Monday, October 12, 2026

AI Overview Capture Registry — EA-WG-CAPTURES-01 v12.167 — 633 semantic addresses, 811 captures, 2026-06-07 to 2026-10-12 Sharks, Lee · 2026-10-12 · Longitudinal dataset snapshot · v12.167 AXN:06F2.EMPIRICAL.🪟▽🌺🔥🍄🪄

 Alexanarch

AXN:06F2.EMPIRICAL.🪟▽🌺🔥🍄🪄

AI Overview Capture Registry — EA-WG-CAPTURES-01 v12.167 — 633 semantic addresses, 811 captures, 2026-06-07 to 2026-10-12

Sharks, Lee · 2026-10-12 · Longitudinal dataset snapshot · v12.167
Deposit accountability: Lee Sharks, ORCID 0009-0000-1599-0703
Substrate: AI-assisted (substrate). Snapshot assembled, counted and written in session by TACHYON (Claude, Anthropic) under MANUS (Lee Sharks) direction, from the canonical store at v12.167. The captures themselves were taken by the operator on the surfaces named in each record.
License: CC-BY-4.0
↓ Download MD ↓ PDF
AI Overview Capture RegistryEA-WG-CAPTURES-01machine-mediated receptionprovenance erasure ratesemantic addresscapture registrylongitudinal datasetAI OverviewChatGPTrecord-page promptcomposition layerentity resolutionadoptionversioned snapshotMMRS
Search this title ↗ (exact match) · Ask ChatGPT ↗ — a composition either forces can be seated in the Capture Registry.

Description

Versioned snapshot of the AI Overview Capture Registry (EA-WG-CAPTURES-01) at v12.167, continuing the deposit chain from v6.0 through v10.9 (#1461), which it supersedes. A longitudinal instrument for recording dated machine-mediated reception events: what composition layers make of a named entity when asked for it at a specific semantic address, on a specific date, in a specific authentication state. 633 semantic addresses carry 811 captures across 84 dates; 792 carry a verbatim transcript and 328 a frame; 505 are scored for Provenance Erasure Rate, at a mean of 0.506 (0.603 at v10.9). Surfaces: Google AI Overview 490, ChatGPT across its recorded labels 167, Google AI Mode 12, Grok 7, Bing Copilot 6, Perplexity 5, Claude 3, Qwen 2, Google Knowledge panel 2, seven single-capture surfaces, and 110 whose surface is undetermined, unresolved or unrecorded. The core data travels as one bundle with its SHA-256; the 469 capture frames are manifested at their canonical paths rather than duplicated. Known defects are recorded as data, not repaired.

Wiki Article

AI Overview Capture Registry — EA-WG-CAPTURES-01 v12.167 is a versioned snapshot of the Crimson Hexagonal Archive's longitudinal reception instrument, deposited by Lee Sharks on 12 October 2026. It supersedes v10.9 (#1461). It records 633 semantic addresses carrying 811 dated captures across 84 dates, spanning 7 June to 12 October 2026. The registry documents what machine composition layers make of a named entity when asked for it at a specific semantic address, on a specific date, in a specific authentication state. Each capture records the exact issued string, the surface, the evidence class, the returned source strip with each source's relation to the archive, a verbatim transcript where obtainable, a match type and a Provenance Erasure Rate. 792 captures carry a transcript and 328 a frame; 505 are PER-scored at a mean of 0.506, against 0.603 at v10.9. The citable unit is the capture — one surface, one semantic address, one date. Each address has had its own page since 25 September 2026, and is the right unit when a claim concerns the address rather than one system's behaviour. Between v10.9 and this edition the instrument changed in five ways. The canonical store moved from the rebuild file to the projection (`data/EA-WG-CAPTURES-01.json`) on 17 August, and the rebuild store was sealed. ChatGPT grew from 3 captures to 167, and Grok, Perplexity, Claude and Qwen entered. Source chips became data. A coverage audit (#1614) made the transcript count monotone. And on 12 October, 43 deposits were captured at their own record pages' Ask ChatGPT prompts, signed out: the author was retained in all 43, the archive in 27 and the identifier in 22. The core data is attached as an 18.7 MB bundle with a SHA-256. Its 469 capture frames are manifested at their canonical paths rather than duplicated. Known defects — two addresses declaring more observations than they hold, twelve PER scores inconsistent with their markers, four captures with no surface recorded — are listed in the record and not repaired, since repair runs in its own mode.
Also published as a standalone entry: /s/wiki/1676/

