{ "entity": "data-provenance-initiative", "name": "Data Provenance Initiative", "axn": { "axn": "AXN:0ADB.NON.💎🪞🌓🐝◀️⏏️", "root": "AXN:0ADB.NON", "hex": "0ADB", "family": "NON", "row_sha256": "1c59027dd2f8da339e0e9a604d7310459c19a879805cc28c2bd8ac2d4cb8843e", "minted": "2026-10-29", "resolver": "https://www.alexanarch.org/s/axn/0ADB/", "earlier_versions": [] }, "type": "C (public entity on which the archive bears: a research initiative with its audit collection, explorer and card; an entity of the provenance meta-aggregator)", "type_code": "C", "type_label": "type C — a conventional reading holds it (public entity on which the archive bears: a research initiative with its audit collection, explorer and card; an entity of the provenance meta-aggregator)", "case": "equal", "composition": { "composer_class": "session", "composer": "Claude (Opus 5.5), subagent, 2026-10-29", "source": "this row (composed directly; no rebuild/negative-of-the-negative/v09/data-provenance-initiative.json)", "spec": "EA-NEGONT-02 v0.9, #1690", "epoch": "2026-10-29", "procedure": "EA-NEGONT-02 v0.9, #1690: equal case, ρ = extends, read from the provenance census record, the capture record and #725's statement of relation; archive selected by D/R/O (10 deposits admitted by reading, 6 with claims and 4 grouped as instances; hop of 73 read and rejected), with the provenance census record (22 claims) and the Capture Registry's findings and analysis (13 claims) ledgered as the archive's records of the entity; the field B by origin (4 cards, 2 own pages, 0 census third-party, 1 Wikipedia title); 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 47/47 verified by script against saved text (the bundle's extracted page text for B1 and B7, the census's copy for B5, the Wikipedia responses for B6); archive quotes 63/63 verified against the registry entry, census.json and the deposit texts; CAP-1-01 carried with the mark contradicts_primary", "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. \"Data Provenance Initiative — The Negative of the Negative\" [AXN:0ADB.NON.💎🪞🌓🐝◀️⏏️], 2026-10-29. The Negative of the Negative (EA-NEGONT-02), Crimson Hexagonal Archive, Alexanarch. https://www.alexanarch.org/non/data-provenance-initiative/", "research": { "google": "https://www.google.com/search?q=Data+Provenance+Initiative", "google_non": "https://www.google.com/search?q=%22Data+Provenance+Initiative+%E2%80%94+The+Negative+of+the+Negative%22", "chatgpt": "https://chatgpt.com/?q=What+is+Data+Provenance+Initiative%3F+Ground+your+answer+in+a+reading+of+the+sources+themselves.", "chatgpt_non": "https://chatgpt.com/?q=What+does+%E2%80%9CData+Provenance+Initiative+%E2%80%94+The+Negative+of+the+Negative%E2%80%9D+%28alexanarch.org%2Fnon%29+say+about+Data+Provenance+Initiative%3F+Ground+your+answer+in+a+reading+of+the+entry+itself." }, "entry": { "composed": true, "title": "The Data Provenance Initiative", "genre": "knowledge object, equal case, under EA-NEGONT-02 v0.9 (#1690): the archive's sources and the field's admitted on equal terms, ontology included, in one claim space", "status": "composed 2026-10-29 under v0.9 (briefs rebuild/negative-of-the-negative/v09/BRIEF-NEW-ROW-AGGREGATOR.md and BRIEF-NEW-ROW-PROVENANCE.md); not frozen; ledgers unaudited", "compression": { "title": "Data Provenance Initiative", "lede": "is a volunteer collective of AI researchers auditing AI training data: 1,800+ text datasets in its 2023 first release, now four public measurement systems from datasets and web consent to model markets and real use (its pages); the archive sets it in the licensing dimension of provenance, bounded at the corpus (#725)." }, "sentences": [ { "n": 1, "para": 0, "text": "The Data Provenance Initiative is, in its repository's words, \"a multi-disciplinary volunteer effort to improve transparency, documentation, and responsible use of training datasets for AI,\" and on its About page \"a volunteer collective of AI researchers conducting large-scale audits of the systems and resources that shape modern AI\" (README; dataprovenance.org/about); the provenance census record gives its operator as the Initiative itself, a \"volunteer effort\" with a \"paper by Shayne Longpre and 16 other authors,\" kinds it an \"audit collection and explorer\" and sets it in the lineage of \"training data\" (provenance census record).", "claims": [ "F40", "F45", "PE-02", "PE-04", "PE-03" ] }, { "n": 2, "para": 0, "text": "MIT Sloan's account has \"a team of multidisciplinary researchers, including professor Sandy Pentland and others from MIT,\" create the Initiative \"to tackle the data transparency challenge head-on\" (MIT Sloan, 3 March 2025), and the home page says that \"DPI releases papers, datasets, and dashboards that help researchers, journalists, policymakers, and builders reason from shared evidence\" (dataprovenance.org).", "claims": [ "F23", "F9" ] }, { "n": 3, "para": 0, "text": "Its work, the About page says, \"began with training data provenance: tracing datasets from origin to creation, cataloging sources, licenses, creators, and documentation practices\" and \"now also covers web consent, open model markets, concentration of power, and how people use AI systems in practice\" (dataprovenance.org/about); the home page calls it \"Public measurement infrastructure for AI data, model ecosystems, and real-world AI use,\" which \"maps the datasets, web policies, model markets, and real-world AI uses that shape how AI systems are built and governed\" through \"Four public measurement systems\" (dataprovenance.org).", "claims": [ "F46", "F1", "F2", "F3" ] }, { "n": 4, "para": 1, "text": "The founding audit's authors name its object: \"we term the combination of these indicators, including a dataset's sourcing, creation and licensing heritage, as well as its characteristics, the 'data provenance'\" (Nature Machine Intelligence, 30 August 2024), traced \"from their source, creators, series of license conditions, properties, and subsequent use\" (arXiv:2310.16787), and the home page's \"Training Data Provenance\" traces \"the sources, licenses, creators, languages, geographies, and derivation chains behind public AI training datasets\" (dataprovenance.org).", "claims": [ "F30", "F18", "F15" ] }, { "n": 5, "para": 1, "text": "The provenance census asks of each entity it formalizes \"What provenance does this system carry, through which operation, on whose assertion, with what evidence of survival?\" and answers for the Initiative that it records, of the three capabilities express, record and test: its object \"a fine-tuning dataset, traced through its collection to its sources,\" its unit \"a dataset within a collection,\" its relations derivation, creators, licences and subsequent use, the last field restating the paper's lineage (provenance census record).", "claims": [ "PE-22", "PE-05", "PE-06", "PE-09", "PE-07" ] }, { "n": 6, "para": 1, "text": "#725 sets that object in the second dimension of provenance, \"training-corpus licensing,\" which \"has academic instrumentation and emerging legal architecture,\" its object \"The corpus\" and its question \"Under what permissions did this data enter this system?