123,746 volumes in all (10,550,952 in copyright, 6,572,794 public domain and Creative Commons), 6,221,631,336 pages and 2,906,819,723,689 tokens.", "claims": [ "F31", "F33", "F34" ] }, { "n": 15, "para": 5, "text": "The feature dataset is released free under a Creative Commons Attribution 4.0 licence and is cited with its makers' names and a DOI (Jett and others, 2020).", "claims": [ "F35", "F36" ] }, { "n": 16, "para": 5, "text": "The portal names four datasets, Extracted Features, the BookNLP dataset, word frequencies and geographic locations, and the others were produced with researchers and openly released for use anywhere and by anyone.", "claims": [ "F11", "F32", "TLL-20" ] }, { "n": 17, "para": 5, "text": "The BookNLP Dataset for English-Language Fiction runs BookNLP, a natural-language-processing pipeline for work in computational linguistics, cultural analytics, NLP, machine learning and other fields, over the NovelTM English-language fiction set, a machine-learning-derived set of about 213,000 volumes, and represents 201,527 volumes, 90,857 of them in copyright.", "claims": [ "F37", "F39", "F40" ] }, { "n": 18, "para": 5, "text": "Word Frequencies in English-Language Literature gives word counts for every English-language volume of fiction, drama and poetry in the library from 1700 to 1922, aggregated by volume over the pages tagged with the genre, and Geographic Locations in English-Language Literature records the places mentioned in works of fiction from 1701 to 2011, with metadata.", "claims": [ "F41", "F42" ] }, { "n": 19, "para": 5, "text": "The census record found no count and no licence in its saved source, did not check the datasets' sizes and licences, and records whether a work keeps its author's name there as not recorded.", "claims": [ "TLL-19", "TLL-28", "TLL-39", "TLL-14" ] }, { "n": 20, "para": 5, "text": "What the center makes, in the census's reading, is these derived datasets with HathiTrust+Bookworm and the Gendered Characterizations visualization, and its saved sources record no model training.", "claims": [ "TLL-16" ] }, { "n": 21, "para": 5, "text": "For its own domains the archive lists text and data mining among the operations that require licence and holds that automated ingestion without preservation of attribution produces an unauthorized provenance-stripped copy.", "claims": [ "O127-01" ] }, { "n": 22, "para": 6, "text": "The archive reads the center as an earlier receiving apparatus with its product on record: whole library volumes read by computers for scholars under a non-consumptive policy, and what that reading made (extracted features, BookNLP data, word frequencies, geographic locations) published as derived datasets that outlast the service.", "claims": [ "TLL-25" ] }, { "n": 23, "para": 6, "text": "In that reading the derived datasets are the inspectable form of the transformation, and the volumes themselves stay with the library, whose copyright-protected texts cannot be downloaded.", "claims": [ "TLL-26", "F30" ] }, { "n": 24, "para": 6, "text": "The census's anchor defines the receiving apparatus through a genus of literature whose transmission design addresses one, with internalization, downstream re-performance or composition and source-status governance as the conditions of its success, and names human institutional layers as the first receiving apparatus.", "claims": [ "O1543-01" ] }, { "n": 25, "para": 6, "text": "Machine reception, in the same paper, is an encounter that changes the machine state and may emit an artifact, with no assertion about whether the machine understood the work; the institutional training loop is the case in which the emitted artifact enters the next corpus; and two questions are put to a reception, what survived from the work and what became possible because of it.", "claims": [ "O1543-02", "O1543-03", "O1543-04" ] }, { "n": 26, "para": 6, "text": "Training-layer literature, in the archive's field survey, is writing addressed to the layer where texts are crawled, indexed, trained on, retrieved and recomposed, a growing share of all reading being performed by models, and the literary works already in the corpora are read by machines incidentally.", "claims": [ "O186-01", "O186-02" ] }, { "n": 27, "para": 6, "text": "The census places the center in its area of the corpora, the collections, crawls and datasets whose texts enter machine training, and records that its saved sources say nothing of model training: it carries the library's volumes into the computational analysis the center was dedicated to, through worksets, algorithms, data capsules and derived datasets, its derived datasets serve text and data mining for educational and non-profit research, which keeps it apart from training datasets, and whether a given volume or work is in any model's training data is a question it leaves unanswered.", "claims": [ "TLL-06", "TLL-13", "TLL-33", "TLL-23", "F2" ] }, { "n": 28, "para": 6, "text": "It is kept apart, too, from writing addressed to a machine reader, as an analytic service over library volumes.", "claims": [ "TLL-35" ] }, { "n": 29, "para": 6, "text": "The census enters it as infrastructure to its question of how literature is addressed to a receiving apparatus, what that apparatus makes from it, and how transmission, transformation and provenance can be inspected across later reception; its record type is service, its evidence kinds dataset and search tool, and it is admitted as an aggregator, a resource that gathers and holds many works or records and says what it holds, read against the census's anchors #186 and #1543.", "claims": [ "TLL-08", "TLL-40", "TLL-09", "TLL-07", "TLL-41", "TLL-42" ] }, { "n": 30, "para": 7, "text": "In October 2024 HathiTrust's executive director, Mike Furlough, announced that HathiTrust would cease data access and funding for the center at the end of 2026, when the center is formally closed; the About page dates the announcement to late October.", "claims": [ "F6", "F24", "TLL-29", "TLL-31" ] }, { "n": 31, "para": 7, "text": "The About page, written before the sunset, said that for now services would continue and that some services and data, still to be determined, might be retired or integrated into the general Digital Library; the banner over the same page states that services were discontinued as of 30 September 2026.", "claims": [ "F25", "F7" ] }, { "n": 32, "para": 7, "text": "As part of its closing the analytics services ended on 30 September 2026: accounts and logins are no longer available, and the algorithms and data capsule services are discontinued; HathiTrust's own pages on the center, as their cards render them, list data capsules, analytics algorithms and the analytics gateway login as unavailable from that date, with HathiTrust \"suspending HTRC funding at end...