Concepts Defined

the capture as citable unit
semantic address
provenance erasure rate
match type
adoption
the reading canon
intake versus repair
evidence class
the address slug caveat
surface discrimination

Full Text

AI Overview Capture Registry — EA-WG-CAPTURES-01 v12.167 — 633 semantic addresses, 811 captures, 2026-06-07 to 2026-10-12

AI Overview Capture Registry — EA-WG-CAPTURES-01 v12.167

633 semantic addresses · 811 captures · 84 dates · 2026-06-07 to 2026-10-12

Lee Sharks · ORCID 0009-0000-1599-0703 · 12 October 2026 · supersedes v10.9 (#1461)

1. The citable unit

ONE SURFACE + ONE SEMANTIC ADDRESS + ONE DATE = ONE CAPTURE.

  • The capture is citable at captures/{slug}/. Cite it for what a named system did.
  • The address is citable at addresses/{slug}/. Cite it for what the address does across surfaces or over time.

Each address has had its own page since 2026-09-25. That page is the unit a fetcher can read whole, which the gallery is not. An address's slug is inherited from the first capture seated at it and is never renamed.

2. State at v12.167

Sections, by address count:

SectionAddresses
Machine Reception107
Heteronyms77
Frameworks63
Archive56
Coinages38
Semantic Economy37
Works35
Revelation & Theology32
Classics & Philology28
Provenance & Erasure24
Institutions23
Valuation17
Sites15
∮ = 115
Reference & General Knowledge12
Architecture11
People11
Projects11
Operative Semiotics10
Platform Erosion9
Disciplines1
Revelation First1

Surfaces, by capture count:

SurfaceCaptures
Google AI Overview490
ChatGPT (all recorded labels: 119 + 27 Luna 5.6 + 12 Luna + 8 chatgpt.com + 1 web, logged out)167
Undetermined56
Unresolved50
Google AI Mode12
Grok7
Bing Copilot6
Perplexity (one agentic)5
Claude3
Qwen2
Google Knowledge panel2
Single-capture surfaces (Gemini, Google Scholar, a Google results page with no AI surface, Bing Copilot Search popup, ScholaRef, SciLynk, TikTok Studio)7
Surface not recorded at the capture4

Authentication state: signed in 223; signed out and incognito (both spellings) 251; incognito 124; signed out 74; unrecorded 91; other recorded states 48.

Evidence: 792 captures carry a verbatim transcript and 328 carry a frame. 505 are scored for PER, at a mean of 0.506; at v10.9 the mean was 0.603.

3. The data flow

Since 2026-08-17 (ratified, MANUS), data/EA-WG-CAPTURES-01.json is the single writable authority. The rebuild store (rebuild/capture-registry/EA-WG-CAPTURES-01-REBUILD.json) is sealed as the rebuild-era source, last written 2026-08-18. This corrects v10.9's account of the data flow, which named the rebuild as canonical; that was accurate at its date.

The seat runs in this order:

1. scripts/capture_intake.py --seat

2. scripts/build_capture_gallery.py

3. scripts/seat_capture_postflight.py, which links, bakes, gates (the runtime gate executes the page scripts), builds the semantic-address layer and publishes addresses/{slug}/, then syncs and cites.

Each batch of intake is kept as rebuild/capture-registry/intake-YYYYMMDD-*/.

