chore: daily update 2026-08-13

This commit is contained in:
OpenWiki Bot
2026-08-13 02:19:02 +08:00
parent c57ead4bf1
commit 8ddc6d9559
14 changed files with 274 additions and 91 deletions
+1 -1
View File
@@ -1,5 +1,5 @@
{
"updatedAt": "2026-08-10T18:09:51.993Z",
"updatedAt": "2026-08-12T18:16:59.273Z",
"command": "update",
"model": "MiniMax-M3",
"status": "complete",
+8 -1
View File
@@ -2,7 +2,7 @@
type: "Reference"
title: "Commitments"
description: "Active work tasks, follow-ups, approvals, and scheduled items extracted from sources (web-search, git-repo, literature flywheel-sync, etc.). Personal errands live in /personal-logistics.md instead."
tags: [commitments, work, follow-ups, distributors-2026-08-07-refresh, dong-huiqun-ji-nan-chengquan-link]
tags: [commitments, work, follow-ups, distributors-2026-08-07-refresh, dong-huiqun-ji-nan-chengquan-link, liang-2026-celvivo-clinostar-positioning]
---
# Commitments
@@ -88,6 +88,13 @@ Concrete work tasks, follow-ups, approvals, and scheduled items extracted from G
- Status: open
- Notes: **Strongest CelVivo ClinoStar product relevance rating (5) in any of the 3 new flywheel-sync papers** — the vHLPO single 3D EB co-induction (mesoderm+endoderm) protocol depends on 3D EB self-organization in low-shear rotating culture, which is exactly what ClinoStar provides. vHLPO 7% ECs vs traditional HLPO 0% is a clinically-meaningful differentiator that no competing 2D / static culture can match. Sales ammunition: "your lung organoid model is missing 100% of vasculature — ClinoStar co-differentiation gives you 7% ECs vs 0%". Cross-vendor co-marketing: CelVivo ClinoStar (culture) + Cellink BIO X (decellularized lung scaffold) + 3Brain HD-MEA (functional readout on the neural mesenchyme). Robin should fold this into the CelVivo industrial-customers program (existing `CelVivo_中国工业客户开发研究报告` v1 + v2 in vault) and pitch to pediatric-hospital pharma R&D accounts (FOXF1 ACDMPV rare disease).
### liang-2026-celvivo-clinostar-positioning: fold Liang 2026 长程成熟 + 体外纤维化模型 story into CelVivo ClinoStar / ClinoReactor sales narrative
- Owner: me
- Source: git-repo-1 2026-08-12 (vault commit cluster `e542c977``8699a154``aacba7aa``297f106d`) — Liang Y, Ye Y, Xie H, Lui VCH, Chen Y, Tam PKH. (2026) *Scientific Reports* DOI 10.1038/s41598-026-42990-2, PMID 41857098; Wiki.js Id 1716, NocoDB Id 770; SeaFile PDF https://fb.biokingdom.top/f/9d53cfaaa88a45b49b72/?dl=1 + 7 真图 (Fig1-7); vault path `04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md` (170 lines; 4-commit LDR cycle)
- Due: unscheduled
- Status: open
- Notes: **Parallel CelVivo ClinoStar rating 4 + ClinoReactor rating 4 to the existing `miao-2025-celvivo-clinostar-positioning`** but for **liver organoid (long-term maturation + fibrosis modeling)** rather than lung organoid (vascularization). Single tissue 3-轨道 (Hep-Orgs + Cho-Orgs + HSC) → DAPT (Notch 抑制) + Dexamethasone for **P1-P10 长程稳定成熟** (single DAPT only sustains P5; DAPT+Dex 协同才实现 P10) → TGFβ 5-7 day activation of qHSC → aHSC (Acta2/Col1a1 上调) → aHSC 共培养诱导 Hep-Orgs **EMT (Snail/Twist/Vimentin ↑; ALB/CK8 ↓; Lgr5/EpCAM ↓; Ki67 ↓)** = **体外肝纤维化模型**. Sales ammunition: "你的肝类器官只能短期培养? DAPT+Dex P1-P10 稳定成熟 + 单组织 3 轨道 + 14 天纤维化模型 — ClinoStar + ClinoReactor 一站搞定"; paired with "你的抗纤维化药筛需要 14+ 天 3D 多细胞模型 — ClinoReactor 6 通道一次测 6 药". Cross-vendor co-marketing: **CelVivo ClinoStar (P1-P10 旋转扩增) + CelVivo ClinoReactor (3 轨道分通道灌流 + TGFβ 时间程序精确切换) + 3Brain HD-MEA (肝-神经互作延伸, 胆碱能投射场景)**. Customer entry: (a) 药企临床前 — 抗纤维化药筛 14+ 天 3D 多细胞模型 (traditional 2D 或单细胞模型失真); (b) 临床肝活检中心 — 1-2 mg 组织 → 3 轨道 → 3 周内药敏测试 (患者来源 anti-fibrosis drug sensitivity); (c) 学术 PI — 2D 静态分化效率低 → 3D 旋转培养效率提升 2-3 倍. Robin should fold this into the CelVivo industrial-customers program (existing `CelVivo_中国工业客户开发研究报告` v1 + v2 in vault) alongside the Miao 2025 vHLPO entry — these two papers together give a liver + lung CelVivo ClinoStar sales narrative with no 3D-bioprinting vendor dependency. The paper's `related:` field already names `[[MOC-类器官与3D培养]]` (the 2026-08-10 first MOC) — confirms the MOC pattern is in active use on real deep-reads on the day of publication.