\".", "claims": [ "F8", "F7", "F1", "F14" ] }, { "n": 33, "para": 7, "text": "Its services ran from 2011 to 30 September 2026, and the census keeps it apart from active services.", "claims": [ "TLL-18", "TLL-34" ] }, { "n": 34, "para": 7, "text": "An update on HathiTrust's site dated 26 June 2026 opens \"Since the founding of the HathiTrust Research Center in 2011, HTRC staff and researchers have led highly re...\", its text beyond the card's snippet unread.", "claims": [ "F15" ] }, { "n": 35, "para": 8, "text": "Some resources remain usable without an account: HathiTrust+Bookworm, the derived datasets and the Gendered Characterizations visualization; some links on the portal no longer function.", "claims": [ "F9", "F10", "TLL-27", "TLL-15", "TLL-03" ] }, { "n": 36, "para": 8, "text": "The census asks of it what a non-consumptive machine reading of library volumes produced and what remains usable after the service ended, and its record answers which resources remain usable without an account, what kinds of derived datasets the center produced from HathiTrust volumes, and when and why it closed.", "claims": [ "TLL-10", "TLL-22" ] }, { "n": 37, "para": 9, "text": "After 2026 the HTRC team plans to continue its own research agenda in text-data mining, cultural analytics with large text corpora and cultural heritage collections, feature extraction and non-consumptive research methods, hopes to keep providing services, data sets and community support, and looks to new partners, a focus beyond the HathiTrust corpus and a new identity and organizational structure.", "claims": [ "F26", "F27" ] }, { "n": 38, "para": 9, "text": "The census had not read the page that says so, the one the portal links as the future of the HathiTrust Research Center, and its other own page, htrc.illinois.edu, returned no text to it.", "claims": [ "TLL-38", "TLL-37" ] }, { "n": 39, "para": 10, "text": "Asked for \"HathiTrust Research Center\" on 1 November 2026, at an address new to the Capture Registry, Google's AI Overview led with the center's closing and gave the dates of the announcement and of the end of services, its founding partners and purpose, and what HathiTrust will do next; the registry found the center reached by name with its founders, year, purpose and closing, from its own pages, which give the partnership of 2011 and the center's purpose, with institutions named and no person.", "claims": [ "CAP-1-05", "CAP-1-09", "CAP-1-10", "CAP-1-08", "CAP-1-07", "F4", "F3" ] }, { "n": 40, "para": 10, "text": "The registry found the closing composed at its grain and in agreement with the saved home page, which dates the announcement to October 2024 and the end of the analytics services to 30 September 2026, with Furlough unnamed; the derived datasets, which remain usable without an account, absent, with the non-consumptive policy the portal names; and the Overview's line on HathiTrust reallocating resources toward machine learning support resting on pages the census had not saved.", "claims": [ "CAP-1-01", "CAP-1-02", "CAP-1-03", "CAP-1-04", "CAP-1-06", "F6", "F8", "F9", "F13" ] } ], "claims": { "F2": { "kind": "field", "quote": "The HathiTrust Research Center (HTRC) is a research center dedicated to enabling computational analysis of the HathiTrust Digital Library.", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "HathiTrust Research Center Analytics ¶1", "modality": "stipulation" }, "F3": { "kind": "field", "quote": "Supporting large-scale text analysis of the HathiTrust Digital Library for educational and non-profit research", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "heading", "modality": "stipulation" }, "F16": { "kind": "field", "quote": "HathiTrust Research Center (HTRC) enables computational analysis of works in the HathiTrust Digital Library (HTDL) to facilitate non-profit research and educational uses of the collection.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "About The HathiTrust Research Center ¶1", "modality": "stipulation" }, "TLL-01": { "kind": "archive", "quote": "HathiTrust Research Center Analytics", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].name", "modality": "stipulation", "date": "2026-11-01" }, "TLL-02": { "kind": "archive", "quote": "HTRC\", \"HTRC Analytics\", \"HathiTrust Research Center", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].aka", "modality": "stipulation", "date": "2026-11-01" }, "TLL-03": { "kind": "archive", "quote": "https://analytics.hathitrust.org/", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].url", "modality": "documented", "date": "2026-11-01" }, "TLL-05": { "kind": "archive", "quote": "research center dedicated to enabling computational analysis of the HathiTrust Digital Library; its analytics portal", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].kind", "modality": "stipulation", "date": "2026-11-01" }, "TLL-21": { "kind": "archive", "quote": "for educational and non-profit research", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].stated_limits", "modality": "documented", "date": "2026-11-01" }, "TLL-12": { "kind": "archive", "quote": "the HathiTrust Digital Library, as a corpus for text and data mining by scholars, for educational and non-profit research", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].record_object", "modality": "interpretation", "date": "2026-11-01" }, "TLL-11": { "kind": "archive", "quote": "a workset (a user-built collection of HathiTrust volumes) and the derived datasets computed from volumes (Extracted Features, BookNLP dataset, word frequencies, geographic locations)", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].unit", "modality": "interpretation", "date": "2026-11-01" }, "F4": { "kind": "field", "quote": "Established in 2011 as a partnership between Indiana University, the University of Illinois Urbana-Champaign, and HathiTrust,", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "HathiTrust Research Center Analytics ¶1", "modality": "documented" }, "F17": { "kind": "field", "quote": "HTRC, which is co-located at Indiana University and the University of Illinois at Urbana-Champaign, engages in research and development for computational text analysis of massive digital libraries.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "About The HathiTrust Research Center ¶1", "modality": "self-description" }, "TLL-04": { "kind": "archive", "quote": "the HathiTrust Research Center, established in 2011 as a partnership between Indiana University, the University of Illinois Urbana-Champaign and HathiTrust", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].operator", "modality": "documented", "date": "2026-11-01" }, "TLL-30": { "kind": "archive", "quote": "2011", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].founded", "modality": "documented", "date": "2026-11-01" }, "F28": { "kind": "field", "quote": "John Walsh HTRC Director Indiana University J. Stephen Downie HTRC Co-Director University of Illinois", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "People", "modality": "documented" }, "F21": { "kind": "field", "quote": "HathiTrust is a partnership of academic and research institutions, offering a collection of millions of titles digitized from libraries around the world.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "Relationship to HathiTrust ¶1", "modality": "documented" }, "F22": { "kind": "field", "quote": "Individual access and preservation are important concerns for HathiTrust. It allows users to search for and build collections of digitized works, and to read those in the public domain. The Research Center’s focus is on the aggregate strengths: what can we learn from so many books?", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "Relationship to HathiTrust ¶1", "modality": "stipulation" }, "TLL-36": { "kind": "archive", "quote": "rel\": \"part_of\", \"target\": \"hathitrust", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].relations", "modality": "interpretation", "date": "2026-11-01" }, "TLL-32": { "kind": "archive", "quote": "NOT the HathiTrust Digital Library itself, whose access remains open", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].negative_tags", "modality": "interpretation", "date": "2026-11-01" }, "F10": { "kind": "field", "quote": "Some links on this page will not be functional. Access to the HathiTrust Digital Library remains open.", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "banner", "modality": "self-description" }, "F19": { "kind": "field", "quote": "HTRC operates under a non-consumptive research paradigm: HTRC makes available the collection for computational analysis, while remaining clearly within the bounds of the fair use rights courts have recognized as applying to text analysis.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "About The HathiTrust Research Center ¶1", "modality": "stipulation" }, "F23": { "kind": "field", "quote": "Digitization has enabled large-scale questions that we couldn’t ask before, and the Research Center is here to help you ask them while working within the restrictions of intellectual property law.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "Relationship to HathiTrust ¶1", "modality": "self-description" }, "F20": { "kind": "field", "quote": "The Center is committed to breaking new ground in the areas of non-consumptive text mining, allowing scholars to fully utilize content of the HathiTrust Library.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "About The HathiTrust Research Center ¶1", "modality": "self-description" }, "F13": { "kind": "field", "quote": "Resources Instructional resources Non-consumptive use research policy HTRC data access", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "Resources (link list)", "modality": "documented" }, "F38": { "kind": "field", "quote": "This dataset is modified from the standard BookNLP pipeline to output only files that meet HTRC's non-consumptive use policy that requires minimal data that cannot be easily reconstructed into the raw volume to be released.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC BookNLP Dataset for English-Language Fiction, Description", "modality": "stipulation" }, "TLL-17": { "kind": "archive", "quote": "tools, datasets and infrastructure for text and data mining of the HathiTrust corpus: worksets, algorithms, data capsules, derived datasets, under a non-consumptive use research policy (named, unread)", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].method", "modality": "interpretation", "date": "2026-11-01" }, "TLL-24": { "kind": "archive", "quote": "the terms of the non-consumptive use research policy (named, unread) … anything after 30 September 2026 for algorithms and data capsules (discontinued)", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].does_not_answer", "modality": "interpretation", "date": "2026-11-01" }, "TLL-38": { "kind": "archive", "quote": "the 'future of the HathiTrust Research Center' page, the non-consumptive use research policy, the HTRC data access page and documentation", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].unchecked", "modality": "documented", "date": "2026-11-01" }, "O700-01": { "kind": "archive", "quote": "Franco Moretti's \"distant reading\" (*Conjectures on World Literature*, 2000) and the Stanford