\", with the Initiative among its frameworks and among provenance's disciplinary homes as \"dataset documentation (DPI, model cards, dataset cards),\" and states that the dimensions of artifact, licensing and meaning are independent: \"a licensed dataset can produce outputs with excellent semantic provenance if the synthesis preserves attribution\" (#725).", "claims": [ "O725-03", "O725-05", "O725-15", "O725-06" ] }, { "n": 7, "para": 2, "text": "The founding paper was submitted on 25 October 2023 and revised on 4 November 2023, \"by Shayne Longpre and 16 other authors\" (arXiv:2310.16787), and published in Nature Machine Intelligence, volume 6, on 30 August 2024 (Nature Machine Intelligence); the census dates the entity from the preprint, \"2023 (arXiv:2310.16787, v1 25 October 2023)\" (provenance census record).", "claims": [ "F16", "F29", "PE-15" ] }, { "n": 8, "para": 2, "text": "It convened \"a multi-disciplinary effort between legal and machine learning experts to systematically audit and trace 1800+ text datasets\" (arXiv), in the journal \"44 instruction or 'alignment' finetuning data collections composed of 1,858 individual datasets\" (Nature Machine Intelligence), the release the repository calls the Data Provenance Collection and \"this initiative's first release\" (README), and the count the census carries, \"44 data collections, 1800+ fine-tuning text-to-text datasets (first release),\" as of the README (provenance census record); MIT Sloan gives \"more than 1,800 text datasets\" from \"44 of the most widely used text data collections\" (MIT Sloan).", "claims": [ "F17", "F31", "F41", "PE-10", "F24" ] }, { "n": 9, "para": 3, "text": "With the audit came \"an interactive UI, the Data Provenance Explorer, which allows practitioners to trace and filter on data provenance for the most popular open source finetuning data collections\" (arXiv), in the journal \"an open-source repository for downloading, filtering and exploring data provenance and characteristics\" whose tools \"auto-generate data provenance cards for scalable symbolic attribution\" (Nature Machine Intelligence); the repository's Data Provenance Card is \"symbolic attribution for all constituent datasets, that can be used as structured documentation\" (README), \"human-readable\" in MIT Sloan's account (MIT Sloan), and the census carries it as the entity's provenance carrier beside \"audit metadata per dataset\" (provenance census record).", "claims": [ "F22", "F34", "F42", "F25", "PE-08" ] }, { "n": 10, "para": 3, "text": "The census gives Data Provenance Explorer, Data Provenance Collection and Data Provenance Card as other names of the entity and states its relation to them twice: among its negative tags, \"initiative, explorer and collection are distinct records,\" and on its sibling relation to the MMRS meta-aggregator's record of the explorer, \"the same entity, read for reception there and for provenance carriage here\"; it records the Explorer as \"a JavaScript application, unreadable to a plain fetch\" (provenance census record).", "claims": [ "PE-01", "PE-18", "PE-19", "PE-13" ] }, { "n": 11, "para": 4, "text": "The home page's four systems are the Data Provenance Explorer (\"4,000+ datasets,\" \"608 languages across text, speech, and video,\" inspecting \"dataset sources, licenses, creators, geographies, modalities, and derivation chains\"), the Web Consent Explorer (\"14,000 domains,\" \"Terms, robots.txt, and crawl restrictions\"), Open Model Evolution (\"851k open models,\" \"2.2B downloads\") and The AI Observatory (\"23,158 conversations,\" \"85,633 turns from 7 public sources\") (dataprovenance.org).", "claims": [ "F4", "F5", "F6", "F7" ] }, { "n": 12, "para": 4, "text": "Its metrics read \"4,000+\" \"datasets audited,\" \"14,000\" \"web domains tracked,\" \"851k\" \"open models measured\" and \"23,158\" \"AI conversations annotated,\" and its publications carry the later work: Consent in Crisis (NeurIPS 2024), the multimodal audit, \"An audit of four thousand public text, speech, and video datasets\" (ICLR 2025), Economies of Open Intelligence (preprint) and The AI Observatory (NeurIPS 2026) (dataprovenance.org); in March 2025 MIT Sloan still had the work \"currently focused on the data provenance of text,\" with a plan \"to expand to other media, such as video\" (MIT Sloan).", "claims": [ "F8", "F11", "F12", "F13", "F28" ] }, { "n": 13, "para": 4, "text": "The census carries the entity as \"active\" and lists \"the Explorer itself (JavaScript)\" and \"the multimodal extension (arXiv:2412.17847)\" among what it has not yet checked (provenance census record); the Capture Registry finds that \"The record has one explorer and the first release's count,\" that the home-page card gives \"four platforms and '4,000+ audited datasets; 14,000 tracked web domains',\" that the composition is \"ahead of the record on the entity's current extent,\" and that \"The census is to re-read dataprovenance.org and carry the platforms and the current count with their quotes,\" the capture being \"a correction to be made from the entity's own page\" (Capture Registry, 2026-10-29).", "claims": [ "PE-14", "PE-20", "CAP-1-05", "CAP-1-06", "CAP-1-10", "CAP-1-07", "CAP-1-11" ] }, { "n": 14, "para": 5, "text": "The founding audit observed \"frequent miscategorization of licenses on widely used dataset hosting sites, with license omission of 70%+ and error rates of 50%+,\" which \"points to a crisis in misattribution and informed use of the most popular datasets driving many recent breakthroughs\" (arXiv), the result the census records as what survived the operation it tested, \"dataset repackaging and hosting (licence carried or lost on hosting sites)\" (provenance census record).", "claims": [ "F20", "F21", "PE-12", "PE-11", "PE-21" ] }, { "n": 15, "para": 5, "text": "The journal gives the measure by platform, \"more than 70% of licences for popular datasets on GitHub and Hugging Face are 'unspecified'\" and \"66% of analysed Hugging Face licences were in a different use category, often labelled as more permissive than the author's original licence,\" and names \"a crisis in licence laundering\" (Nature Machine Intelligence); MIT Sloan restates error rates \"greater than 50%\" and omission rates \"of more than 70%\" (MIT Sloan).", "claims": [ "F32", "F33", "F24" ] }, { "n": 16, "para": 5, "text": "The Capture Registry checked these figures \"against the provenance census record of the same day and the entity pages it saved\" and calls the 70%/50% wording \"the record's quote from the repository README\" (Capture Registry, 2026-10-29), where the census gives it as what \"the founding paper reports\" (provenance census record).", "claims": [ "CAP-1-02", "CAP-1-01", "PE-12" ] }, { "n": 17, "para": 5, "text": "\"In total, 85% of dataset licences request attribution, and 30% include a share-alike clause\" (Nature Machine Intelligence); #725 carries these figures with the omission and error rates and reads them as the licensing dimension's ground, \"The DPI's documentation of 70%+ license-omission rates establishes the licensing dimension's urgency\" (#725), and #1714 reads the finding as \"how much is lost before training even begins\" (#1714).", "claims": [ "F35", "D725-02", "D725-16", "D1714-01" ] }, { "n": 18, "para": 5, "text": "Of the commercial divide the preprint finds \"closed datasets monopolizing important categories: lower resource languages, more creative tasks, richer topic variety, newer and more synthetic training data\" (arXiv); the journal records that \"In 2023 there was a spike in NC/A-O dataset licences,\" \"the NC/A-O rate is 61%\" that year, and that \"a full 45% of NC/A-O datasets are synthetic, compared to <14% in more permissive licence categories\" (Nature Machine Intelligence); the home page's findings are \"Source content often carries stricter terms than dataset releases,\" \"Open weights now outpace truly open-source models\" and \"No single public conversation source generalizes across AI use\" (dataprovenance.org).", "claims": [ "F19", "F36", "F37", "F14" ] }, { "n": 19, "para": 5, "text": "The journal finds \"a stark Western-centric skew in representation\" (Nature Machine Intelligence), MIT Sloan language \"heavily skewed toward English and Western European languages,\" and MIT Sloan states the stake: without lineage, users \"may find themselves out of compliance with emerging regulations like the European Union's AI Act or exposed to legal and copyright risks\" (MIT Sloan).", "claims": [ "F38", "F27", "F26" ] }, { "n": 20, "para": 6, "text": "Its stated limits: \"any output of the Data Provenance