### robin-picked-papers-nocodb-table: capture the structural change — new NocoDB table for Robin-handpicked papers
- Owner: me
- Source: literature flywheel-sync 2026-08-08 — Liu 2026 is the **first entry** in the new NocoDB table `Robin_Picked_Papers` (table_id `mbjo0wb56qv1qly`), created 2026-08-08 per Robin instruction to capture papers Robin hand-picks / provides outside the regular PubMed triage. The table is separate from the existing `Organoid_Literature` table.
+9 -6
View File
File diff suppressed because one or more lines are too long
+165 -63
View File
@@ -21,40 +21,45 @@ help locate things in the vault, not summarize their content.
`~/.openwiki/connectors/git-repo/config.json`)
- **Configured repos:**
- `obsidian-vault``/home/ldw/workspace` (Robin Obsidian vault, on
`main`, HEAD `d97b39edb328b7e15d28de4a54a6d0bc2dd51274` as of
2026-08-10).
`main`, HEAD `297f106d2b137af3480261052ff080cbc48d5b48` as of
2026-08-12).
- `openwiki-wiki``/home/ldw/.openwiki/wiki` (the OpenWiki knowledge
base itself, on `main`, HEAD `2bc03f3ddb54e44d53dfed9366daeee109b82e87`
as of 2026-08-09).
base itself, on `main`, HEAD `c57ead4bf115dbca5101720db63a7730476d6894`
as of 2026-08-12).
- **Auth:** local paths only — no remote, no credentials.
- **Latest fetch:** `2026-08-10T18:06:19Z` (raw manifest
`~/.openwiki/connectors/git-repo/raw/2026-08-10T18-06-18-966Z/manifest.json`).
- **Latest fetch:** `2026-08-12T18:08:49Z` (raw manifest
`~/.openwiki/connectors/git-repo/raw/2026-08-12T18-08-49-138Z/manifest.json`).
- **Source config:** `~/.openwiki/connectors/git-repo/config.json`
- **State:** `~/.openwiki/connectors/git-repo/state.json` records
`latestIds` per repo; the 2026-08-10 fetch bumped `obsidian-vault`
from `d7df3830` (2026-08-08) to `d97b39ed` (2026-08-10, 3 new
commits in the 24-hour window) and left `openwiki-wiki` at
`2bc03f3` (2026-08-09, the sources-sync refresh recorded in the
prior update).
`latestIds` per repo; the 2026-08-12 fetch bumped `obsidian-vault`
from `d97b39ed` (2026-08-10) to `297f106d` (2026-08-12, 4 new commits
on the same Liang 2026 paper) and bumped `openwiki-wiki` from
`2bc03f3` (2026-08-09) to `c57ead4` (2026-08-12, 2 new commits:
`431ee6a` daily update 2026-08-12 + `c57ead4` sources-sync 2026-08-12).
## obsidian-vault — working-tree status (2026-08-10)
## obsidian-vault — working-tree status (2026-08-12)
- **Branch:** `main`
- **HEAD:** `d97b39edb328b7e15d28de4a54a6d0bc2dd51274` (vault HEAD after
the **Phase A metadata batch + 2 sample runs** on 2026-08-10)
- **Ahead of origin/main:** 12 commits (the 2026-08-08 baseline of 9
commits was extended by the 2026-08-09 Wang 2024 Theranostics OrgOC
entry `a14758b1` plus the 2026-08-10 Phase A metadata batch
`d97b39ed` + the 2 sample runs `6b717aef` and `3b929c2f`).
- **Dirty:** yes — same untracked file set as the 2026-08-08 fetch
- **HEAD:** `297f106d2b137af3480261052ff080cbc48d5b48` (vault HEAD after
the **Liang 2026 liver organoid fibrosis platform cluster** on
2026-08-12)
- **Ahead of origin/main:** 13 commits new since 2026-08-03 fetch (the
2026-08-10 cluster of 12 was extended by the 2026-08-12 Liang 2026
cluster of 4 commits on the same paper).
