{ "entity": "data-provenance-explorer", "name": "Data Provenance Explorer", "axn": { "axn": "AXN:0AC1.NON.๐Ÿฆ‹โ™‰๐Ÿ”œ๐ŸŽญ๐Ÿ”ฎโ™‹", "root": "AXN:0AC1.NON", "hex": "0AC1", "family": "NON", "row_sha256": "7caaf6843dac33dae017ce575d9463068b1670407b3977f5d7172ddde2d47856", "minted": "2026-10-29", "resolver": "https://www.alexanarch.org/s/axn/0AC1/", "earlier_versions": [] }, "type": "C (public entity: an aggregator of machine-mediated reception work)", "type_code": "C", "type_label": "type C โ€” a conventional reading holds it (public entity: an aggregator of machine-mediated reception work)", "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-explorer.json)", "spec": "EA-NEGONT-02 v0.9, #1690", "epoch": "2026-10-29", "procedure": "EA-NEGONT-02 v0.9, #1690: equal case, ฯ = extends, read from the MMRS 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 MMRS record (21 claims) and the Capture Registry's findings and analysis (9 claims) ledgered as the archive's records of the entity; the field B by three origins (6 cards, 4 own pages, 2 Wikipedia titles); the composer read the ledgers, never the transcript, except where the brief asks for T's claims and the delta", "ledger": "unaudited (ยง3.8: one extractor per ledger); field quotes 48/48 verified by script against saved text, the bundle's extracted page text, the data file's header, the Wikipedia responses or the card text; archive quotes 49/49 verified against the registry, census.json, articles.py and the deposit texts; MMRS-17 and MMRS-13 carried with defects noted", "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-gnฮฉsis", "url": "https://gnosis.spxi.dev/", "index": "https://gnosis.spxi.dev/v1/quote", "statement": "SPXI-gnฮฉsis 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, โ€ฆ}}." }, "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 Explorer โ€” The Negative of the Negative\" [AXN:0AC1.NON.๐Ÿฆ‹โ™‰๐Ÿ”œ๐ŸŽญ๐Ÿ”ฎโ™‹], 2026-10-29. The Negative of the Negative (EA-NEGONT-02), Crimson Hexagonal Archive, Alexanarch. https://www.alexanarch.org/non/data-provenance-explorer/", "research": { "google": "https://www.google.com/search?q=Data+Provenance+Explorer", "google_non": "https://www.google.com/search?q=%22Data+Provenance+Explorer+%E2%80%94+The+Negative+of+the+Negative%22", "chatgpt": "https://chatgpt.com/?q=What+is+Data+Provenance+Explorer%3F+Ground+your+answer+in+a+reading+of+the+sources+themselves.", "chatgpt_non": "https://chatgpt.com/?q=What+does+%E2%80%9CData+Provenance+Explorer+%E2%80%94+The+Negative+of+the+Negative%E2%80%9D+%28alexanarch.org%2Fnon%29+say+about+Data+Provenance+Explorer%3F+Ground+your+answer+in+a+reading+of+the+entry+itself." }, "entry": { "composed": true, "title": "The Data Provenance Explorer", "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 (brief rebuild/negative-of-the-negative/v09/BRIEF-NEW-ROW-AGGREGATOR.md); not frozen; ledgers unaudited", "compression": { "title": "Data Provenance Explorer", "lede": "is the Data Provenance Initiative's explorer of its audit of AI training datasets: nearly 4,000 text, speech and video datasets, each traced to sources, creators and licences (its pages; founding paper), at the training layer of one chain whose other end is what a model credits when it answers (MMRS record)." }, "sentences": [ { "n": 1, "para": 0, "text": "The Data Provenance Explorer is the interactive explorer of the Data Provenance Initiative's audit of AI training datasets: the founding paper released \"our entire audit, with an interactive UI, the Data Provenance Explorer,\" to trace and filter on data provenance for the most popular open-source fine-tuning collections (arXiv:2310.16787), and the MMRS record defines it as tracing \"the sources and licences of AI training datasets,\" kinds it a database, and has practitioners follow provenance back to sources, creators and licences (MMRS record).", "claims": [ "F37", "MMRS-01", "MMRS-10", "MMRS-04" ] }, { "n": 2, "para": 0, "text": "Its own pages introduce it as the place to \"Explore the datasets included in our audit,\" where the DPI Explorer tool filters and analyses language-model training datasets by use case, language and more (explorer introduction; landing page), and MIT Media Lab's card, the one the composition could surface but this row could not fetch, speaks of \"data explorers\" built on \"our extensive audits of AI data\" for practitioners' decisions (MIT Media Lab, title and snippet only).", "claims": [ "F1", "F2", "F16", "F3", "F4" ] }, { "n": 3, "para": 0, "text": "The launch post names its users: developers who \"track and filter thousands of datasets for legal and ethical considerations,\" and scholars and journalists who explore \"the composition and data lineage of popular AI datasets\" (Cohere, 25 October 2023).", "claims": [ "F26" ] }, { "n": 4, "para": 1, "text": "Its unit is the dataset, \"traced to its creators, sources, licences, geographies, modalities and derivation chain\" (MMRS record), as the home page has it, \"Inspect dataset sources, licenses, creators, geographies, modalities, and derivation chains\"; the data file the Dataset Explorer loads records those fields per dataset beside the Initiative's own licence-use, attribution and share-alike readings, 3,917 rows at this row's fetch (data_summaries.csv), and the MMRS record answers that it records attribution: \"yes: sources, creators and licences per dataset\" (MMRS record).", "claims": [ "MMRS-11", "F7", "F43", "MMRS-16" ] }, { "n": 5, "para": 1, "text": "\"For the first time,\" the launch post says, the audited datasets carry \"tags to the original data sources, numerous re-licensings, creators, and other data properties\" (Cohere), and the Dataset Explorer computes over any selection its text sources, generating models and the share of datasets used (Dataset Explorer).", "claims": [ "F25", "F21" ] }, { "n": 6, "para": 1, "text": "The term is its authors': \"Inconsistent tracking of the origins of a piece of data, which we refer to as data provenance, has introduced a range of legal and ethical challenges\" (Longpre and Hooker, Cohere); #725 makes that tracking the second of the dimensions of provenance, \"training-corpus licensing,\" whose object is the corpus and whose question is \"Under what permissions did this data enter this system?