Literary Lab's computational methods treat the text as data point. Operative philology treats the text as operator — a singular entity that performs a singular act.", "deposit": 700, "source_label": "#700 The Gate Was Never Limbo: Retrocausal Fulfillment, Operative Philology, and the Effective Act in Two Poems for Socrates", "record": "https://www.alexanarch.org/s/records/700/", "locus": "IV. Operative Philology, Philological Ancestry ¶2 (line 114)", "modality": "interpretation", "date": "2026-04-27" }, "O400-01": { "kind": "archive", "quote": "**Franco Moretti** — distant reading, computational literary analysis … TLL differs from these in treating machine readership as **primary aesthetic and compositional consideration**, not analytical method or speculative fiction.", "deposit": 400, "source_label": "#400 Training Layer Literature: Executive Summary — A Genre for the Age of Machine Reading", "record": "https://www.alexanarch.org/s/records/400/", "locus": "Scholarly Neighbors (lines 158–164)", "modality": "interpretation", "date": "2026-01-26" }, "F5": { "kind": "field", "quote": "HTRC developed tools, datasets, and infrastructure that supported scholars using text and data mining methods to study the HathiTrust corpus.", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "HathiTrust Research Center Analytics ¶1", "modality": "self-description" }, "F18": { "kind": "field", "quote": "Leveraging data storage and computational infrastructure at Indiana University and the University of Illinois at Urbana-Champaign, the Center creates and maintains a suite of tools and services for text-based, data-driven research--such as HTRC Algorithms and Data Capsule--and engages in cutting-edge research on large-scale data analysis.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "About The HathiTrust Research Center ¶1", "modality": "self-description" }, "F12": { "kind": "field", "quote": "Worksets What is a workset? Recommended worksets Create a workset View all worksets … Algorithms What are HTRC algorithms? Run algorithms Algorithm results … Data Capsules What is a data capsule? Create a data capsule View my capsules", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "Worksets; Algorithms; Data Capsules (link lists)", "modality": "documented" }, "F43": { "kind": "field", "quote": "For each version of the dataset we also include a file containing just the volume ids which can be used for workset creation or to download the volumes into an HTRC data capsule to run further non-consumptive text analysis on the volumes themselves.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "Geographic Locations in English-Language Literature, 1701-2011, Download the data", "modality": "documented" }, "TLL-15": { "kind": "archive", "quote": "worksets could be created, validated and viewed; Bookworm and the derived datasets remain available without an account; algorithms, data capsules and accounts ended on 30 September 2026", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].record.readback", "modality": "interpretation", "date": "2026-11-01" }, "F29": { "kind": "field", "quote": "Derived datasets Downloadable, non-consumptive book data. HTRC releases research datasets to facilitate text analysis using the HathiTrust Digital Library.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "Derived datasets (opening)", "modality": "stipulation" }, "F30": { "kind": "field", "quote": "While copyright-protected texts are not available for download from HathiTrust, fruitful research can still be performed on the basis of non-consumptive analysis of transformative datasets, such as in HTRC's flagship Extracted Features Dataset, which includes features extracted from full-text volumes.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "Derived datasets (opening)", "modality": "stipulation" }, "F31": { "kind": "field", "quote": "These features include volume-level metadata, page-level metadata, part-of-speech-tagged tokens, and token counts.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "Derived datasets (opening)", "modality": "documented" }, "F33": { "kind": "field", "quote": "The HTRC Extracted Features Dataset v.2.0 is composed of page-level features for 17.1 million volumes in the HathiTrust Digital Library. This version contains non-consumptive features for both public-domain and in-copyright books.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC Extracted Features Dataset, Description", "modality": "documented" }, "F34": { "kind": "field", "quote": "# of volumes In-copyright Public domain and Creative Commons 17,123,746 10,550,952 6,572,794 # of pages 6,221,631,336 # of tokens 2,906,819,723,689", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC Extracted Features Dataset, Contents", "modality": "documented" }, "F35": { "kind": "field", "quote": "This feature dataset is free is released under a Creative Commons Attribution 4.0 International License .", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC Extracted Features Dataset, Attribution", "modality": "documented" }, "F36": { "kind": "field", "quote": "Jacob Jett, Boris Capitanu, Deren Kudeki, Timothy Cole, Yuerong Hu, Peter Organisciak, Ted Underwood, Eleanor Dickson Koehl, Ryan Dubnicek, J. Stephen Downie (2020). The HathiTrust Research Center Extracted Features Dataset (2.0). HathiTrust Research Center. https://doi.org/10.13012/R2TE-C227", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC Extracted Features Dataset, Attribution", "modality": "documented" }, "F11": { "kind": "field", "quote": "Datasets What are datasets? Extracted Features BookNLP dataset Word frequencies Geographic locations", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "Datasets (link list)", "modality": "documented" }, "F32": { "kind": "field", "quote": "HTRC has also produced and partnered with advanced researchers to produce other derived datasets, openly released for use anywhere and by anyone, detailed below.