- **Dirty:** yes — same 19 untracked file set as the 2026-08-10 fetch
(8 `02-Clients/Agents/*2026-0807.md` distributor baseline files + the
literature-stage files Robin works on between commits + 5 `文悦精读流水线`
yml variants + `dify精读进度-20260805.md` + `rustdesk-selfhosted-2026-08-05.md`
+ `literature_deepread_v6.py` etc.).
+ `literature_deepread_v6.py` etc.); the Liang 2026 file moved from
untracked → committed via `e542c977`.
- **Working-tree status (raw manifest, abbreviated):**
| Status | Path |
| --- | --- |
| `A` (committed 2026-08-12, `e542c977`) | `04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md`**NEW external evidence** (Liang Y et al. Sci Rep 2026 DOI 10.1038/s41598-026-42990-2, PMID 41857098, 3 轨道 Hep-Orgs + Cho-Orgs + HSC, DAPT+Dex P1-P10 长程成熟, TGFβ 激活体外纤维化模型; Wiki.js Id=1716, NocoDB Id=770, SeaFile PDF + 7 真图) |
| `M` (committed 2026-08-12, `8699a154`) | same Liang 2026 file — page 946 9 项 SOP 重写版 (105+/122- lines) |
| `M` (committed 2026-08-12, `aacba7aa`) | same Liang 2026 file — frontmatter title 改中文 + 与正文 H1 一致 (1-line touch) |
| `M` (committed 2026-08-12, `297f106d`) | same Liang 2026 file — 修齐 page 934 标杆 (H1 去括号/元数据用bold/📄PDF文件名, 5+/4- lines) |
| `M` (committed 2026-08-10) | `04-Literature/Deep-Reads/Organoid/2026-07-29_Organoids_disease_modeling_treatment_2026_review.md` (Phase A batch frontmatter — `volume` / `pages` / `authors` array; also touched by `6b717aef` for related back-link) |
| `M` (committed 2026-08-10) | `CelVivo_精读报告_04_bioRxiv_PAH_Metabolomics.md` (Phase A batch frontmatter — `volume` / `pages` / `authors` array; also touched by `6b717aef`) |
| `M` (committed 2026-08-10) | `obsidian-vault/04-Literature/Deep-Reads/3Brain/shin-2024-thalamocortical-organoids-22q11ds.md` (Phase A batch frontmatter; also touched by `6b717aef`) |
@@ -83,6 +88,10 @@ help locate things in the vault, not summarize their content.
| Date | Hash | Note |
| --- | --- | --- |
| 2026-08-12 | `297f106d` | **literature: 修齐 page 934 标杆** — H1 去括号 / 元数据用 bold / 📄PDF 文件名 (Liang 2026 v3) |
| 2026-08-12 | `aacba7aa` | **literature: frontmatter title 改中文 + 与正文 H1 一致** (Liang 2026 v2) |
| 2026-08-12 | `8699a154` | **literature: Liang 2026 Sci Rep liver organoid fibrosis - page 946 9 项 SOP 重写版** (Liang 2026 v2; 105+/122- lines; core-question / research-model / 6-finding 3-stage tables / 6 SeaFile Fig / "与我们的产品" 4-star / 4-paper refs / 转发语 / 完整落款) |
| 2026-08-12 | `e542c977` | **literature: Liang 2026 Sci Rep liver organoid + fibrosis platform (Id=770 NocoDB)****NEW external evidence** (3 轨道 Hep/Cho/HSC + DAPT+Dex P1-P10 长程成熟 + TGFβ 激活 HSC 体外纤维化模型; 7/7 Ollama qwen2.5vl 视觉审核通过; SeaFile 7/7 公网 200 验真; 飞轮 PATCH comm Id=87 + product Id=10 + NocoDB PATCH 770) |
| 2026-08-10 | `d97b39ed` | **Phase A 批量:6 篇精读加 Front Matter 6 字段** (doi/journal/year/volume/pages/authors/pmid) — Organoids 2026 review + CelVivo PAH + Shin 2024 + Fernandez Vallone 2026 + Liu 2026 + 类器官综述_CMOS_HD_MEA |
| 2026-08-10 | `3b929c2f` | **wang2024 方案 2 样品:6 个 Front Matter 字段 + 7 张图加 alt 描述**`wang2024-org-on-chip.md` |
| 2026-08-10 | `6b717aef` | **MOC 方案 1 样品:建 1 个 MOC + 7 篇加 Front Matter (related: 反链)** — first MOC `MOC-类器官与3D培养.md` created; 7 papers got `related:` back-link frontmatter |
@@ -108,6 +117,32 @@ help locate things in the vault, not summarize their content.