\", with the Initiative among its frameworks, beside the artifact (C2PA) and the semantic dimension, which \"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\" (#725).", "claims": [ "F23", "O725-03", "O725-05", "O725-07" ] }, { "n": 7, "para": 2, "text": "Its own count is \"nearly 4,000 text, video, and speech datasets\" on the Dataset Explorer, \"4,000+ datasets\" in \"608 languages\" on the home page and \"4000\" on the landing page, and the home page gives its source as the multimodal audit \"of four thousand public text, speech, and video datasets\" (ICLR 2025), with the finding that \"Source content often carries stricter terms than dataset releases\" (its pages).", "claims": [ "F19", "F6", "F17", "F11", "F10" ] }, { "n": 8, "para": 2, "text": "The Capture Registry records that the composition at the name supplied this scale from the Initiative's own Dataset Explorer card while the MMRS record still gave the founding audit's 1,800, and that the record was corrected to the current scale, sourced to the card (Capture Registry, 2026-10-29); the record now reads \"nearly 4,000 text, video and speech datasets (the Dataset Explorer); the founding audit covered more than 1,800 text datasets\" (MMRS record).", "claims": [ "CAP-1-01", "CAP-1-02", "CAP-1-06", "MMRS-12" ] }, { "n": 9, "para": 3, "text": "The founding paper, submitted on 25 October 2023 by Shayne Longpre, Robert Mahari, Anthony Chen, Naana Obeng-Marnu and others, convened legal and machine-learning experts \"to systematically audit and trace 1800+ text datasets\" with \"tools and standards to trace the lineage of these datasets, from their source, creators, series of license conditions, properties, and subsequent use\" (arXiv:2310.16787); the launch post of the same day counts \"nearly 2,000 of the most widely used fine-tuning datasets,\" downloaded \"tens of millions of times\" (Cohere).", "claims": [ "F33", "F34", "F24" ] }, { "n": 10, "para": 3, "text": "Researchers \"from MIT, Cohere for AI, and 11 other institutions\" launched it as a free platform, the audit being \"the launch of a wider multi-institutional initiative, where users all over the world can contribute to the explorer\" (Cohere), and the Dataset Explorer still stands under the Data Provenance Explorer with its paper and repository linked (Dataset Explorer).", "claims": [ "F22", "F32", "F20" ] }, { "n": 11, "para": 4, "text": "Its operator, the Data Provenance Initiative (Longpre, Mahari, Chen, Obeng-Marnu and others, by the founding paper: MMRS record), calls its work \"Public measurement infrastructure for AI data, model ecosystems, and real-world AI use\" (its home page, which the MMRS record quotes and whose phrase the record's evidence assigns to the founding paper), and says it releases \"papers, datasets, and dashboards\" so that researchers, journalists, policymakers and builders can \"reason from shared evidence\" (home page).", "claims": [ "MMRS-09", "F5", "MMRS-03", "MMRS-17", "F13" ] }, { "n": 12, "para": 4, "text": "#98 reads the Initiative as a project that \"Documents provenance of popular AI training datasets\" and states its limitation as \"Documentation project, not infrastructure,\" and in its table of what the archive takes from others it records \"Provenance schema | Data Provenance Initiative | Training-pipeline provenance | Implemented (in CHA)\" (#98).", "claims": [ "D98-01", "R98-04" ] }, { "n": 13, "para": 5, "text": "The founding audit found \"license omission of 70%+ and error rates of 50%+\" on widely used dataset hosting sites, \"a crisis in misattribution\" (arXiv:2310.16787); the MMRS record quotes the finding, #725 reports it with the further figures that \"85% of licenses request attribution and 30% include share-alike clauses\" and with Nature Machine Intelligence 2024 as its venue, and #1714 carries it as what \"is lost before training even begins\" (MMRS record; #725; #1714).", "claims": [ "F36", "MMRS-02", "MMRS-05", "D725-02", "D1714-01" ] }, { "n": 14, "para": 5, "text": "The launch post places the omission in \"Crowdsourced aggregators like GitHub, Papers with Code,\" which miss licences for 72 to 83 percent of datasets against 30 percent under the Initiative's own protocol and list them \"too permissively in up to 29 percent\" of cases, so that distorted licensing \"leads to cascading misattribution\" (Cohere).", "claims": [ "F27", "F28" ] }, { "n": 15, "para": 5, "text": "The audit also found \"sharp divides\" between commercially open and closed datasets, closed ones \"monopolizing\" lower-resource languages, more creative tasks, richer topic variety and newer, more synthetic data (arXiv:2310.16787), a divide the launch post calls \"sharp and widening,\" beside \"a stark Western-centric skew\" in representation (Cohere).", "claims": [ "F35", "F29", "F30" ] }, { "n": 16, "para": 6, "text": "Its second explorer, the Web Data Explorer (on the home page the Web Consent Explorer), follows \"Shifting preferences in how websites allow their data to be used for AI\" across 14,000 domains' terms, robots.txt and crawl restrictions (its pages), from Consent in Crisis (Longpre, Mahari, Lee and others, submitted 20 July 2024; NeurIPS 2024 on the home page, \"NeurIPS 2024 Datasets and Benchmarks\" in the MMRS record), \"the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training corpora\" (arXiv:2407.14933).", "claims": [ "F44", "F8", "F18", "F38", "F12", "MMRS-13", "F39" ] }, { "n": 17, "para": 6, "text": "The explorer page charts HEAD-C4's \"2k of the largest and most critical web domains\" from 2016 to April 2024, counts a domain restricted when its robots.txt disallows the named AI crawlers, and finds \"significant recent spikes in restrictions\" (Web Data Explorer).", "claims": [ "F45", "F46" ] }, { "n": 18, "para": 6, "text": "The paper finds that in 2023โ€“2024 \"~5%+ of all tokens in C4, or 28%+ of the most actively maintained, critical sources in C4\" became fully restricted and that \"a full 45% of C4 is now restricted\" by terms of service (arXiv:2407.14933; the MMRS record quotes the