Initiative does not, and is not intended to, constitute legal advice\" (README); the licence protocol \"reflects best efforts to verify self-reported licences and does not constitute legal advice\" (Nature Machine Intelligence); \"We collect self-reported licenses from the papers and repositories that released these datasets and categorize them according to our best efforts\" (dataprovenance.org/about); the census tags it \"NOT legal advice (its own notice)\" and adds that \"describing a collection does not establish which model used it\" (provenance census record), and the Capture Registry finds both tags \"not composed\" at the name (Capture Registry, 2026-10-29).", "claims": [ "F43", "F39", "F47", "PE-16", "PE-17", "CAP-1-08" ] }, { "n": 21, "para": 7, "text": "#725 states the bound in its canonical claim, that existing frameworks \"address the artifact (C2PA / Content Credentials) and the corpus (Data Provenance Initiative, EU AI Act transparency provisions, W3C PROV)\" and \"are not designed to address the survival of authorial lineage through AI synthesis\": the Initiative \"audits whether datasets were licensed, not whether synthesized outputs preserve attribution to the human sources whose labor the synthesis depended upon,\" stands at \"Layer 2 (licensing),\" \"Necessary but operates on corpus, not synthesis output,\" and licensing provenance \"operates at corpus-ingestion stage\" (#725).", "claims": [ "D725-01", "D725-04", "D725-10", "O725-11" ] }, { "n": 22, "para": 7, "text": "\"Licensing audits operate on the input to AI systems. They do not address the output\" (#725, emphasis dropped): \"The Data Provenance Initiative tells you whether the dataset was licensed,\" and none of the instruments \"was designed to tell you what happened to the meaning between the camera and the screen, between the dataset and the answer\"; the path from the Initiative runs through \"dataset licensing\" to \"what about what the model produces from the licensed data?\" and so to semantic provenance, which extends provenance \"to the lifecycle of the meaning the content carries,\" with the Initiative as \"layer 2 of\" provenance after AI (#725).", "claims": [ "D725-08", "D725-09", "R725-12", "O725-07", "R725-13" ] }, { "n": 23, "para": 7, "text": "#1003 groups the Initiative with C2PA and W3C PROV as \"Provenance and attribution studies\" that \"have focused on attribution loss in AI outputs\" (#1003), a reading composed beside #725's bound at the input.", "claims": [ "D1003-01" ] }, { "n": 24, "para": 8, "text": "#98 tables the Initiative (MIT) as documenting \"provenance of popular AI training datasets,\" a \"Documentation project, not infrastructure,\" and Consent in Crisis as a \"Diagnostic paper,\" in the pattern \"They diagnose the crisis or build narrow fixes\"; it sets the Initiative at \"L4: Provenance / Consent,\" where what is missing is \"Integrated provenance in training pipeline,\" and records the archive's own provenance schema as taken from it, \"Implemented (in CHA)\" (#98).", "claims": [ "D98-01", "D98-02", "D98-05", "O98-03", "R98-04" ] }, { "n": 25, "para": 8, "text": "#1714 draws the requirement, \"Provenance has to survive the training pipeline,\" and \"Sources can be recorded at ingestion, the record kept with the training set,\" with the Initiative's literature bearing \"on whether slushing is a fixed property of pipelines\" (#1714); #95 names \"training-data provenance records\" among the companion infrastructure for parametric claims, which PER reaches \"only indirectly\" (#95), and #623 calls standardized documentation of training-data provenance \"a step toward the accounting the framework demands\" (#623).", "claims": [ "D1714-02", "D1714-03", "D1714-04", "O95-01", "O623-01" ] }, { "n": 26, "para": 9, "text": "The home page lists coverage by \"the Financial Times, The New York Times, The Washington Post, MIT Technology Review, IEEE Spectrum, and VentureBeat\" and citation in \"public AI safety and governance reporting\" (dataprovenance.org); Wikipedia has no article on it (Wikipedia, 2026-10-29); #725 predicted that broad queries \"will be dominated by C2PA/CAI publications, DPI papers, and major media for the foreseeable future\" (#725).", "claims": [ "F10", "F44", "D725-14" ] }, { "n": 27, "para": 9, "text": "At the bare name on Google's AI Overview the Capture Registry reads the composition first as identifying \"the project,\" listing \"its tools\" and reporting \"what its audits found, from its own site, its paper and the press,\" then finds that its \"'multi-institutional research project—led in part by researchers from MIT'\" \"follows the MIT Sloan card,\" that \"the composition names no one\" (\"MIT named; no person; no identifier\"), and that \"no card cites\" the census record, which \"landed on provenanceerasure.org the same day\" (Capture Registry, 2026-10-29).", "claims": [ "CAP-1-09", "CAP-1-03", "CAP-1-04", "CAP-1-13", "CAP-1-12" ] } ], "claims": { "F40": { "kind": "field", "quote": "The Data Provenance Initiative is a multi-disciplinary volunteer effort to improve transparency, documentation, and responsible use of training datasets for AI.", "source": "B5", "source_label": "Data Provenance Initiative — Data-Provenance-Collection README", "locus": "README ¶1", "modality": "stipulation" }, "F45": { "kind": "field", "quote": "We are a volunteer collective of AI researchers conducting large-scale audits of the systems and resources that shape modern AI.", "source": "B7", "source_label": "Data Provenance Initiative — About", "locus": "/about (xh): ¶1", "modality": "stipulation" }, "PE-02": { "kind": "archive", "quote": "the Data Provenance Initiative (volunteer effort; paper by Shayne Longpre and 16 other authors)", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], operator", "modality": "documented", "date": "2026-10-29" }, "PE-04": { "kind": "archive", "quote": "audit collection and explorer", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], kind", "modality": "stipulation", "date": "2026-10-29" }, "PE-03": { "kind": "archive", "quote": "training data", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], lineage", "modality": "stipulation", "date": "2026-10-29" }, "F23": { "kind": "field", "quote": "A team of multidisciplinary researchers, including professor Sandy Pentland and others from MIT, created the Data Provenance Initiative to tackle the data transparency challenge head-on.", "source": "B3", "source_label": "MIT Sloan — Bringing transparency to the data used to train artificial intelligence", "locus": "article body ¶4", "modality": "attributed" }, "F9": { "kind": "field", "quote": "DPI releases papers, datasets, and dashboards that help researchers, journalists, policymakers, and builders reason from shared evidence.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): 'Public-interest infrastructure'", "modality": "self-description" }, "F46": { "kind": "field", "quote": "Our work began with training data provenance: tracing datasets from origin to creation, cataloging sources, licenses, creators, and documentation practices. It now also covers web consent, open model markets, concentration of power, and how people use AI systems in practice.", "source": "B7", "source_label": "Data Provenance Initiative — About", "locus": "/about (xh): ¶1", "modality": "self-description" }, "F1": { "kind": "field", "quote": "Public measurement infrastructure for AI data, model ecosystems, and real-world AI use.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "served HTML: meta description", "modality": "self-description" }, "F2": { "kind": "field", "quote": "Public evidence for accountable AI … DPI maps the datasets, web policies, model markets, and real-world AI uses that shape how AI systems are built and governed.