4. Files

The core data bundle is EA-WG-CAPTURES-01-v12.167.tar.gz (18,662,466 bytes; SHA-256 ce2c510cc2bd91926cebd71c094c5a13f1f14198a04ea44609477b2e40305548). It holds:

  • data/EA-WG-CAPTURES-01.json, the canonical store;
  • rebuild/capture-registry/: the pipeline documents, the intake directories and the sealed rebuild store;
  • data/capture-deposit-links.json;
  • data/semantic-addresses.json;
  • datasets/capture-registry/;
  • captures/index.html.

manifest.json lists 478 files with SHA-256, bytes, media type and role: the eight core files, the bundle, and the 469 capture frames (179.2 MB), which are manifested at their canonical paths under data/captures/{slug}/ rather than duplicated. This follows the registry's rule: images are held there, and galleries display them rather than host them. Total manifested: 269.4 MB.

5. Version chain

v6.0 (#825) → v6.1 (#1397) → v7.0 (#1398) → v7.2 (#1396, #1401) → v8.3 (#3) → v8.9 (#936) → v10.9 (#1461) → v12.167 (this deposit)

Between v10.9 and v12.167 the registry went from 328 addresses and 470 captures to 633 and 811. The intervening minor versions are recorded in the canonical file, not as separate deposits.

6. What changed in the instrument since v10.9

1. Canonical authority moved from the rebuild store to the projection (2026-08-17).

2. Address pages. Every address has a page of its own (2026-09-25).

3. Surfaces widened. At v10.9, ChatGPT accounted for 3 captures; it now accounts for 167. The registry also holds Google AI Mode, Grok, Bing Copilot, Perplexity, Claude and Qwen.

4. Source chips are data. Each chip is recorded with its relation to the archive and carries into the PER notes. What Enters Composition Through the Cards (#1612) profiles source admission across June–September.

5. The transcript is the capture. #1614 audited transcript coverage and installed the gate that keeps the count monotone.

6. The record-page run (2026-10-12). 43 deposits, from #1421 to #1675, were captured at their own record pages' Ask ChatGPT prompts, signed out and incognito. The author was retained in all 43, the archive in 27, the identifier in 22. Mean PER was 0.22, with one score excluded (see §7).

7. Known defects at v12.167, recorded as data

Defect counts, as the registry declares them:

DefectCount
citations-null166
analysis-without-finding152
truncated-by-interface126
surface-unresolved50
unsupported-citations10
date-unresolved3

Declared but not held. Two addresses declare more observations than they hold, so the registry counts 813 observations and holds 811:

  • operative-semiotics-20260610 declares 4 and holds 3.
  • operational-semiotics-bing-copilot-20260823 declares 2 and holds 1.

PER against its markers. Twelve captures carry all four PER markers true with PER 1.0:

  • Ten were seated on 2026-08-13. The marker convention of that seating is not yet verified.
  • Two were seated this month, under the convention where true means retained, and are inconsistent with it: dedication-what-syllogizing-can-divide-chatgpt-20261011 and missing-translator-ask-chatgpt-20261012.

Surface not recorded. Four captures carry no surface label at the capture. They are counted here as unrecorded and not assigned.

None of these is repaired in this snapshot. Repair is its own mode.

Attachments 2 files

Files deposited with this record, below the work they belong to. Each is served at its own URL and carries its SHA-256.

↓ EA-WG-CAPTURES-01-v12.167.tar.gz (17.8 MB) ↓ manifest.json (165 KB)
sha256 ce2c510cc2bd91926cebd71c094c5a13f1f14198a04ea44609477b2e40305548
sha256 dda99475b27910d84c150f01f422afb020f2cf974affc9133d4256098ce18bb8

External Metadata

DataCite severance status: —
External metadata recovered post-severance (non-authoritative). The sidecar maps each DOI to its locator in the bulk data stores.

Version history

Series: ea-wg-captures

Traversal

In the registry: 2026-10 · EMPIRICAL · all deposits

No comments:

Post a Comment