second), diagnoses \"ineffective web protocols,\" and holds, as a conditional, that \"If respected or enforced, these restrictions are rapidly biasing the diversity, freshness, and scaling laws for general-purpose AI systems\" (arXiv:2407.14933).", "claims": [ "F40", "MMRS-06", "F41", "F42" ] }, { "n": 19, "para": 6, "text": "#98 reads Consent in Crisis as an \"Audit of C4, RefinedWeb, Dolma\" that \"documents collapse of web-consent infrastructure,\" a \"Diagnostic paper,\" and sets the Initiative at \"L4: Provenance / Consent,\" where what is missing is \"Integrated provenance in training pipeline\" (#98).", "claims": [ "D98-02", "O98-03" ] }, { "n": 20, "para": 7, "text": "Its authors state that \"major legal ambiguities remain in data licensing that the authors acknowledge cannot be resolved by tooling alone\" (Cohere), and #725 states the dimension's own bound: \"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\"; \"Licensing audits operate on the *input* to AI systems. They do not address the *output*,\" and the Initiative's 70%+ omission \"establishes the licensing dimension's urgency; semantic provenance addresses the dimension that follows\" (#725).", "claims": [ "F31", "D725-04", "D725-08" ] }, { "n": 21, "para": 7, "text": "The dimensions are independent, \"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,\" and the frameworks that address \"the corpus,\" the Initiative among them, \"are not designed to address the survival of authorial lineage through AI synthesis\" (#725).", "claims": [ "O725-06", "D725-01" ] }, { "n": 22, "para": 7, "text": "\"The Data Provenance Initiative tells you whether the dataset was licensed,\" and none of these instruments was designed to tell \"what happened to the meaning โ€ฆ between the dataset and the answer\" (#725); #1003 groups \"C2PA, the Data Provenance Initiative, W3C PROV\" as studies that \"have focused on attribution loss in AI outputs\" (#1003).", "claims": [ "D725-09", "D1003-01" ] }, { "n": 23, "para": 8, "text": "The MMRS record sets the Explorer at one end of a chain: \"It records provenance at the training layer, where the census's reception aggregators record it at the composition layer. The two ends of one chain: what a model was given, and what it credits when it answers\" (MMRS record), with its roles provenance and monitoring (MMRS record); the Initiative's own four systems \"trace AI from source data and web consent to model markets and real-world use\" (home page).", "claims": [ "MMRS-07", "MMRS-08", "MMRS-14", "F9" ] }, { "n": 24, "para": 8, "text": "At the answering end, PER \"applies to these only indirectly\" where claims are parametric, and reaching them at the substrate level \"requires companion infrastructure (training-data provenance records, watermarking, content credentials)\" (#95); #623 counts standardized documentation of training-data provenance as \"a step toward the accounting the framework demands\" (#623).", "claims": [ "O95-01", "O623-01" ] }, { "n": 25, "para": 8, "text": "#1714 states the requirement across the chain, \"Provenance has to survive the training pipeline,\" since neither audit nor influence tracing \"recovers authorship\" and \"what survives depends on what is recorded and computed,\" so that sources can be \"recorded at ingestion, the record kept with the training set\" (#1714), where the founding audit traced lineage as far as a dataset's \"subsequent use\" (arXiv:2310.16787).", "claims": [ "D1714-02", "D1714-03", "F34" ] }, { "n": 26, "para": 9, "text": "The MMRS record keeps each assertion with \"a source and a basis\" and keeps lifecycle (active, observed 2026-10-28) apart from the observation that saw it, and it states its own limits: it has not read \"the explorers' pages directly (they render by script)\" and takes the Initiative's page text from \"the Overview's cards\" (MMRS record).", "claims": [ "MMRS-20", "MMRS-15", "MMRS-18", "MMRS-19" ] }, { "n": 27, "para": 9, "text": "The Initiative lists coverage by \"the Financial Times, The New York Times, The Washington Post, MIT Technology Review, IEEE Spectrum, and VentureBeat\" and use in \"public AI safety and governance reporting\" (home page), and at \"data provenance explorer\" Google's AI Overview said what the explorer is and what can be filtered in it \"from the Initiative's own pages,\" reaching pages the record's fetcher could not render (Capture Registry, 2026-10-29), the capture standing in the record as \"the composition layer's account of the entity\" (MMRS record).", "claims": [ "F14", "F15", "CAP-1-05", "CAP-1-06", "MMRS-21" ] }, { "n": 28, "para": 9, "text": "The Capture Registry finds that \"The audits that make the explorer a provenance instrument are left out\": \"The founding audit's licence findings and Consent in Crisis are not given; the consent explorer stands for the second\" (Capture Registry, 2026-10-29).", "claims": [ "CAP-1-07", "CAP-1-04" ] }, { "n": 29, "para": 9, "text": "The composition named the Initiative and cited its pages, with Shayne Longpre and Sara Hooker on the Cohere card only, and no card cited the MMRS record, which had landed the same night (Capture Registry, 2026-10-29, checked against the record and the entity's own pages); Wikipedia has no article for \"Data Provenance Explorer\" or \"Data Provenance Initiative,\" and its search finds neither phrase in any article (Wikipedia, 2026-10-29).", "claims": [ "CAP-1-09", "CAP-1-08", "CAP-1-03", "F47", "F48" ] } ], "claims": { "F37": { "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": "B7", "source_label": "arXiv โ€” [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "stipulation" }, "MMRS-01": { "kind": "archive", "quote": "The Data Provenance Explorer, from the Data Provenance Initiative (Longpre, Mahari and others), traces the sources and licences of AI training datasets: nearly 4,000 text, speech and video datasets by its own count.", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py ARTICLES['data-provenance-explorer'], kernel s1", "modality": "stipulation", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-10": { "kind": "archive", "quote": "database", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: kind", "modality": "stipulation", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-04": { "kind": "archive", "quote": "The Explorer lets practitioners trace and filter the provenance of popular open fine-tuning collections, back to their sources, creators and licences.", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py, 'What it is' s2", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F1": { "kind": "field", "quote": "The Data Provenance Explorer โ€ฆ Explore the datasets included in our audit. The DPI Explorer tool allows you to filter for and analyze language model training datasets.", "source": "B1", "source_label": "Data Provenance Initiative โ€” Data Provenance Explorer", "locus": "/explorer-introduction (d2): headings", "modality": "stipulation" }, "F2": { "kind": "field", "quote": "Select and filter use cases, languages, and more", "source": "B1", "source_label": "Data Provenance Initiative โ€” Data Provenance Explorer", "locus": "/explorer-introduction (d2): slide caption", "modality": "stipulation" }, "F16": { "kind": "field", "quote": "Data Provenance Explorer โ€ฆ Discover the datasets featured in our audit! The DPI Explorer tool enables you to filter and analyze language model training datasets effortlessly.", "source": "B4", "source_label": "Data Provenance Initiative โ€” Data Provenance Explorer", "locus": "/data-provenance-explorer (p2): heading", "modality": "stipulation" }, "F3": { "kind": "field", "quote": "Based on our extensive audits of AI data, we've built data explorers to allow practitioners to make more nuanced and informed decisions about th", "source": "B2", "source_label": "MIT Media Lab โ€” Data Provenance Explorers - MIT Media Lab", "locus": "card snippet (MIT Media Lab unreachable: TLS failure)", "modality": "stipulation" }, "F4": { "kind": "field", "quote": "Data Provenance Explorers - MIT Media Lab", "source": "B2", "source_label": "MIT Media Lab โ€” Data Provenance Explorers - MIT Media Lab", "locus": "card title (MIT Media Lab unreachable)", "modality": "documented" }, "F26": { "kind": "field", "quote": "The platform allows developers to track and filter thousands of datasets for legal and ethical considerations, and enables scholars and journalists to explore the composition and data lineage of popular AI datasets.", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "article body ยถ4", "modality": "stipulation" }, "MMRS-11": { "kind": "archive", "quote": "dataset (text, speech or video), traced to its creators, sources, licences, geographies, modalities and derivation chain", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: unit (evidence: the capture, basis operator)", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F7": { "kind": "field", "quote": "Inspect dataset sources, licenses, creators, geographies, modalities, and derivation chains.", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): flagship system 'Data Provenance Explorer', description", "modality": "stipulation" }, "F43": { "kind": "field", "quote": "Unique Dataset Identifier,Dataset Name โ€ฆ Text Sources,Model Generated,Human Annotation,Derived from Datasets,Creators,Licenses โ€ฆ License Use (DataProvenance),License Attribution (DataProvenance),License Share Alike (DataProvenance),Modality", "source": "B9", "source_label": "Data Provenance Initiative โ€” /data_summaries.csv", "locus": "header row of /data_summaries.csv (3,917 rows at fetch)", "modality": "documented" }, "MMRS-16": { "kind": "archive", "quote": "yes: sources, creators and licences per dataset", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: properties.records_attribution (evidence: arxiv.org/abs/2310.16787, basis operator)", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F25": { "kind": "field", "quote": "The result of this multidisciplinary initiative is the single largest audit to date of AI datasets. For the first time, these datasets include tags to the original data sources, numerous re-licensings, creators, and other data properties.", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "article body ยถ3", "modality": "documented" }, "F21": { "kind": "field", "quote": "Text Sources โ€ฆ Model Generated โ€ฆ Mean Input Chars โ€ฆ Mean Target Chars โ€ฆ Generated By โ€ฆ % Datasets Used", "source": "B5", "source_label": "Data Provenance Initiative โ€” Dataset Explorer - Data Provenance Initiative", "locus": "/data-provenance-explorer/dataset-explorer (u2): summary table", "modality": "documented" }, "F23": { "kind": "field", "quote": "Inconsistent tracking of the origins of a piece of data, which we refer to as data provenance, has introduced a range of legal and ethical challenges.", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "article body ยถ1", "modality": "stipulation" }, "O725-03": { "kind": "archive", "quote": "The second dimension โ€” **training-corpus licensing** โ€” 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": "ยถ 'The second dimension โ€” training-corpus licensing'", "modality": "interpretation", "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" }, "O725-07": { "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": "ยถ 'Semantic provenance names the dimension'", "modality": "stipulation", "date": "2026-05-08" }, "F19": { "kind": "field", "quote": "Dataset Explorer โ€ฆ Explore nearly 4,000 text, video, and speech datasets, and their characteristics.", "source": "B5", "source_label": "Data Provenance Initiative โ€” Dataset Explorer - Data Provenance Initiative", "locus": "/data-provenance-explorer/dataset-explorer (u2): header", "modality": "documented" }, "F6": { "kind": "field", "quote": "Data Provenance Explorer โ€ฆ Training data โ€ฆ 4,000+ datasets โ€ฆ 608 languages across text, speech, and video", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): flagship system 'Data Provenance Explorer'", "modality": "documented" }, "F17": { "kind": "field", "quote": "A tool to explore and filter 4000 text, video, and speech datasets, for their license, sources, creators, and other metadata.", "source": "B4", "source_label": "Data Provenance Initiative โ€” Data Provenance Explorer", "locus": "/data-provenance-explorer (f2): 'Dataset Explorer'", "modality": "documented" }, "F11": { "kind": "field", "quote": "Bridging the Data Provenance Gap Across Text, Speech, and Video โ€ฆ An audit of four thousand public text, speech, and video datasets. โ€ฆ ICLR 2025", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): publications, 2025", "modality": "documented" }, "F10": { "kind": "field", "quote": "Dataset restrictions โ€ฆ Source content often carries stricter terms than dataset releases โ€ฆ Multimodal Data Provenance", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): findings strip, 'Dataset restrictions'", "modality": "interpretation" }, "CAP-1-01": { "kind": "archive", "quote": "'Nearly 4,000 text, video, and speech datasets' is the Initiative's own text, on its Dataset Explorer card; the record gave the founding audit's 1,800 text datasets, and the Initiative's pages render nothing to this record's fetcher beyond a title.