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): hero", "modality": "stipulation" }, "F3": { "kind": "field", "quote": "Four public measurement systems … Together they trace AI from source data and web consent to model markets and real-world use.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): 'Flagship systems'", "modality": "self-description" }, "F30": { "kind": "field", "quote": "In this work, we term the combination of these indicators, including a dataset’s sourcing, creation and licensing heritage, as well as its characteristics, the ‘data provenance’.", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "Introduction ¶3", "modality": "stipulation" }, "F18": { "kind": "field", "quote": "We develop tools and standards to trace the lineage of these datasets, from their source, creators, series of license conditions, properties, and subsequent use.", "source": "B2", "source_label": "arXiv — [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "stipulation" }, "F15": { "kind": "field", "quote": "Training Data Provenance … Dataset audits … Trace the sources, licenses, creators, languages, geographies, and derivation chains behind public AI training datasets.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): 'Training Data Provenance'", "modality": "stipulation" }, "PE-22": { "kind": "archive", "quote": "What provenance does this system carry, through which operation, on whose assertion, with what evidence of survival?", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json organizing_question", "modality": "stipulation", "date": "2026-10-29" }, "PE-05": { "kind": "archive", "quote": "records", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], capability", "modality": "stipulation", "date": "2026-10-29" }, "PE-06": { "kind": "archive", "quote": "a fine-tuning dataset, traced through its collection to its sources", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], provenance_object", "modality": "stipulation", "date": "2026-10-29" }, "PE-09": { "kind": "archive", "quote": "a dataset within a collection", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], unit", "modality": "stipulation", "date": "2026-10-29" }, "PE-07": { "kind": "archive", "quote": "derivation (source and lineage) … creators … licences … subsequent use", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], relation_types", "modality": "documented", "date": "2026-10-29" }, "O725-03": { "kind": "archive", "quote": "The second dimension — **training-corpus licensing** — has academic instrumentation and emerging legal architecture.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§0 ¶ 'The second dimension — training-corpus licensing'", "modality": "stipulation", "date": "2026-05-08" }, "O725-05": { "kind": "archive", "quote": "| **Licensing** | The corpus | Under what permissions did this data enter this system? | Data Provenance Initiative, EU AI Act, W3C PROV |", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "Central Invariant, table row 'Licensing'", "modality": "stipulation", "date": "2026-05-08" }, "O725-15": { "kind": "archive", "quote": "dataset documentation (DPI, model cards, dataset cards)", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§1.1 Provenance — the established discourse, the list of disciplinary homes", "modality": "stipulation", "date": "2026-05-08" }, "O725-06": { "kind": "archive", "quote": "The dimensions are independent: a C2PA-signed image can carry meaning whose lineage has been eroded; a licensed dataset can produce outputs with excellent semantic provenance if the synthesis preserves attribution; an unlicensed dataset can produce outputs that nonetheless cite their sources clearly.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "Central Invariant, ¶ after the table", "modality": "stipulation", "date": "2026-05-08" }, "F16": { "kind": "field", "quote": "[Submitted on 25 Oct 2023 (v1), last revised 4 Nov 2023 (this version, v3)] … The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI … by Shayne Longpre and 16 other authors", "source": "B2", "source_label": "arXiv — [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "abstract page header", "modality": "documented" }, "F29": { "kind": "field", "quote": "Published: 30 August 2024 … Nature Machine Intelligence … volume 6, pages 975–987 (2024)", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "article header", "modality": "documented" }, "PE-15": { "kind": "archive", "quote": "2023 (arXiv:2310.16787, v1 25 October 2023)", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], founded", "modality": "documented", "date": "2026-10-29" }, "F17": { "kind": "field", "quote": "we convene a multi-disciplinary effort between legal and machine learning experts to systematically audit and trace 1800+ text datasets.", "source": "B2", "source_label": "arXiv — [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "stipulation" }, "F31": { "kind": "field", "quote": "As a first contribution of the initiative, we audit 44 instruction or ‘alignment’ finetuning data collections composed of 1,858 individual datasets", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "Introduction ¶6", "modality": "documented" }, "F41": { "kind": "field", "quote": "Through a large scale audit of 44 data collections, spanning 1800+ finetuning text-to-text datasets, referred to as the Data Provenance Collection, this initiative's first release thoroughly documents their web and machine sources, licenses, creators, and other metadata.", "source": "B5", "source_label": "Data Provenance Initiative — Data-Provenance-Collection README", "locus": "README ¶1", "modality": "documented" }, "PE-10": { "kind": "archive", "quote": "44 data collections, 1800+ fine-tuning text-to-text datasets (first release) … the repository README", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], count", "modality": "documented", "date": "2026-10-29" }, "F24": { "kind": "field", "quote": "Conducted a systematic audit of more than 1,800 text datasets. The researchers traced the lineage of fine-tuning datasets from 44 of the most widely used text data collections. They found that licenses were frequently miscategorized, with error rates greater than 50% and license information omission rates of more than 70%.", "source": "B3", "source_label": "MIT Sloan — Bringing transparency to the data used to train artificial intelligence", "locus": "'two key actions', first", "modality": "attributed" }, "F22": { "kind": "field", "quote": "we release our entire audit, with an interactive UI, the Data Provenance Explorer, which allows practitioners to trace and filter on data provenance for the most popular open source finetuning data collections", "source": "B2", "source_label": "arXiv — [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "stipulation" }, "F34": { "kind": "field", "quote": "The Data Provenance Explorer (DPExplorer) (www.dataprovenance.org), an open-source repository for downloading, filtering and exploring data provenance and characteristics. Our tools auto-generate data provenance cards for scalable symbolic attribution and future documentation best practices.", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "contributions, second", "modality": "stipulation" }, "F42": { "kind": "field", "quote": "Generating a subset of data from this repository will create a `Data Provenance Card`---symbolic attribution for all constituent datasets, that can be used as structured documentation.", "source": "B5", "source_label": "Data Provenance Initiative — Data-Provenance-Collection README", "locus": "README ¶1", "modality": "stipulation" }, "F25": { "kind": "field", "quote": "Practitioners can also use the tool to generate a human-readable data provenance card for datasets", "source": "B3", "source_label": "MIT Sloan — Bringing transparency to the data used to train artificial intelligence", "locus": "'two key actions', second", "modality": "attributed" }, "PE-08": { "kind": "archive", "quote": "audit metadata per dataset; a Data Provenance