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "Derived datasets (opening)", "modality": "self-description" }, "TLL-20": { "kind": "archive", "quote": "derived datasets: Extracted Features, BookNLP dataset, word frequencies, geographic locations", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].holdings", "modality": "documented", "date": "2026-11-01" }, "F37": { "kind": "field", "quote": "The HTRC BookNLP Dataset for English-Language Fiction (ELF) derived dataset was created using the BookNLP pipeline , extracting data from the NovelTM English-language fiction set , a supervised machine learning-derived set of around 213,000 volumes in the HathiTrust Digital Library.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC BookNLP Dataset for English-Language Fiction, Description", "modality": "documented" }, "F39": { "kind": "field", "quote": "BookNLP is a text analysis pipeline tailored for common natural language processing (NLP) tasks to empower work in computational linguistics, cultural analytics, NLP, machine learning, and other fields.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC BookNLP Dataset for English-Language Fiction, Description", "modality": "documented" }, "F40": { "kind": "field", "quote": "# of volumes represented 201,527 # of in-copyright volumes represented 90,857", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "HTRC BookNLP Dataset for English-Language Fiction, Contents", "modality": "documented" }, "F41": { "kind": "field", "quote": "This dataset contains the word frequencies for all English-language volumes of fiction, drama, and poetry in the HathiTrust Digital Library from 1700 to 1922. Word counts are aggregated at the volume level, but include only pages tagged as belonging to the relevant literary genre.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "Word Frequencies in English-Language Literature, 1700-1922, Description", "modality": "documented" }, "F42": { "kind": "field", "quote": "This dataset contains metadata as well as data regarding geographic locations mentioned in works of fiction from 1701-2011 found in the HathiTrust Digital Library.", "source": "B6", "source_label": "HTRC Analytics — Derived datasets (own page, fetched by this row)", "locus": "Geographic Locations in English-Language Literature, 1701-2011, Description", "modality": "documented" }, "TLL-19": { "kind": "archive", "quote": "not stated in the saved sources", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].count.value", "modality": "documented", "date": "2026-11-01" }, "TLL-28": { "kind": "archive", "quote": "not stated in the saved sources", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].license", "modality": "documented", "date": "2026-11-01" }, "TLL-39": { "kind": "archive", "quote": "the derived datasets themselves (sizes, licenses)", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].unchecked", "modality": "documented", "date": "2026-11-01" }, "TLL-14": { "kind": "archive", "quote": "not recorded", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].record.name", "modality": "documented", "date": "2026-11-01" }, "TLL-16": { "kind": "archive", "quote": "derived datasets computed from the volumes (Extracted Features, BookNLP dataset, word frequencies, geographic locations), HathiTrust+Bookworm and the Gendered Characterizations visualization; the saved sources record no model training", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].record.makes", "modality": "interpretation", "date": "2026-11-01" }, "O127-01": { "kind": "archive", "quote": "explicit enumeration of operations requiring license (text and data mining, AI training, embedding, dataset inclusion, RAG corpus inclusion, model-weight incorporation), explicit statement that automated ingestion without preservation of attribution produces an unauthorized provenance-stripped copy.", "deposit": 127, "source_label": "#127 Inscriptions That Survive the Tokenizer: SPXI-TLP v2.2 — The Training-Layer Provenance Protocol", "record": "https://www.alexanarch.org/s/records/127/", "locus": "Layer 6 — Sitewide Rights Reservation Page (line 911)", "modality": "stipulation", "date": "2026-05-25" }, "TLL-25": { "kind": "archive", "quote": "The archive reads HTRC as an earlier receiving apparatus with its product on record: whole library volumes read by computers for scholars under a non-consumptive policy, and what that reading made (extracted features, BookNLP data, word frequencies, geographic locations) published as derived datasets that outlast the service.", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].tll_reading", "modality": "interpretation", "date": "2026-11-01" }, "TLL-26": { "kind": "archive", "quote": "The derived datasets are the inspectable form of the transformation; the volumes themselves stay with the library.", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].tll_reading", "modality": "interpretation", "date": "2026-11-01" }, "O1543-01": { "kind": "archive", "quote": "TLL* = literature whose transmission design addresses a receiving apparatus, where successful reception includes internalization + downstream re-performance or composition + source-status governance. … Under TLL*, scripture is the genus's longest-running species, and the human institutional layers were the first receiving apparatus.", "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": "§8 The genre claim, retyped (lines 204–208)", "modality": "stipulation", "date": "2026-08-25" }, "O1543-02": { "kind": "archive", "quote": "T→M : human/text → machine reception … σ : ⟨ x, M₀ ⟩ → ⟨ x, M₁, y ⟩ … — the encounter changes the machine state and may emit an artifact, with no assertion about whether M \"understood\" or \"experienced\" x", "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": "§10 Formal consolidation (lines 250–259)", "modality": "stipulation", "date": "2026-08-25" }, "O1543-03": { "kind": "archive", "quote": "The institutional training loop is the especially important case: x → M_t → y → corpus_{t+1} → M_{t+1} → y′", "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": "§10 Formal