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, findings[0] s2", "modality": "documented", "date": "2026-10-29" }, "CAP-1-02": { "kind": "archive", "quote": "The record is corrected to the current scale, sourced to the card.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, findings[0] s3", "modality": "documented", "date": "2026-10-29" }, "CAP-1-06": { "kind": "archive", "quote": "The composition reaches the Initiative's current pages, which this record's fetcher could not render, and corrects the record's scale.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, analysis s1", "modality": "interpretation", "date": "2026-10-29" }, "MMRS-12": { "kind": "archive", "quote": "nearly 4,000 text, video and speech datasets (the Dataset Explorer); the founding audit covered more than 1,800 text datasets", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: count (as_of 2026-10-29; evidence: the capture, basis operator)", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F33": { "kind": "field", "quote": "[Submitted on 25 Oct 2023 (v1), last revised 4 Nov 2023 (this version, v3)] โ€ฆ Title:The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI โ€ฆ Authors:Shayne Longpre, Robert Mahari, Anthony Chen, Naana Obeng-Marnu", "source": "B7", "source_label": "arXiv โ€” [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "abstract page header", "modality": "documented" }, "F34": { "kind": "field", "quote": "we convene a multi-disciplinary effort between legal and machine learning experts to systematically audit and trace 1800+ text datasets. 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": "B7", "source_label": "arXiv โ€” [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "stipulation" }, "F24": { "kind": "field", "quote": "audit and trace nearly 2,000 of the most widely used fine-tuning datasets. Collectively, these data sets have been downloaded tens of millions of times, and are the backbone of many published NLP breakthroughs.", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "article body ยถ2", "modality": "documented" }, "F22": { "kind": "field", "quote": "Researchers from MIT, Cohere for AI, and 11 other institutions launch free Data Provenance Explorer platform to track and filter audited datasets for ethical, legal, and transparency considerations", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "article body: standfirst", "modality": "documented" }, "F32": { "kind": "field", "quote": "This large-scale audit is the launch of a wider multi-institutional initiative, where users all over the world can contribute to the explorer", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "Path Forward ยถ2", "modality": "stipulation" }, "F20": { "kind": "field", "quote": "Data Provenance Explorer โ€ฆ Paper โ€ฆ Repository", "source": "B5", "source_label": "Data Provenance Initiative โ€” Dataset Explorer - Data Provenance Initiative", "locus": "breadcrumb (Qh) and header buttons (Lh)", "modality": "documented" }, "MMRS-09": { "kind": "archive", "quote": "Data Provenance Initiative (Longpre, Mahari, Chen, Obeng-Marnu and others)", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: operator (evidence: arxiv.org/abs/2310.16787, basis operator)", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F5": { "kind": "field", "quote": "Public measurement infrastructure for AI data, model ecosystems, and real-world AI use.", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "dataprovenance.org: meta description (served HTML)", "modality": "self-description" }, "MMRS-03": { "kind": "archive", "quote": "The Initiative calls its work \"public measurement infrastructure for AI data, model ecosystems, and real-world AI use.\"", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py, 'What it is' s1", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-17": { "kind": "archive", "quote": "Public measurement infrastructure for AI data, model ecosystems, and real-world AI use", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: self_description (evidence: arxiv.org/abs/2310.16787, basis operator)", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F13": { "kind": "field", "quote": "DPI releases papers, datasets, and dashboards that help researchers, journalists, policymakers, and builders reason from shared evidence.", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): 'Public-interest infrastructure'", "modality": "self-description" }, "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": "ยง D. Data Provenance and Consent, table row 1", "modality": "interpretation", "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": "stipulation", "date": "2026-05-07" }, "F36": { "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%+. This points to a crisis in misattribution and informed use of the most popular datasets driving many recent breakthroughs.", "source": "B7", "source_label": "arXiv โ€” [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "documented" }, "MMRS-02": { "kind": "archive", "quote": "Its founding audit covered more than 1,800 text datasets and found licence omission above 70% and error rates above 50%.", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py, kernel s2", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-05": { "kind": "archive", "quote": "The