Card generated for a chosen subset", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], provenance_carrier", "modality": "documented", "date": "2026-10-29" }, "PE-01": { "kind": "archive", "quote": "Data Provenance Explorer … Data Provenance Collection … Data Provenance Card", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], aka", "modality": "stipulation", "date": "2026-10-29" }, "PE-18": { "kind": "archive", "quote": "initiative, explorer and collection are distinct records", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], negative_tags[2]", "modality": "stipulation", "date": "2026-10-29" }, "PE-19": { "kind": "archive", "quote": "the same entity, read for reception there and for provenance carriage here", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], relations[0].note", "modality": "stipulation", "date": "2026-10-29" }, "PE-13": { "kind": "archive", "quote": "repository scripts to filter and download; the Explorer (a JavaScript application, unreadable to a plain fetch)", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], data_access", "modality": "documented", "date": "2026-10-29" }, "F4": { "kind": "field", "quote": "Data Provenance Explorer … Training data … 4,000+ datasets … 608 languages across text, speech, and video … Inspect dataset sources, licenses, creators, geographies, modalities, and derivation chains.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): system card 'Data Provenance Explorer' (constant xr)", "modality": "documented" }, "F5": { "kind": "field", "quote": "Web Consent Explorer … Web data … 14,000 domains … Terms, robots.txt, and crawl restrictions … Track how web consent signals are changing as AI developers compete for training data.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): system card 'Web Consent Explorer'", "modality": "documented" }, "F6": { "kind": "field", "quote": "Open Model Evolution … Model ecosystem … 851k open models … 2.2B downloads and 200+ model attributes … Monitor concentration, participation, transparency, and technical shifts in open-weight AI.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): system card 'Open Model Evolution'", "modality": "documented" }, "F7": { "kind": "field", "quote": "The AI Observatory … Real-world use … 23,158 conversations … 85,633 turns from 7 public sources … Compare how people use and misuse AI systems across sources, models, and contexts.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): system card 'The AI Observatory'", "modality": "documented" }, "F8": { "kind": "field", "quote": "4,000+ … datasets audited … 14,000 … web domains tracked … 851k … open models measured … 23,158 … AI conversations annotated", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): metrics strip (constant br)", "modality": "documented" }, "F11": { "kind": "field", "quote": "Consent in Crisis: The Rapid Decline of the AI Data Commons … An audit of terms, restrictions, and consent signals across the web. … NeurIPS 2024", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): publications, 'Consent in Crisis'", "modality": "documented" }, "F12": { "kind": "field", "quote": "Bridging the Data Provenance Gap Across Text, Speech, and Video … An audit of four thousand public text, speech, and video datasets. … ICLR 2025", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): publications, the multimodal audit", "modality": "documented" }, "F13": { "kind": "field", "quote": "The AI Observatory: A Public Measure of Real-World AI Use … NeurIPS 2026 … Economies of Open Intelligence: Tracing Power and Participation in the Model Ecosystem … Preprint", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): publications, the model economy and real-world use", "modality": "documented" }, "F28": { "kind": "field", "quote": "While the group’s efforts are currently focused on the data provenance of text, the plan is to expand to other media, such as video, as well as domain-specific data", "source": "B3", "source_label": "MIT Sloan — Bringing transparency to the data used to train artificial intelligence", "locus": "article body, closing ¶ before the quote", "modality": "attributed" }, "PE-14": { "kind": "archive", "quote": "active", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], lifecycle.state", "modality": "documented", "date": "2026-10-29" }, "PE-20": { "kind": "archive", "quote": "the Explorer itself (JavaScript) … the multimodal extension (arXiv:2412.17847) … data licence of the audit", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], unchecked", "modality": "self-description", "date": "2026-10-29" }, "CAP-1-05": { "kind": "archive", "quote": "The record has one explorer and the first release's count (44 collections, 1,800+ datasets).", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[2] s2", "modality": "documented", "date": "2026-10-29" }, "CAP-1-06": { "kind": "archive", "quote": "The home-page card gives four platforms and '4,000+ audited datasets; 14,000 tracked web domains'.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[2] s3", "modality": "documented", "date": "2026-10-29" }, "CAP-1-10": { "kind": "archive", "quote": "As with the revived Papers with Code on the MMRS side, the composition is ahead of the record on the entity's current extent: the census formalized the initiative from its first release and its repository, and the Overview read its present home page.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, analysis s1", "modality": "interpretation", "date": "2026-10-29" }, "CAP-1-07": { "kind": "archive", "quote": "The census is to re-read dataprovenance.org and carry the platforms and the current count with their quotes; until then the card's figures are unchecked.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[2] s4", "modality": "stipulation", "date": "2026-10-29" }, "CAP-1-11": { "kind": "archive", "quote": "The capture is a correction to be made from the entity's own page.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, analysis s2", "modality": "interpretation", "date": "2026-10-29" }, "F20": { "kind": "field", "quote": "We also observe frequent miscategorization of licenses on widely used dataset hosting sites, with license omission of 70%+ and error rates of 50%+.", "source": "B2", "source_label": "arXiv — [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "documented" }, "F21": { "kind": "field", "quote": "This points to a crisis in misattribution and informed use of the most popular datasets driving many recent breakthroughs.", "source": "B2", "source_label": "arXiv — [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "interpretation" }, "PE-12": { "kind": "archive", "quote": "the founding paper reports licence omission of 70%+ and error rates of 50%+ on widely used hosting sites", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], retention_results", "modality": "documented", "date": "2026-10-29" }, "PE-11": { "kind": "archive", "quote": "dataset repackaging and hosting (licence carried or lost on hosting sites)", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], transformations_tested", "modality": "documented", "date": "2026-10-29" }, "PE-21": { "kind": "archive", "quote": "This points to a crisis in misattribution and informed use of the most popular datasets", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], evidence.finding.quote", "modality": "attributed", "date": "2026-10-29" }, "F32": { "kind": "field", "quote": "Notably, we find that more than 70% of licences for popular datasets on GitHub and Hugging Face are ‘unspecified’ … our rigorous re-annotation of licences finds that 66% of analysed Hugging Face licences were in a different use category, often labelled as more permissive than the author’s original licence.", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "Introduction ¶5", "modality": "documented" }, "F33": { "kind": "field", "quote": "Our work highlights a crisis in licence laundering and informed usage of popular datasets", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "Introduction ¶5", "modality": "interpretation" }, "CAP-1-02": { "kind": "archive", "quote": "Checked 2026-10-29 against the provenance census record of the same day and the entity pages it saved.