| 2026-07-28 | `2718e46d` | feat(literature): Parate 2020 SCRT — PEMF 增强 MSC 旁分泌功能促软骨再生 |
| 2026-07-28 | `032de92f` | feat: 精读 Lee 2025 Front Vet Sci 犬脂肪源 MSC 3D 球体 |
The **2026-08-12 cluster** is a **single-paper LDR cycle** on
**Liang Y et al. (2026) Sci Rep DOI 10.1038/s41598-026-42990-2** — a
mouse liver organoid platform paper from 澳门科技大学 + 香港大学 that
establishes: (i) single-tissue 3-轨道 (Hep-Orgs + Cho-Orgs + HSC)
separation; (ii) DAPT (Notch 抑制) + Dexamethasone for P1-P10 长程
稳定成熟 (ALB / PAS / LDL / CYP all stable across 10 passages — single
DAPT only sustains P5); (iii) TGFβ 5-7 day activation of qHSC → aHSC
(Acta2 / Col1a1 上调); (iv) aHSC 共培养诱导 Hep-Orgs EMT
(Snail / Twist / Vimentin ↑; ALB / CK8 ↓; Lgr5 / EpCAM ↓; Ki67 ↓) =
体外肝纤维化模型. The 4 commits are the **same single file**
`04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md`
walked through Robin's standard 3-stage SOP cycle: (a) **`e542c977`**
adds the file (186 lines, single-pass entry); (b) **`8699a154`** rewrites
the same file to the page 946 9 项 SOP 标杆 (105+/122- lines, adding
the 6 核心发现 三段式 tables + 6 SeaFile Fig + "与我们的产品" 4-star
table + 4-paper 参考文献 + 转发语 + 完整落款 + SeaFile PDF link); (c)
**`aacba7aa`** + **`297f106d`** are the **page 934 修齐** micro-revisions
(frontmatter title 改中文 / H1 去括号 / 元数据用 bold 单行 / 📄PDF
文件名 with actual filename) — the same alignment Robin applied across
the 2026-08-11 OVB-类器官 cycle. The "与我们的产品" 4-star table
on the paper lists CelVivo ClinoStar ⭐⭐⭐⭐ (P1-P10 长程扩增对应
旋转培养 30+ 天无剪切; HSC 静止态在模拟微重力下 7+ 天维持) +
CelVivo ClinoReactor ⭐⭐⭐⭐ (单组织 3 轨道分通道灌流; TGFβ 时间程序
精确切换) + CelVivo PhaseHolographic 成像 ⭐⭐⭐ + 3Brain HD-MEA ⭐⭐⭐
(肝-神经互作延伸).
The **2026-08-10 cluster** is a **frontmatter-hygiene + MOC-discipline
sprint** rather than new external evidence: (a) **Phase A batch**
(`d97b39ed`) standardized 6 deep-read notes with the structured 6-field
@@ -131,28 +166,48 @@ indexed on [`/sources/literature.md`](/sources/literature.md). The
`1614ccf9`) are the 8-step SOP rewrite cycle (v3 → v11) Robin re-ran
on the same paper.
## openwiki-wiki — working-tree status (2026-08-10)
## openwiki-wiki — working-tree status (2026-08-12)
- **Branch:** `main`
- **HEAD:** `2bc03f3ddb54e44d53dfed9366daeee109b82e87` (the
- **HEAD:** `c57ead4bf115dbca5101720db63a7730476d6894` (the
`chore(sources): refresh NocoDB/SeaFile/Wiki.js/RAGFlow counts
(sources-sync 2026-08-10)` commit recorded during the prior
2026-08-10 update — no new wiki-side commits landed in the 24-hour
window since then).
- **Working-tree state:** 9 staged-but-not-yet-committed file changes
(this OpenWiki run's own edits — the same 17 files from the prior
2026-08-08 manifest minus the 3 literature deep-read synthesis pages
that the prior 2026-08-10 sources-sync commit already captured:
`.last-update.json` + `quickstart.md` + `sources/README.md` +
`sources/hackernews.md` + `sources/nocodb.md` + `sources/ragflow.md` +
`sources/seafile.md` + `sources/web-search.md` + `sources/wikijs.md`).
(sources-sync 2026-08-12)` commit recorded in this run's window).
- **Working-tree state:** 10 modified files (uncommitted — pending next
CLI orchestration). The dirty file set is the **synthesis-layer edits
from the prior 2 source-specific runs in this same 24-hour window**:
- Hackernews-1 (2026-08-12T18:00Z) — Wired organoid feature refresh on
`/themes.md` `class-organoid-3d-bioprinting` Last seen → 2026-08-12;
new "Latest update — 2026-08-12 18:00 UTC" section on
`/sources/hackernews.md`; updated quickstart / index status; tag bump.
- Web-search-1 (2026-08-12, third skip) — Tavily still disabled,
`TAVILY_API_KEY` empty; new "2026-08-12 attempted update — skipped"
section on `/sources/web-search.md`; updated quickstart status.
- Daily source-sync (2026-08-12) — `/sources/nocodb.md` /
`/sources/ragflow.md` / `/sources/seafile.md` / `/sources/wikijs.md`
each got a 6-line counter increment + `openwiki_generated: true`
placeholder frontmatter inserted.