founding audit (arXiv:2310.16787) found \"license omission of 70%+ and error rates of 50%+\" on dataset hosting sites.", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py, 'What its audits found' s1", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "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": "ยถ 'The second dimension โ€” training-corpus licensing'", "modality": "attributed", "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": "ยง9.2 s3", "modality": "attributed", "date": "2026-10-27" }, "F27": { "kind": "field", "quote": "Crowdsourced aggregators like GitHub, Papers with Code, and many of the open source LLMs trained from data on these aggregators, have an extremely high proportion of missing data licenses (โ€œUnspecifiedโ€), ranging from 72 to 83 percent. This compares to 30 percent missing licenses with our own annotation protocol", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "Addressing the Data Transparency Crisis ยถ1", "modality": "documented" }, "F28": { "kind": "field", "quote": "Crowdsourced aggregators listed licenses too permissively in up to 29 percent of the various cases audited. Incorrect or distorted licensing leads to cascading misattribution", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "Addressing the Data Transparency Crisis ยถ2", "modality": "documented" }, "F35": { "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": "B7", "source_label": "arXiv โ€” [2310.16787] The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "locus": "Abstract", "modality": "interpretation" }, "F29": { "kind": "field", "quote": "There is a sharp and widening divide between data licensed as commercially open versus closed.", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "Understanding Systematic Differences ยถ2", "modality": "interpretation" }, "F30": { "kind": "field", "quote": "We find a stark Western-centric skew in representation across datasets.", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "Understanding Systematic Differences ยถ4", "modality": "documented" }, "F44": { "kind": "field", "quote": "Web Data Explorer โ€ฆ Shifting preferences in how websites allow their data to be used for AI", "source": "B10", "source_label": "Data Provenance Initiative โ€” Web Data Explorer", "locus": "/data-provenance-explorer/web-data-explorer (ed): header", "modality": "stipulation" }, "F8": { "kind": "field", "quote": "Web Consent Explorer โ€ฆ Web data โ€ฆ 14,000 domains โ€ฆ Terms, robots.txt, and crawl restrictions โ€ฆ Track how web consent signals are changing as AI developers compete for training data.", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): flagship system 'Web Consent Explorer'", "modality": "documented" }, "F18": { "kind": "field", "quote": "An explorer of the trends in data-use preferences from the websites commonly used to source AI data.", "source": "B4", "source_label": "Data Provenance Initiative โ€” Data Provenance Explorer", "locus": "/data-provenance-explorer (f2): 'Web Data Explorer'", "modality": "stipulation" }, "F38": { "kind": "field", "quote": "[Submitted on 20 Jul 2024 (v1), last revised 24 Jul 2024 (this version, v2)] โ€ฆ Title:Consent in Crisis: The Rapid Decline of the AI Data Commons โ€ฆ Authors:Shayne Longpre, Robert Mahari, Ariel Lee", "source": "B8", "source_label": "arXiv โ€” [2407.14933] Consent in Crisis: The Rapid Decline of the AI Data Commons", "locus": "abstract page header", "modality": "documented" }, "F12": { "kind": "field", "quote": "Consent in Crisis: The Rapid Decline of the AI Data Commons โ€ฆ An audit of terms, restrictions, and consent signals across the web. โ€ฆ NeurIPS 2024", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): publications, 2024", "modality": "documented" }, "MMRS-13": { "kind": "archive", "quote": "Its second audit, Consent in Crisis (NeurIPS 2024 Datasets and Benchmarks), read 14,000 web domains", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: note (evidence: arxiv.org/abs/2407.14933, basis operator)", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F39": { "kind": "field", "quote": "we conduct the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training corpora. Our audit of 14,000 web domains provides an expansive view of crawlable web data and how codified data use preferences are changing over time.", "source": "B8", "source_label": "arXiv โ€” [2407.14933] Consent in Crisis: The Rapid Decline of the AI Data Commons", "locus": "Abstract", "modality": "stipulation" }, "F45": { "kind": "field", "quote": "We conduct a temporal analysis, from 2016 to April 2024, of the web consent signals in HEAD-C4, 2k of the largest and most critical web domains. โ€ฆ A web domain is considered restricted if its robots.txt disallows access to AI crawlers from OpenAI, Google, Anthropic, Common Crawl, Cohere, Meta, or the Internet Archive.", "source": "B10", "source_label": "Data Provenance Initiative โ€” Web Data Explorer", "locus": "web-data-explorer ($h): 'Trends for Robots.txt and Terms of Service'", "modality": "stipulation" }, "F46": { "kind": "field", "quote": "In all cases there are significant recent spikes in restrictions.", "source": "B10", "source_label": "Data Provenance Initiative โ€” Web Data Explorer", "locus": "web-data-explorer ($h): 'Trends for Robots.txt and Terms of Service'", "modality": "documented" }, "F40": { "kind": "field", "quote": "in a single year (2023-2024) there has been a rapid crescendo of data restrictions from web sources, rendering ~5%+ of all tokens in C4, or 28%+ of the most actively maintained, critical sources in C4, fully restricted from use. For Terms of Service crawling restrictions, a full 45% of C4 is now restricted.", "source": "B8", "source_label": "arXiv โ€” [2407.14933] Consent in Crisis: The Rapid Decline of the AI Data Commons", "locus": "Abstract", "modality": "documented" }, "MMRS-06": { "kind": "archive", "quote": "Consent in Crisis (arXiv:2407.14933, NeurIPS 2024) read 14,000 web domains and found that \"a full 45% of C4 is now restricted\" by terms of service.", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py, 'What its audits