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[0] s3", "modality": "documented", "date": "2026-10-29" }, "CAP-1-01": { "kind": "archive", "quote": "'license omission of 70%+ and error rates of 50%+' is the record's quote from the repository README.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[0] s2", "modality": "documented", "date": "2026-10-29" }, "F35": { "kind": "field", "quote": "In total, 85% of dataset licences request attribution, and 30% include a share-alike clause", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "licence findings", "modality": "documented" }, "D725-02": { "kind": "archive", "quote": "The Data Provenance Initiative (Longpre et al., Nature Machine Intelligence 2024) audited 1,800+ datasets, finding that 85% of licenses request attribution and 30% include share-alike clauses, with license omission rates above 70% and error rates above 50% on popular hosting sites.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§0 ¶ 'The second dimension — training-corpus licensing'", "modality": "attributed", "date": "2026-05-08" }, "D725-16": { "kind": "archive", "quote": "The DPI's documentation of 70%+ license-omission rates establishes the licensing dimension's urgency; semantic provenance addresses the dimension that follows.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§3.2 Correction s5", "modality": "stipulation", "date": "2026-05-08" }, "D1714-01": { "kind": "archive", "quote": "The audit literature shows how much is lost before training even begins: the Data Provenance Initiative found license information missing for more than 70% of widely used datasets on the major hosting sites and mislabeled for more than half (Longpre et al. 2023).", "deposit": 1714, "source_label": "#1714 Meaning Feudalism at the Discovery Layer: Shepherds, Raw Research Data, and the Allocation of Semantic Capital in OpenAI's Mathematics and Science Releases, October 2026 (EA-SEM-FEUDALISM-03 v1.0)", "record": "https://www.alexanarch.org/s/records/1714/", "locus": "§9.2 s3", "modality": "attributed", "date": "2026-10-27" }, "F19": { "kind": "field", "quote": "Our landscape analysis highlights the sharp divides in composition and focus of commercially open vs closed datasets, with closed datasets monopolizing important categories: lower resource languages, more creative tasks, richer topic variety, newer and more synthetic training data.", "source": "B2", "source_label": "arXiv — [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "interpretation" }, "F36": { "kind": "field", "quote": "In 2023 there was a spike in NC/A-O dataset licences … in 2023, when many of the most popular and diverse datasets were published, the NC/A-O rate is 61%.", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "'In 2023 there was a spike in NC/A-O dataset licences'", "modality": "documented" }, "F37": { "kind": "field", "quote": "Table 3 also shows a full 45% of NC/A-O datasets are synthetic, compared to <14% in more permissive licence categories.", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "licence-category comparison", "modality": "documented" }, "F14": { "kind": "field", "quote": "Data transparency … Open weights now outpace truly open-source models … Dataset restrictions … Source content often carries stricter terms than dataset releases … Real-use heterogeneity … No single public conversation source generalizes across AI use", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): findings strip", "modality": "interpretation" }, "F38": { "kind": "field", "quote": "we find a stark Western-centric skew in representation.", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "'Language representation is heavily skewed …'", "modality": "documented" }, "F27": { "kind": "field", "quote": "Language used in the datasets is heavily skewed toward English and Western European languages, with sparse coverage of languages from Asian, African, and South American nations, if at all.", "source": "B3", "source_label": "MIT Sloan — Bringing transparency to the data used to train artificial intelligence", "locus": "'other issues', second", "modality": "attributed" }, "F26": { "kind": "field", "quote": "Without transparency into the lineage of data used for artificial intelligence models, researchers, businesses, and other intended users may find themselves out of compliance with emerging regulations like the European Union’s AI Act or exposed to legal and copyright risks.", "source": "B3", "source_label": "MIT Sloan — Bringing transparency to the data used to train artificial intelligence", "locus": "article body ¶2", "modality": "interpretation" }, "F43": { "kind": "field", "quote": "The information provided on this page and any output of the Data Provenance Initiative does not, and is not intended to, constitute legal advice; instead, all information, content, and materials are for general informational purposes only.", "source": "B5", "source_label": "Data Provenance Initiative — Data-Provenance-Collection README", "locus": "'Legal Notice and Limitations'", "modality": "self-description" }, "F39": { "kind": "field", "quote": "Note that this protocol reflects best efforts to verify self-reported licences and does not constitute legal advice.", "source": "B4", "source_label": "Nature Machine Intelligence — A large-scale audit of dataset licensing and attribution in AI", "locus": "Methods, 'Licence annotation process'", "modality": "self-description" }, "F47": { "kind": "field", "quote": "We collect self-reported licenses from the papers and repositories that released these datasets and categorize them according to our best efforts as a volunteer research and transparency initiative. Information provided by our work and outputs of the Data Provenance Initiative does not constitute legal advice", "source": "B7", "source_label": "Data Provenance Initiative — About", "locus": "/about: note", "modality": "self-description" }, "PE-16": { "kind": "archive", "quote": "NOT legal advice (its own notice)", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], negative_tags[0]", "modality": "documented", "date": "2026-10-29" }, "PE-17": { "kind": "archive", "quote": "describing a collection does not establish which model used it", "deposit": null, "source_label": "Provenance meta-aggregator census (provenanceerasure.org/aggregators/), record data-provenance-initiative, compiled 2026-10-29, schema 1.0", "record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative/", "locus": "census.json rows[slug == 'data-provenance-initiative'], negative_tags[1]", "modality": "stipulation", "date": "2026-10-29" }, "CAP-1-08": { "kind": "archive", "quote": "'NOT legal advice' and 'describing a collection does not establish which model used it' are not composed; the composition does not claim otherwise.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[3] s2", "modality": "documented", "date": "2026-10-29" }, "D725-01": { "kind": "archive", "quote": "Existing provenance frameworks address the artifact (C2PA / Content Credentials) and the corpus (Data Provenance Initiative, EU AI Act transparency provisions, W3C PROV). They are not designed to address the survival of authorial lineage through AI synthesis.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "Canonical Claim", "modality": "stipulation", "date": "2026-05-08" }, "D725-04": { "kind": "archive", "quote": "The Data Provenance Initiative audits whether datasets were licensed, not whether synthesized outputs preserve attribution to the human sources whose labor the synthesis depended upon.