- Literature (2026-08-12) — `/sources/literature.md` got a single
short Liang 2026 row appended (this row is a working-tree add for
the next sources-sync commit; the full synthesis lives at the
paper's vault path and on `/themes/01-organoid-equipment.md` /
`/themes/05-robin-research.md`).
- **Auth:** local path only — no remote, no credentials.
### Recent commits (latest first)
| Date | Hash | Note |
| --- | --- | --- |
| 2026-08-10 | `2bc03f3` | chore(sources): refresh NocoDB/SeaFile/Wiki.js/RAGFlow counts (sources-sync 2026-08-10) |
| 2026-08-12 | `c57ead4` | chore(sources): refresh NocoDB/SeaFile/Wiki.js/RAGFlow counts (sources-sync 2026-08-12) |
| 2026-08-12 | `431ee6a` | chore: daily update 2026-08-12 |
| 2026-08-11 | `b64ae41` | lit: PMID 41536916 Bioactive Materials AIVOs 综述 (Wiki.js 1711) |
| 2026-08-11 | `523ee7f` | lit: PMID 41686639 Cell Reports TNBC DEO + ROCK (Wiki.js 1710) |
| 2026-08-11 | `9be4f55` | lit: PMID 41909700 Front Immunol 2026 类器官-小胶质细胞综述 (Wiki.js 1709) |
| 2026-08-11 | `cc69ece` | lit: PMID 42041571 v4 - 按 literature-deep-read-research 9 项强制格式 |
| 2026-08-11 | `b4bc8d9` | lit: PMID 42041571 修正 - 真实PDF + 10张真图链接 |
| 2026-08-11 | `12480ab` | lit: 修正 wiki_url 到真实内网地址 |
| 2026-08-11 | `cdc59c5` | lit: PMID 42041571 OVB-organoids vs cerebral organoids Cells 2026 |
| 2026-08-11 | `2bcde39` | chore(sources): refresh NocoDB/SeaFile/Wiki.js/RAGFlow counts (sources-sync 2026-08-11) |
| 2026-08-11 | `7556e31` | chore: daily update 2026-08-11 |
| 2026-08-09 | `dde053a` | auto: 2026-08-09 Wang 2024 Theranostics OrgOC 综述精读入口 |
| 2026-08-09 | `3267338` | chore: daily update 2026-08-09 |
| 2026-08-09 | `06f60e1` | chore(sources): refresh NocoDB/SeaFile/Wiki.js/RAGFlow counts (sources-sync 2026-08-09) |
@@ -178,10 +233,30 @@ on the same paper.
| 2026-07-24 | `3102e96` | feat(sources): 全国 261 家经销商地图 (2026-07-24, 不含敏感信息) |
The wiki repo is the OpenWiki output itself — it persists across
update runs. No new wiki-side commits landed in the 2026-08-09T18:06Z
→ 2026-08-10T18:06Z window: the most recent wiki commit
(`2bc03f3`, sources-sync 2026-08-10) was recorded in the prior
update.
update runs. **2 new wiki-side commits landed in the 2026-08-10T18:08Z
→ 2026-08-12T18:08Z window**: (a) `431ee6a` (2026-08-12 +0800 02:00,
`chore: daily update 2026-08-12`) and (b) `c57ead4` (2026-08-12 +0800
02:30, `chore(sources): refresh NocoDB/SeaFile/Wiki.js/RAGFlow counts
(sources-sync 2026-08-12)`). Between these 2 commits, the wiki HEAD
advanced from `2bc03f3` (2026-08-09 sources-sync) to `c57ead4`. The
intervening 6 wiki commits from 2026-08-11 (`7556e31` daily +
`2bcde39` sources-sync + `cdc59c5` / `12480ab` / `b4bc8d9` / `cc69ece`
PMID 42041571 OVB-organoids deep-read cycle + `9be4f55` PMID 41909700
Front Immunol + `523ee7f` PMID 41686639 Cell Reports TNBC + `b64ae41`
PMID 41536916 Bioactive Materials AIVOs) are **between** the prior
fetch and this one — they all post-date the prior fetch's HEAD but are
already in the new HEAD's ancestry. The **Liang 2026 wiki sync** has
not yet landed (the `/sources/literature.md` short row is in working
tree only); the next wiki commit should add a fuller Liang 2026 row
when the synthesis pipeline catches up.