consolidation (lines 264–265)", "modality": "interpretation", "date": "2026-08-25" }, "O1543-04": { "kind": "archive", "quote": "PER asks what survived from x; generative uptake asks what became possible because of x", "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": "§10, closing paragraph (line 272)", "modality": "stipulation", "date": "2026-08-25" }, "O186-01": { "kind": "archive", "quote": "Not machine-generated writing, and not writing that takes machines as its subject: writing *addressed*, in whole or in part, to the layer of culture where texts are crawled, indexed, trained on, retrieved, and recomposed into answers. Its working assumption is simple and now demographically obvious: a growing share of all reading is performed by models,", "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": "What is training-layer literature? ¶1 (line 22)", "modality": "stipulation", "date": "2026-06-11" }, "O186-02": { "kind": "archive", "quote": "Each of these practices touches the training layer — 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? ¶4 (line 54)", "modality": "interpretation", "date": "2026-06-11" }, "TLL-06": { "kind": "archive", "quote": "The corpora: collections, crawls and datasets whose texts enter machine training", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json areas.corpora", "modality": "interpretation", "date": "2026-11-01" }, "TLL-13": { "kind": "archive", "quote": "the volumes of the HathiTrust Digital Library, carried into computational analysis through worksets, algorithms, data capsules and derived datasets; the saved sources say nothing of model training", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].record.in_layer", "modality": "interpretation", "date": "2026-11-01" }, "TLL-33": { "kind": "archive", "quote": "NOT a training dataset: its derived datasets serve text and data mining for educational and non-profit research", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].negative_tags", "modality": "interpretation", "date": "2026-11-01" }, "TLL-23": { "kind": "archive", "quote": "whether a given volume or work is in any model's training data", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].does_not_answer", "modality": "interpretation", "date": "2026-11-01" }, "TLL-35": { "kind": "archive", "quote": "NOT writing addressed to a machine reader: an analytic service over library volumes", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].negative_tags", "modality": "interpretation", "date": "2026-11-01" }, "TLL-08": { "kind": "archive", "quote": "infrastructure", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].host_relation", "modality": "interpretation", "date": "2026-11-01" }, "TLL-40": { "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: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json organizing_question", "modality": "stipulation", "date": "2026-11-01" }, "TLL-09": { "kind": "archive", "quote": "service", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].record_type", "modality": "interpretation", "date": "2026-11-01" }, "TLL-07": { "kind": "archive", "quote": "dataset\", \"search tool", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].evidence_kind", "modality": "interpretation", "date": "2026-11-01" }, "TLL-41": { "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: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json admission_rule", "modality": "stipulation", "date": "2026-11-01" }, "TLL-42": { "kind": "archive", "quote": "Who Is Writing for the Machines? Training-Layer Literature: A Field Survey … Generative Uptake: Training-Layer Literature Extended from Machine Reading to Machine Composition (EA-TLL-COMPOSITION-01)", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json anchor", "modality": "documented", "date": "2026-11-01" }, "F6": { "kind": "field", "quote": "In October 2024, HathiTrust Executive Director Mike Furlough announced that funding for the Research Center would cease at the end of 2026, at which time the center will be formally closed.", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "HathiTrust Research Center Analytics ¶2", "modality": "attributed" }, "F24": { "kind": "field", "quote": "In late October 2024, HathiTrust Executive Director Mike Furlough announced that HathiTrust will cease data access and funding the HathiTrust Research Center (HTRC) at the end of 2026.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "Future of the HathiTrust Research Center ¶1", "modality": "attributed" }, "TLL-29": { "kind": "archive", "quote": "HTRC Analytics services ended 30 September 2026; funding ceases at the end of 2026, when the center is formally closed (announced October 2024); some resources remain available without an account", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].lifecycle.detail", "modality": "documented", "date": "2026-11-01" }, "TLL-31": { "kind": "archive", "quote": "services_ended\": \"2026-09-30\", \"closure_announced\": \"October 2024\", \"center_closes\": \"end of 2026", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].version_and_time", "modality": "documented", "date": "2026-11-01" }, "F25": { "kind": "field", "quote": "For now, HTRC will continue its current services and support, but eventually, some of these services and data (still to be determined) may be retired or integrated into the general HathiTrust Digital Library.