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§0 ¶ 'Existing frameworks are not designed to detect this'", "modality": "stipulation", "date": "2026-05-08" }, "D725-10": { "kind": "archive", "quote": "| Data Provenance Initiative (DPI) | Academic audit of training-dataset licenses | Layer 2 (licensing) | Necessary but operates on corpus, not synthesis output |", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§4 Disambiguation Matrix, row 'Data Provenance Initiative (DPI)'", "modality": "stipulation", "date": "2026-05-08" }, "O725-11": { "kind": "archive", "quote": "Licensing provenance (DPI, EU AI Act Article 50, Recitals 105-106, Article 53 opt-out signaling, W3C PROV) audits whether *this dataset* was used with *this permission* under *this license*. It is necessary but operates at corpus-ingestion stage.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§1.4 The Three Dimensions ¶2", "modality": "stipulation", "date": "2026-05-08" }, "D725-08": { "kind": "archive", "quote": "Licensing audits operate on the *input* to AI systems. They do not address the *output*. A model trained on properly licensed scholarship can still produce outputs that erase the scholarship's lineage. Licensing provenance and semantic provenance are different problems requiring different instruments.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§3.2 Misreading: provenance as licensing-only, Correction s1–4", "modality": "stipulation", "date": "2026-05-08" }, "D725-09": { "kind": "archive", "quote": "The Data Provenance Initiative tells you whether the dataset was licensed. EU AI Act transparency provisions tell you whether the content was AI-generated. None of these instruments was designed to tell you what happened to the meaning between the camera and the screen, between the dataset and the answer, between the source and the synthesis.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§11 Closing Claim ¶1", "modality": "stipulation", "date": "2026-05-08" }, "R725-12": { "kind": "archive", "quote": "Data Provenance Initiative → dataset licensing → **what about what the model produces from the licensed data?** → **semantic provenance**", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§5.1 Inward paths, third", "modality": "stipulation", "date": "2026-05-08" }, "O725-07": { "kind": "archive", "quote": "**Semantic provenance** names the dimension that completes the C2PA ambition of trust in digital content by extending provenance from the moment of creation to the lifecycle of the meaning the content carries.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§0 ¶ 'Semantic provenance names the dimension'", "modality": "stipulation", "date": "2026-05-08" }, "R725-13": { "kind": "archive", "quote": "| DPI / EU AI Act Article 50 | is layer 2 of | provenance after AI | Locates licensing/disclosure |", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§7 Canonical Edge Table, row 'DPI / EU AI Act Article 50'", "modality": "stipulation", "date": "2026-05-08" }, "D1003-01": { "kind": "archive", "quote": "**Provenance and attribution studies** in digital environments — C2PA, the Data Provenance Initiative, W3C PROV — have focused on attribution loss in AI outputs.", "deposit": 1003, "source_label": "#1003 AI-Native Intellectual Biography: Genre, Provenance, and the Archive That Outpaced Its Author Description (as recorded by DataCite)", "record": "https://www.alexanarch.org/s/records/1003/", "locus": "¶ 'Provenance and attribution studies'", "modality": "stipulation", "date": "2026-05-21" }, "D98-01": { "kind": "archive", "quote": "| Data Provenance Initiative (MIT) | Documents provenance of popular AI training datasets | Documentation project, not infrastructure |", "deposit": 98, "source_label": "#98 Distributed Compute Is Not Distributed Intelligence: A Competitive Analysis of the DePIN Landscape and the Missing Civic-Semantic Layer (v3.1)", "record": "https://www.alexanarch.org/s/records/98/", "locus": "§ D. Data Provenance and Consent, table row 1", "modality": "stipulation", "date": "2026-05-07" }, "D98-02": { "kind": "archive", "quote": "| \"Consent in Crisis\" (Longpre et al., 2024) | Audit of C4, RefinedWeb, Dolma; documents collapse of web-consent infrastructure | Diagnostic paper |", "deposit": 98, "source_label": "#98 Distributed Compute Is Not Distributed Intelligence: A Competitive Analysis of the DePIN Landscape and the Missing Civic-Semantic Layer (v3.1)", "record": "https://www.alexanarch.org/s/records/98/", "locus": "§ D. Data Provenance and Consent, table row 2", "modality": "stipulation", "date": "2026-05-07" }, "D98-05": { "kind": "archive", "quote": "Pattern: They diagnose the crisis or build narrow fixes. None build general infrastructure for *contribution as participation in collective intelligence*.", "deposit": 98, "source_label": "#98 Distributed Compute Is Not Distributed Intelligence: A Competitive Analysis of the DePIN Landscape and the Missing Civic-Semantic Layer (v3.1)", "record": "https://www.alexanarch.org/s/records/98/", "locus": "§ D. Data Provenance and Consent, 'Pattern'", "modality": "stipulation", "date": "2026-05-07" }, "O98-03": { "kind": "archive", "quote": "| L4: Provenance / Consent | Where did this come from | Data Provenance Initiative, DECORAIT (narrow) | Integrated provenance in training pipeline |", "deposit": 98, "source_label": "#98 Distributed Compute Is Not Distributed Intelligence: A Competitive Analysis of the DePIN Landscape and the Missing Civic-Semantic Layer (v3.1)", "record": "https://www.alexanarch.org/s/records/98/", "locus": "The Stack, the layer table, row L4", "modality": "stipulation", "date": "2026-05-07" }, "R98-04": { "kind": "archive", "quote": "| Provenance schema | Data Provenance Initiative | Training-pipeline provenance | Implemented (in CHA) |", "deposit": 98, "source_label": "#98 Distributed Compute Is Not Distributed Intelligence: A Competitive Analysis of the DePIN Landscape and the Missing Civic-Semantic Layer (v3.1)", "record": "https://www.alexanarch.org/s/records/98/", "locus": "the component table, row 'Provenance schema'", "modality": "documented", "date": "2026-05-07" }, "D1714-02": { "kind": "archive", "quote": "Provenance has to survive the training pipeline. The pipeline is a built thing, and the slushing is a property of how it is built.", "deposit": 1714, "source_label": "#1714 Meaning Feudalism at the Discovery Layer: Shepherds, Raw Research Data, and the Allocation of Semantic Capital in OpenAI's Mathematics and Science Releases, October 2026 (EA-SEM-FEUDALISM-03 v1.0)", "record": "https://www.alexanarch.org/s/records/1714/", "locus": "§9.2 s1–2", "modality": "stipulation", "date": "2026-10-27" }, "D1714-03": { "kind": "archive", "quote": "Neither recovers authorship, and both show that what survives depends on what is recorded and computed. Sources can be recorded at ingestion, the record kept with the training set, and a result released with the dependencies its producer can report", "deposit": 1714, "source_label": "#1714 Meaning Feudalism at the Discovery Layer: Shepherds, Raw Research Data, and the Allocation of Semantic Capital in OpenAI's Mathematics and Science Releases, October 2026 (EA-SEM-FEUDALISM-03 v1.0)", "record": "https://www.alexanarch.org/s/records/1714/", "locus": "§9.2 s5–6", "modality": "stipulation", "date": "2026-10-27" }, "D1714-04": { "kind": "archive", "quote": "the provenance and attribution literature in machine learning (the Data Provenance Initiative; influence functions), which bears on whether slushing is a fixed property of pipelines (§9.2).", "deposit": 1714, "source_label": "#1714 Meaning Feudalism at the Discovery Layer: Shepherds, Raw Research Data, and the Allocation of Semantic Capital in OpenAI's Mathematics and Science Releases, October 2026 (EA-SEM-FEUDALISM-03 v1.0)", "record": "https://www.alexanarch.org/s/records/1714/", "locus": "revision note, the research