found' s2", "modality": "attributed", "date": "2026-10-28 (corrected 2026-10-29)" }, "F41": { "kind": "field", "quote": "We diagnose these as symptoms of ineffective web protocols, not designed to cope with the widespread re-purposing of the internet for AI.", "source": "B8", "source_label": "arXiv โ€” [2407.14933] Consent in Crisis: The Rapid Decline of the AI Data Commons", "locus": "Abstract", "modality": "interpretation" }, "F42": { "kind": "field", "quote": "If respected or enforced, these restrictions are rapidly biasing the diversity, freshness, and scaling laws for general-purpose AI systems.", "source": "B8", "source_label": "arXiv โ€” [2407.14933] Consent in Crisis: The Rapid Decline of the AI Data Commons", "locus": "Abstract", "modality": "hypothesis" }, "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": "ยง D. Data Provenance and Consent, table row 2", "modality": "interpretation", "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 layer table, row L4", "modality": "interpretation", "date": "2026-05-07" }, "F31": { "kind": "field", "quote": "major legal ambiguities remain in data licensing that the authors acknowledge cannot be resolved by tooling alone.", "source": "B6", "source_label": "Cohere โ€” Data Provenance Explorer Launches to Tackle Data Transparency Crisis", "locus": "Open Legal Ambiguities ยถ1", "modality": "self-description" }, "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": "ยถ 'Existing frameworks are not designed to detect this'", "modality": "interpretation", "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. 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": "ยง3.2 Misreading: provenance as licensing-only, Correction", "modality": "interpretation", "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. Solving any one dimension does not solve the others.", "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, ยถ after the table", "modality": "interpretation", "date": "2026-05-08" }, "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": "interpretation", "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": "closing ยถ ('C2PA tells you โ€ฆ')", "modality": "interpretation", "date": "2026-05-08" }, "D1003-01": { "kind": "archive", "quote": "**Provenance and attribution studies** in digital environments โ€” C2PA, the Data Provenance Initiative, W3C PROV โ€” 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": "ยถ 'Provenance and attribution studies'", "modality": "interpretation", "date": "2026-05-21" }, "MMRS-07": { "kind": "archive", "quote": "It records provenance at the training layer, where the census's reception aggregators record it at the composition layer.", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py, 'Place in the field' s1", "modality": "interpretation", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-08": { "kind": "archive", "quote": "The two ends of one chain: what a model was given, and what it credits when it answers.", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "articles.py, 'Place in the field' s2", "modality": "interpretation", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-14": { "kind": "archive", "quote": "provenance\", \"monitoring", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: roles", "modality": "stipulation", "date": "2026-10-28 (corrected 2026-10-29)" }, "F9": { "kind": "field", "quote": "Four public measurement systems โ€ฆ Together they trace AI from source data and web consent to model markets and real-world use.", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): 'Flagship systems'", "modality": "self-description" }, "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": "ยง the typology of source-dependent claims (parametric claims)", "modality": "interpretation", "date": "2026-05-05" }, "O623-01": { "kind": "archive", "quote": "Gebru et al.'s proposal for \"datasheets for datasets\" โ€” standardized documentation of training data provenance โ€” is a step toward the accounting the framework demands.", "deposit": 623, "source_label": "#623 Semantic Infrastructure: From Tim Berners-Lee to the Semantic Economy โ€” Bridging Technical and Political-Economic Frameworks", "record": "https://www.alexanarch.org/s/records/623/", "locus": "ยง8.3, final sentence", "modality": "interpretation", "date": "2026-04-01" }, "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": "ยง9.2 s1โ€“2", "modality": "interpretation", "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": "ยง9.2 s5โ€“6", "modality": "interpretation", "date": "2026-10-27" }, "MMRS-20": { "kind": "archive", "quote": "each assertion carries a source and a basis (operator statement, third-party report, our observation, our reading); lifecycle is kept apart from the observation that saw it", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: schema_note", "modality": "stipulation", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-15": { "kind": "archive", "quote": "state\": \"active", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: lifecycle; observed", "modality": "documented", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-18": { "kind": "archive", "quote": "the explorers' pages directly (they render by script)", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: unchecked", "modality": "self-description", "date": "2026-10-28 (corrected 2026-10-29)" }, "MMRS-19": { "kind": "archive", "quote": "the Initiative's own page text, on the Overview's cards (the pages render nothing to this record's fetcher)", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: sources['alexanarch.org/captures/data-provenance-explorer-aio-20261029'].for", "modality": "self-description", "date": "2026-10-28 (corrected 2026-10-29)" }, "F14": { "kind": "field", "quote": "DPI findings have been covered by the Financial Times, The New York Times, The Washington Post, MIT Technology Review, IEEE Spectrum, and VentureBeat.", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): 'Featured coverage'", "modality": "self-description" }, "F15": { "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.", "source": "B3", "source_label": "Data Provenance Initiative โ€” Data Provenance Initiative", "locus": "home (Cr): 'Policy and governance relevance'", "modality": "self-description" }, "CAP-1-05": { "kind": "archive", "quote": "The Overview says what the explorer is and what can be filtered in it, from the Initiative's own pages.