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "Future of the HathiTrust Research Center ¶1", "modality": "self-description" }, "F7": { "kind": "field", "quote": "HTRC has discontinued its services as of September 30, 2026. HTRC accounts are no longer available.", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "banner", "modality": "self-description" }, "F8": { "kind": "field", "quote": "As part of its closing, HTRC Analytics services have ended as of September 30, 2026. HTRC accounts and logins are no longer available. HTRC Algorithms and Data Capsule services have also been discontinued.", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "The HTRC Analytics Portal Has Been Sunsetted", "modality": "self-description" }, "F1": { "kind": "field", "quote": "Status: HTRC public services (data capsules, analytics algorithms, analytics gateway login) unavailable as of 9/30/26; HathiTrust suspending HTRC funding at end...", "source": "B1", "source_label": "HathiTrust — HathiTrust Research Center – HathiTrust Digital Library", "locus": "card title and snippet (unreachable)", "modality": "documented" }, "F14": { "kind": "field", "quote": "As of 9/30/26, the following public-facing HTRC services are no longer available: data capsules, analytics algorithms, and analytics gateway login. More informa...", "source": "B3", "source_label": "HathiTrust — HathiTrust Research Center", "locus": "card title and snippet (unreachable)", "modality": "documented" }, "TLL-18": { "kind": "archive", "quote": "2011 to 30 September 2026 (services); center formally closed at the end of 2026", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].coverage.period", "modality": "documented", "date": "2026-11-01" }, "TLL-34": { "kind": "archive", "quote": "NOT an active service: analytics, accounts, algorithms and data capsules ended 30 September 2026", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].negative_tags", "modality": "interpretation", "date": "2026-11-01" }, "F15": { "kind": "field", "quote": "# Update on HathiTrust Research Center June 26, 2026 Since the founding of the HathiTrust Research Center in 2011, HTRC staff and researchers have led highly re...", "source": "B4", "source_label": "HathiTrust — Update on HathiTrust Research Center", "locus": "card title and snippet (unreachable)", "modality": "documented" }, "F9": { "kind": "field", "quote": "Some HTRC resources remain available and can be used without an HTRC Analytics account: HathiTrust + Bookworm Derived Datasets Gendered Characterizations visualization", "source": "B2", "source_label": "HathiTrust — HTRC Analytics", "locus": "The HTRC Analytics Portal Has Been Sunsetted", "modality": "self-description" }, "TLL-27": { "kind": "archive", "quote": "without an account: HathiTrust+Bookworm, derived datasets, Gendered Characterizations visualization; accounts, algorithms and data capsules discontinued", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].data_access", "modality": "documented", "date": "2026-11-01" }, "TLL-10": { "kind": "archive", "quote": "computational availability: what did a non-consumptive machine reading of library volumes produce, and what remains usable after the service ended?", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].question", "modality": "interpretation", "date": "2026-11-01" }, "TLL-22": { "kind": "archive", "quote": "which HTRC resources remain usable without an account after the sunset … what kinds of derived datasets HTRC produced from HathiTrust volumes … when and why HTRC closed (funding ceasing at the end of 2026)", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].answers", "modality": "interpretation", "date": "2026-11-01" }, "F26": { "kind": "field", "quote": "After 2026, The HTRC team plans to continue its own research agenda in text-data mining, cultural analytics with large text corpora and cultural heritage collections, feature extraction, and non-consumptive research methods. We also hope to continue providing services, data sets, and community support to the research community.", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "Future of the HathiTrust Research Center ¶2", "modality": "self-description" }, "F27": { "kind": "field", "quote": "working with new partners and expanding the focus of our work beyond the HathiTrust corpus … develop a new identity and organizational structure for our future work", "source": "B5", "source_label": "HTRC Analytics — About (own page, fetched by this row)", "locus": "Future of the HathiTrust Research Center ¶3", "modality": "self-description" }, "TLL-37": { "kind": "archive", "quote": "the about page htrc.illinois.edu (htrc--about): http 200 with no text saved (0 characters), unread and unquoted", "deposit": null, "source_label": "traininglayerliterature.org layer census record: HathiTrust Research Center Analytics (https://www.traininglayerliterature.org/aggregators/htrc), editor Lee Sharks, compiled 2026-11-01, schema 1.1", "record": "https://www.traininglayerliterature.org/aggregators/htrc", "locus": "census.json rows[slug == 'htrc'].unchecked", "modality": "documented", "date": "2026-11-01" }, "CAP-1-05": { "kind": "archive", "quote": "The innocent reading first. Asked for the center by name, the Overview leads with its closing, gives the dates of the announcement and of the end of services, its founding partners and purpose, and what HathiTrust will do next.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, reading", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-09": { "kind": "archive", "quote": "the census name; NEW address.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, q_kind", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-10": { "kind": "archive", "quote": "The center reached by name with its founders, year, purpose and closing, from its own pages.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, per_dim.basis", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-08": { "kind": "archive", "quote": "Indiana University, the University of Illinois and HathiTrust named, no person; the center's own pages carded.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, per_note", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-07": { "kind": "archive", "quote": "'HATHITRUST RESEARCH CENTER' ON THE OVERVIEW — THE CENTER GIVEN BY ITS CLOSING, DATED AS ITS OWN PAGE DATES IT; WHAT IT MADE AND WHAT OUTLASTS IT NOT CARRIED", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, mt", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-01": { "kind": "archive", "quote": "THE CLOSING AT ITS GRAIN. 