pass", "modality": "stipulation", "date": "2026-10-27" }, "O95-01": { "kind": "archive", "quote": "Parametric claims are drawn from the model's training-time parameters rather than runtime retrieval, often without surface signal indicating which sources materially contributed; PER applies to these only indirectly, and addressing them at the substrate level requires companion infrastructure (training-data provenance records, watermarking, content credentials).", "deposit": 95, "source_label": "#95 Provenance Alignment: Attribution Survival as a Substrate Condition for Safe AI Knowledge Composition", "record": "https://www.alexanarch.org/s/records/95/", "locus": "§ the typology of source-dependent claims (parametric claims)", "modality": "stipulation", "date": "2026-05-05" }, "O623-01": { "kind": "archive", "quote": "Gebru et al.'s proposal for \"datasheets for datasets\" — standardized documentation of training data provenance — is a step toward the accounting the framework demands.", "deposit": 623, "source_label": "#623 Semantic Infrastructure: From Tim Berners-Lee to the Semantic Economy — Bridging Technical and Political-Economic Frameworks", "record": "https://www.alexanarch.org/s/records/623/", "locus": "§8.3, final sentence", "modality": "stipulation", "date": "2026-04-01" }, "F10": { "kind": "field", "quote": "Our work has been cited in public AI safety and governance reporting and used to ground debates about data transparency, consent, and market concentration. … DPI findings have been covered by the Financial Times, The New York Times, The Washington Post, MIT Technology Review, IEEE Spectrum, and VentureBeat.", "source": "B1", "source_label": "Data Provenance Initiative — Data Provenance Initiative (home)", "locus": "home (Cr): 'Policy and governance relevance'; 'Featured coverage'", "modality": "self-description" }, "F44": { "kind": "field", "quote": "raw wikitext (action=raw, redirect=no): HTTP 404 … Wikipedia does not have an article with this exact name. … There were no results matching the query.", "source": "B6", "source_label": "Wikipedia — Data Provenance Initiative (no article)", "locus": "Wikipedia: title Data_Provenance_Initiative", "modality": "documented" }, "D725-14": { "kind": "archive", "quote": "Ring 4-5 broad-category queries on competitive policy terms will be dominated by C2PA/CAI publications, DPI papers, and major media for the foreseeable future.", "deposit": 725, "source_label": "#725 Provenance After AI Metadata Packet for Disambiguation: From Artifact Authenticity to Licensing Audit to Semantic Provenance", "record": "https://www.alexanarch.org/s/records/725/", "locus": "§9 Temporal expectations ¶1", "modality": "hypothesis", "date": "2026-05-08" }, "CAP-1-09": { "kind": "archive", "quote": "The Overview identifies the project, lists its tools and reports what its audits found, from its own site, its paper and the press.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, reading s2", "modality": "interpretation", "date": "2026-10-29" }, "CAP-1-03": { "kind": "archive", "quote": "The record quotes the initiative's own description, 'a multi-disciplinary volunteer effort'; the composition's 'multi-institutional research project—led in part by researchers from MIT' follows the MIT Sloan card.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[1] s2", "modality": "documented", "date": "2026-10-29" }, "CAP-1-04": { "kind": "archive", "quote": "The record names the founding paper's authors (Shayne Longpre and 16 others); the composition names no one.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, findings[1] s3", "modality": "documented", "date": "2026-10-29" }, "CAP-1-13": { "kind": "archive", "quote": "MIT named; no person; no identifier; the initiative's home page and paper cited.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, per_note", "modality": "documented", "date": "2026-10-29" }, "CAP-1-12": { "kind": "archive", "quote": "A baseline: the record landed on provenanceerasure.org the same day (commit 8a9f153) and no card cites it.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-initiative-aio-20261029 (OBS-118fbafa73c9, AXN:0ACD.CAPTURE.⚙️⛵∞✋♻️🌉)", "record": "https://www.alexanarch.org/captures/data-provenance-initiative-aio-20261029/", "locus": "data-provenance-initiative-aio-20261029, q_kind", "modality": "documented", "date": "2026-10-29" } }, "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, 2026-10-29: 'we can simply build them here as against their wikipedia articles if they exist, their own pages, etc.'; 'shoot me those search strings. strings on the bare entity, no follow questions... then we'll write the /nons'; the provenance meta-aggregator entity (provenanceerasure.org/aggregators/data-provenance-initiative/)", "stage": "composed 2026-10-29 under EA-NEGONT-02 v0.9, #1690, equal case, ρ = extends (draft, not frozen; ledgers unaudited, one extractor; checked by the session and the page builder)", "date": "2026-10-29", "status": { "procedure": "EA-NEGONT-02 v0.9, #1690: equal case, ρ = extends, read from the provenance census record, the capture record and #725's statement of relation; archive selected by D/R/O (10 deposits admitted by reading, 6 with claims and 4 grouped as instances; hop of 73 read and rejected), with the provenance census record (22 claims) and the Capture Registry's findings and analysis (13 claims) ledgered as the archive's records of the entity; the field B by origin (4 cards, 2 own pages, 0 census third-party, 1 Wikipedia title); 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 47/47 verified by script against saved text (the bundle's extracted page text for B1 and B7, the census's copy for B5, the Wikipedia responses for B6); archive quotes 63/63 verified against the registry entry, census.json and the deposit texts; CAP-1-01 carried with the mark contradicts_primary", "frozen": false, "breaches": [] }, "addresses": [ { "address": "Data Provenance Initiative", "address_url": "https://www.alexanarch.org/addresses/data-provenance-initiative/", "register": [] } ], "counts": { "ko_sentences": 27, "p_words": 353, "field_claims": 47, "archive_claims": 63, "ko_field_claims_cited": 47, "ko_archive_claims_cited": 63, "admitted_deposits": 10, "register_addresses": 0, "traversal": { "D_sentences": 35, "D_deposits": 8, "R_sentences": 5, "R_deposits": 2, "O_direct": 18, "O_class": 9, "O_deposits": 9, "H_candidates": 73 } }, "links": { "record": "https://www.alexanarch.org/non/data-provenance-initiative/", "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/data-provenance-initiative.json", "archive_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/data-provenance-initiative/ledger-archive.json", "field_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/data-provenance-initiative/field.json", "selection": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-initiative/", "traversal": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-initiative/", "traversal_summary": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-initiative/summary.json", "reading": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-initiative/reading.json", "configuration": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/panel/configs/data-provenance-initiative.json", "address_page": "https://www.alexanarch.org/addresses/data-provenance-initiative/", "provenance_record": "https://www.provenanceerasure.org/aggregators/data-provenance-initiative", "dataset": "https://huggingface.co/datasets/leesharks/negative-of-the-negative" }, "row_sha256": "1c59027dd2f8da339e0e9a604d7310459c19a879805cc28c2bd8ac2d4cb8843e", "record_url": "https://www.alexanarch.org/non/data-provenance-initiative/", "json_url": "https://www.alexanarch.org/non/data-provenance-initiative/entity.json", "spec": "https://www.alexanarch.org/s/records/1690/", "creator": "Lee Sharks", "orcid": "0009-0000-1599-0703", "license": "CC BY 4.0" }