### Summary of last 24 hours
| Window (UTC) | Vault | Wiki |
| --- | --- | --- |
| 2026-08-11T18:00:00Z → 2026-08-12T18:08:49Z | HEAD `d97b39ed``297f106d` (4 new commits, all on Liang 2026 liver organoid fibrosis paper deep-read) | HEAD `2bc03f3``c57ead4` (2 new commits; 6 commits since prior fetch also recorded here: daily + sources-sync on 2026-08-11; literature deep-read cycle on PMID 42041571 OVB-organoids + 3 2026-08-11 PMID entries) |
| **Net new external evidence** | **Liang Y et al. (2026) Sci Rep DOI 10.1038/s41598-026-42990-2** — mouse liver organoid 3-轨道 (Hep/Cho/HSC) + DAPT+Dex P1-P10 长程成熟 + TGFβ 激活体外纤维化模型; Wiki.js Id=1716, NocoDB Id=770 | none — synthesis layer only (HN-1 Wired organoid refresh + web-search-1 third skip) |
| Untracked → committed migrations | `04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md` (was untracked in 2026-08-10 fetch, now committed via `e542c977`) | none — all 10 dirty files (`.last-update.json`, `quickstart.md`, 4 × sources/{hackernews,web-search,literature,nocodb,ragflow,seafile,wikijs}.md, `themes.md`) are uncommitted synthesis edits awaiting the next CLI commit cycle |
## Vault navigation index
@@ -298,6 +373,7 @@ fields still 待补).
## Notable entities surfaced by the vault (structural hints only)
- **Liang 2026 liver organoid fibrosis platform (2026-08-12)** — `04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md` (170 lines; `[[MOC-类器官与3D培养]]` already names this paper via `related:` back-link). The paper is **the net-new external evidence** this run (git-repo-1 2026-08-12) brought into the vault; see synthesis at `/themes/01-organoid-equipment.md` § CelVivo evidence (added 2026-08-12) and `/commitments.md` `liang-2026-celvivo-clinostar-positioning`. Single-paper LDR cycle: 4 commits (`e542c977``8699a154``aacba7aa``297f106d`) walked Robin's standard 3-stage SOP on the same file (186 lines → 105+/122- page 946 rewrite → page 934 修齐 micro-revisions). The 4-star "与我们的产品" table on the paper lists **CelVivo ClinoStar ⭐⭐⭐⭐** (P1-P10 长程扩增对应旋转培养 30+ 天无剪切; HSC 静止态在模拟微重力下 7+ 天维持) + **CelVivo ClinoReactor ⭐⭐⭐⭐** (单组织 3 轨道分通道灌流; TGFβ 时间程序精确切换) — **parallel CelVivo ClinoStar rating 5 to Miao 2025 v2's ClinoStar rating 5** from the 2026-08-08 flywheel-sync, but for liver organoid (long-term maturation + fibrosis modeling) rather than lung organoid (vascularization). 7 SeaFile Fig (Fig1-7) + 4-paper 参考文献 (Huch 2013 / Huch 2015 / Clevers 2016). Customer-entry: 药企临床前 (抗纤维化药筛) + 临床肝活检中心 (1-2 mg → 3 周药敏) + 学术 PI (2D vs 3D 旋转 efficiency). **MOC linkage**: the paper's `related:` field already names `[[MOC-类器官与3D培养]]` (the first MOC, created 2026-08-10) — confirming the MOC pattern is in active use on real deep-reads.
- **CelVivo industrial customers program** — a dedicated subfolder under
`05-Documents/Products/Celvivo/Industrial-Customers/` holds `CelVivo_中国工业
客户开发研究报告` (v1 + v2), `客户管线定位_1页图`, and `工业客户开发手册-v3`.
@@ -378,24 +454,43 @@ fields still 待补).
## Synthesis policy for this source
- **This run (2026-08-10):** 3 new vault commits landed in the 24-hour
window (Phase A metadata batch + 2 sample runs) — these are
**frontmatter-hygiene + MOC-discipline**, not new external evidence.
No `/commitments.md`, `/open-questions.md`, `/personal-logistics.md`,
or `/themes.md` row changes are warranted by this run; the only
pages that need to track the new HEADs are this page
(`/sources/git-repo.md`), `/themes/05-robin-research.md` (vault HEAD
pointer), and `/quickstart.md` (current-status paragraph). The
previous run (2026-08-08) was the substantive update — 1 new entry
surfaced to `/commitments.md` (`distributor-8-07-association-followup`)
+ 1 partial-answer update to `/open-questions.md`
(`agent-dong-huiqun-celvivo` — agency side now resolved as 济南成全;
personal contact + role granularity still 待补). The
`/themes/05-robin-research.md` truth-of-vault snapshot moves to the
new HEAD `d97b39ed` and now also notes the Phase A metadata batch +
first MOC creation. The `/sources/distributors-china-2026.md` page
still reflects the 259-dealer 8-07 baseline (unchanged since
2026-08-08).
- **This run (2026-08-12, git-repo-1 18:08Z):** 4 new vault commits
landed in the 24-hour window — all on the **same single Liang 2026
Sci Rep liver organoid paper**, walked through Robin's standard
3-stage LDR cycle (`e542c977` adds the file → `8699a154` page 946 9
项 SOP 重写版 → `aacba7aa` + `297f106d` page 934 修齐 micro-revisions).