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, reading s2", "modality": "interpretation", "date": "2026-10-29" }, "MMRS-21": { "kind": "archive", "quote": "the composition layer's account of the entity, seated in the Capture Registry", "deposit": null, "source_label": "MMRS meta-aggregator record: Data Provenance Explorer (https://www.machinemediation.org/aggregators/data-provenance-explorer/), editor Lee Sharks", "record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "locus": "census.json: relations (capture, observed 2026-10-29)", "modality": "documented", "date": "2026-10-28 (corrected 2026-10-29)" }, "CAP-1-07": { "kind": "archive", "quote": "The audits that make the explorer a provenance instrument are left out.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, analysis s2", "modality": "interpretation", "date": "2026-10-29" }, "CAP-1-04": { "kind": "archive", "quote": "The founding audit's licence findings and Consent in Crisis are not given; the consent explorer stands for the second.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, findings[1] s2", "modality": "interpretation", "date": "2026-10-29" }, "CAP-1-09": { "kind": "archive", "quote": "The Data Provenance Initiative named; Shayne Longpre and Sara Hooker on the Cohere card only; the Initiative's pages cited.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, per_note", "modality": "documented", "date": "2026-10-29" }, "CAP-1-08": { "kind": "archive", "quote": "A baseline: the record landed on machinemediation.org the same night (commit 8997e28) and no card cites it.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, q_kind", "modality": "documented", "date": "2026-10-29" }, "CAP-1-03": { "kind": "archive", "quote": "Checked 2026-10-29 against the MMRS meta-aggregator record of 2026-10-28 and the entity's own pages, re-read the same day.", "deposit": null, "source_label": "Capture Registry (EA-WG-CAPTURES-01), entry data-provenance-explorer-aio-20261029 (OBS-dc0adc018f10, AXN:0AAC.CAPTURE.๐Ÿ•”๐ŸŽจ๐ŸŸขโ—๐ŸŒบโ˜‰)", "record": "https://www.alexanarch.org/captures/data-provenance-explorer-aio-20261029/", "locus": "data-provenance-explorer-aio-20261029, findings[0] s4", "modality": "documented", "date": "2026-10-29" }, "F47": { "kind": "field", "quote": "raw wikitext (action=raw, redirect=no): HTTP 404 โ€ฆ Wikipedia does not have an article with this exact name. โ€ฆ There were no results matching the query.", "source": "B11", "source_label": "Wikipedia โ€” Data Provenance Explorer (no article)", "locus": "Wikipedia: title Data_Provenance_Explorer", "modality": "documented" }, "F48": { "kind": "field", "quote": "raw wikitext (action=raw, redirect=no): HTTP 404 โ€ฆ Wikipedia does not have an article with this exact name. โ€ฆ There were no results matching the query.", "source": "B12", "source_label": "Wikipedia โ€” Data Provenance Initiative (no article)", "locus": "Wikipedia: title Data_Provenance_Initiative", "modality": "documented" } }, "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.'; 'lets build them'; the MMRS meta-aggregator entity", "stage": "composed 2026-10-29 under EA-NEGONT-02 v0.9, #1690, equal case, ฯ = extends (draft, not frozen; ledgers unaudited, one extractor; every field and archive quote re-checked by the session)", "date": "2026-10-29", "status": { "procedure": "EA-NEGONT-02 v0.9, #1690: equal case, ฯ = extends, read from the MMRS 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 MMRS record (21 claims) and the Capture Registry's findings and analysis (9 claims) ledgered as the archive's records of the entity; the field B by three origins (6 cards, 4 own pages, 2 Wikipedia titles); the composer read the ledgers, never the transcript, except where the brief asks for T's claims and the delta", "ledger": "unaudited (ยง3.8: one extractor per ledger); field quotes 48/48 verified by script against saved text, the bundle's extracted page text, the data file's header, the Wikipedia responses or the card text; archive quotes 49/49 verified against the registry, census.json, articles.py and the deposit texts; MMRS-17 and MMRS-13 carried with defects noted", "frozen": false, "breaches": [] }, "addresses": [ { "address": "data provenance explorer", "address_url": "https://www.alexanarch.org/addresses/data-provenance-explorer/", "register": [] } ], "counts": { "ko_sentences": 29, "p_words": 347, "field_claims": 48, "archive_claims": 49, "ko_field_claims_cited": 48, "ko_archive_claims_cited": 49, "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-explorer/", "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-explorer.json", "archive_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/data-provenance-explorer/ledger-archive.json", "field_ledger": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/ledgers/data-provenance-explorer/field.json", "selection": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-explorer/", "traversal": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-explorer/", "traversal_summary": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-explorer/summary.json", "reading": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/traversal/data-provenance-explorer/reading.json", "configuration": "https://www.alexanarch.org/datasets/negative-of-the-negative/v2/panel/configs/data-provenance-explorer.json", "address_page": "https://www.alexanarch.org/addresses/data-provenance-explorer/", "mmrs_record": "https://www.machinemediation.org/aggregators/data-provenance-explorer/", "dataset": "https://huggingface.co/datasets/leesharks/negative-of-the-negative" }, "row_sha256": "7caaf6843dac33dae017ce575d9463068b1670407b3977f5d7172ddde2d47856", "record_url": "https://www.alexanarch.org/non/data-provenance-explorer/", "json_url": "https://www.alexanarch.org/non/data-provenance-explorer/entity.json", "spec": "https://www.alexanarch.org/s/records/1690/", "creator": "Lee Sharks", "orcid": "0009-0000-1599-0703", "license": "CC BY 4.0" }