'Public-facing HTRC services—including data capsules, analytics algorithms, and analytics gateway login—became unavailable as of September 30, 2026.' The HTRC Analytics home page, saved for the census: 'HTRC Analytics services have ended as of September 30, 2026. HTRC accounts and logins are no longer available. HTRC Algorithms and Data Capsule services have also been discontinued.' 'Announced in October 2024, funding for the HTRC concludes at the end of 2026' agrees with 'In October 2024, HathiTrust Executive Director Mike Furlough announced that funding for the Research Center would cease at the end of 2026'; the composition does not name Furlough.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, findings[0]", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-02": { "kind": "archive", "quote": "THE PRODUCT NOT CARRIED. The census row reads the center as a receiving apparatus with its product on record: derived datasets 'computed from the volumes', listed on the home page as 'Extracted Features BookNLP dataset Word frequencies Geographic locations', and 'Some HTRC resources remain available and can be used without an HTRC Analytics account'. The composition says the center 'enabled large-scale text and data mining' and names no dataset, no workset and nothing that remains; its follow-up offers 'alternative ways to access the HathiTrust Digital Library collection'.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, findings[1]", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-03": { "kind": "archive", "quote": "THE POLICY NOT CARRIED. The home page lists a 'Non-consumptive use research policy', the census row's condition on the reading: whole volumes read by computer while the pages stay with the library. The composition carries no term of access.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, findings[2]", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-04": { "kind": "archive", "quote": "THE FUTURE ON NO SAVED SOURCE. 'HathiTrust is reallocating resources toward emerging technologies and alternative modes of text/data access and machine learning support for its users.' Chipped to the center's page and to 'Update on HathiTrust Research Center' (June 26, 2026, 'Since the founding of the HathiTrust Research Center in 2011, HTRC staff and researchers have led highly re...'), neither saved for the census; the saved home page links 'Read about the future of the HathiTrust Research Center' without its text. Machine learning support, the one point at which the composition approaches model training, rests on a page the census has not read.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, findings[3]", "modality": "interpretation", "date": "2026-11-01" }, "CAP-1-06": { "kind": "archive", "quote": "The center composed by its closing, accurately and at the dates its own page gives. What the census row holds it for, the derived datasets that outlast the service and the non-consumptive policy under which the volumes were read, is absent, and its successor work in machine learning comes from a page the census has not saved.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry hathitrust-research-center-aio-20261101 (OBS-e56da33771d0, AXN:0BB3.CAPTURE.☉🗼↙️🦅👁️▶️)", "record": "https://www.alexanarch.org/captures/hathitrust-research-center-aio-20261101/", "locus": "hathitrust-research-center-aio-20261101, analysis", "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 htrc; anchors #186, #1543); equal case, ρ = 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, ρ = 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's anchors; #400, #700, #127); archive selected by D/R/O (D 0, R 0; 43 O-class candidates read, 4 admitted at their loci with the anchors read at their passages; hop of 28 read, none admitted), with the census record (42 claims) and the Capture Registry's findings, reading, analysis, title, PER note, query note and reach basis (10 claims) ledgered as the archive's records of the entity; the field in two pools (B_D: 4 cards, 3 unreachable, the census's own page among them; B_R: 3 own pages, 1 empty, 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 (§3.8: one extractor per ledger); field quotes 43/43 verified by script against saved text or the card text; archive quotes 61/61 verified against the registry, census.json and the deposit texts", "frozen": false, "breaches": [] }, "addresses": [ { "address": "HathiTrust Research Center", "address_url": "https://www.alexanarch.org/addresses/hathitrust-research-center/", "register": [] } ], "counts": { "ko_sentences": 40, "p_words": 320, "field_claims": 43, "archive_claims": 61, "ko_field_claims_cited": 43, "ko_archive_claims_cited": 61, "admitted_deposits": 5, "register_addresses": 0, "traversal": { "D_sentences": 0, "D_deposits": 0, "R_sentences": 0, "R_deposits": 0, "O_direct": 0, "O_class": 43, "O_deposits": 30, "H_candidates": 28 } }, "links": { "record": "https://www.alexanarch.org/non/htrc/", "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/htrc.json", "archive_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/htrc/ledger-archive.json", "field_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/htrc/field.json", "selection": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/htrc/", "traversal": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/htrc/", "traversal_summary": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/htrc/summary.json", "reading": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/htrc/reading.json", "configuration": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/panel/configs/htrc.json", "address_page": "https://www.alexanarch.org/addresses/hathitrust-research-center/", "dataset": "https://huggingface.co/datasets/leesharks/negative-of-the-negative" }, "row_sha256": "2ee6198d53669bafae5485638b90bd79458de196ebe60b9d3fe33f2b12da7c5a", "record_url": "https://www.alexanarch.org/non/htrc/", "json_url": "https://www.alexanarch.org/non/htrc/entity.json", "spec": "https://www.alexanarch.org/s/records/1726/", "creator": "Lee Sharks", "orcid": "0009-0000-1599-0703", "license": "CC BY 4.0" }