This is the **net-new external evidence** this run brings into the
vault: **Liang Y et al. (2026) Sci Rep DOI 10.1038/s41598-026-42990-2**
— mouse liver organoid 3-轨道 (Hep-Orgs + Cho-Orgs + HSC) +
DAPT+Dex P1-P10 长程成熟 + TGFβ 激活体外纤维化模型 (EMT + Ki67↓ +
stemness↓). Wiki.js Id=1716, NocoDB Id=770, PMID 41857098. Wiki
edits this run: (a) `/sources/git-repo.md` (this page) — refreshed
HEAD pointers, added 4 commits to the recent-commits table, added a
new "Liang 2026 liver organoid fibrosis platform (2026-08-12)"
Notable-entity entry, refreshed synthesis-policy section, updated
openwiki-wiki working-tree status section; (b) `/themes/05-robin-research.md` — vault
HEAD `d97b39ed``297f106d`, "Latest cluster (2026-08-10)" →
"Latest cluster (2026-08-12)", added a new top-row entry to the
30-day research-output table for the Liang 2026 cluster, updated
the by-vendor CelVivo row to include the Liang 2026 ClinoStar
rating-5 entry; (c) `/themes/01-organoid-equipment.md` — added
Liang 2026 to the CelVivo evidence anchors (ClinoStar rating 4 for
P1-P10 长程 + 旋转 30+ 天无剪切; ClinoReactor rating 4 for 单组织 3
轨道分通道灌流 + TGFβ 时间程序; PhaseHolographic imaging rating 3;
3Brain HD-MEA rating 3 for 肝-神经互作延伸); (d) `/commitments.md`
— added `liang-2026-celvivo-clinostar-positioning` (Owner: me, fold
Liang 2026 长程成熟 + 体外纤维化模型 story into CelVivo ClinoStar
sales narrative; companion to existing `miao-2025-celvivo-clinostar-positioning`).
**No `/open-questions.md` row, no `/personal-logistics.md` item**
the Liang 2026 paper is fully published and the synthesis is direct;
no ambiguity that requires a memory-graph open question. No
`/themes.md` row change (the Liang 2026 evidence is a single-paper
flywheel-sync output, not a recurring signal — it routes into the
existing `class-organoid-3d-bioprinting` and `china-cde-cell-gene-therapy-rules-2026`
vendor theme evidence without needing a new theme row). The
previous run (2026-08-10) was the prior frontmatter-hygiene +
MOC-discipline sprint; the 2026-08-08 run was the substantive
distributor / Liu-2026-roadmap / `_known_associations.md` update.
- The vault is a knowledge base, not a live signal stream; durable
per-document synthesis (paper deep reads, sales scripts, customer
files) requires reading individual files, which is delegated to the
@@ -404,14 +499,21 @@ fields still 待补).
theme only when the connector observes a recurring workflow (e.g. weekly
literature digest cadence, sales training iteration pattern) across multiple
fetches.
- **Process signal worth watching (2026-08-10):** Robin started a
MOC-discipline sprint — first MOC
(`04-Literature/Deep-Reads/MOCs/MOC-类器官与3D培养.md`) created with a
forward link to `[[MOC-3Brain-HD-MEA]]`. Track on the next git-repo
fetch whether more MOCs land (MOC-3Brain-HD-MEA, MOC-Cellink-BIO-X,
etc.) and whether the Phase A batch expands to cover the remaining
~1,200 deep-read notes. If the MOC pattern extends to ≥3 MOCs, it
may warrant a `/themes.md` annex row on `vault-knowledge-architecture`.
- **Process signal worth watching (2026-08-12):** (a) **Liang 2026's
MOC linkage confirms the MOC pattern is in active use** — the new
paper's `related:` field already names
`[[MOC-类器官与3D培养]]` (the first MOC, created 2026-08-10) on the
day of publication, not a future-state plan. This is a stronger
signal than the prior "MOC `related:` lists future MOCs" framing
implied. Track on the next git-repo fetch whether more papers
acquire MOC `related:` back-links and whether MOC-3Brain-HD-MEA /
MOC-Cellink-BIO-X land. (b) **Page 934 修齐 micro-revisions now
appear on every new LDR cycle** — `297f106d` is the second paper
(after `381fcbaa` OVB-organoids 2026-08-11) where Robin applied
the H1 去括号 / 元数据 bold / 📄PDF 文件名 alignment. The pattern
appears to be the new standard end-state. (c) **Phase A frontmatter
batch rollout** is still paused (only 6 of ~1,204 deep-reads
received the 6-field frontmatter); no progress this run.
## Next update
+39 -4
View File
@@ -2,7 +2,7 @@
type: "Reference"
title: "Hacker News — evidence index"
description: "Compact evidence trail for the Hacker News connector (hackernews-1, Robin-curated life-sciences + AI workflow). Synthesis lives on /themes.md, /commitments.md, etc.; this page only records ingestion coverage and notable items."
tags: [hackernews, evidence-index, source, 2026-08-10]
tags: [hackernews, evidence-index, source, 2026-08-12, 2026-08-10]
---
# Hacker News — evidence index
@@ -15,10 +15,45 @@ Compact evidence trail for the Hacker News connector (`hackernews-1`, Robin-cura
- **Backend:** public HN feeds (`top`, `new`) + Algolia HN search queries
- **Auth:** none — public feeds
- **Window:** last 24 hours
- **Latest fetch:** `2026-08-10T18:00:52Z` (LLM-agent topic set: `organoid`, `CelVivo`, `3Brain`, `Cellink`, `openwiki`, `deepagents` — 6 queries; the source-specific instruction "Track organoid / CelVivo / 3Brain / Cellink / openwiki / AI agent stories" is the active query set; prior 2026-08-08 18:00, 2026-08-08 03:15, 2026-08-07 12:29, 2026-08-03 18:00, 2026-08-02 18:00, 2026-08-01 18:00, 2026-07-31 18:00, 2026-07-30 18:00, 2026-07-29 18:00, 2026-07-28 18:00, 2026-07-27 18:00, 2026-07-26 18:16 and 18:00 pulls also documented below)
- **Raw dumps:** `~/.openwiki/connectors/hackernews/raw/2026-08-10T18-00-02-327Z/hackernews-results.json` (current — no promotable hits, see 2026-08-10 18:00 UTC entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-08T18-00-01-989Z/hackernews-results.json` (prior — no promotable hits, see 2026-08-08 18:00 UTC entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-08T03-14-40-856Z/hackernews-results.json` (prior — no promotable hits, see 2026-08-08 03:15 UTC entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-07T12-29-44-173Z/hackernews-results.json` (prior — no promotable hits, see 2026-08-07 entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-03T18-00-02-766Z/hackernews-results.json` (earlier — material findings, see 2026-08-03 entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-02T18-00-02-278Z/hackernews-results.json` (empty) · `~/.openwiki/connectors/hackernews/raw/2026-08-01T18-00-02-274Z/hackernews-results.json` (empty) · `~/.openwiki/connectors/hackernews/raw/2026-07-31T18-00-02-519Z/hackernews-results.json` (empty) · `~/.openwiki/connectors/hackernews/raw/2026-07-30T18-00-02-784Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-29T18-00-02-667Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-28T18-00-02-178Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-27T18-00-02-615Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-16-06-805Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-00-02-441Z/hackernews-results.json`
- **Latest fetch:** `2026-08-12T18:00:30Z` (LLM-agent topic set: `organoid`, `CelVivo`, `3Brain`, `Cellink`, `openwiki`, `deepagents` — 6 queries; the source-specific instruction "Track organoid / CelVivo / 3Brain / Cellink / openwiki / AI agent stories" is the active query set; prior 2026-08-10 18:00, 2026-08-08 18:00, 2026-08-08 03:15, 2026-08-07 12:29, 2026-08-03 18:00, 2026-08-02 18:00, 2026-08-01 18:00, 2026-07-31 18:00, 2026-07-30 18:00, 2026-07-29 18:00, 2026-07-28 18:00, 2026-07-27 18:00, 2026-07-26 18:16 and 18:00 pulls also documented below)
- **Raw dumps:** `~/.openwiki/connectors/hackernews/raw/2026-08-12T18-00-01-956Z/hackernews-results.json` (current — one new low-engagement organoid signal, see 2026-08-12 18:00 UTC entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-10T18-00-02-327Z/hackernews-results.json` (prior — no promotable hits, see 2026-08-10 18:00 UTC entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-08T18-00-01-989Z/hackernews-results.json` (prior — no promotable hits, see 2026-08-08 18:00 UTC entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-08T03-14-40-856Z/hackernews-results.json` (prior — no promotable hits, see 2026-08-08 03:15 UTC entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-07T12-29-44-173Z/hackernews-results.json` (prior — no promotable hits, see 2026-08-07 entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-03T18-00-02-766Z/hackernews-results.json` (earlier — material findings, see 2026-08-03 entry below) · `~/.openwiki/connectors/hackernews/raw/2026-08-02T18-00-02-278Z/hackernews-results.json` (empty) · `~/.openwiki/connectors/hackernews/raw/2026-08-01T18-00-02-274Z/hackernews-results.json` (empty) · `~/.openwiki/connectors/hackernews/raw/2026-07-31T18-00-02-519Z/hackernews-results.json` (empty) · `~/.openwiki/connectors/hackernews/raw/2026-07-30T18-00-02-784Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-29T18-00-02-667Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-28T18-00-02-178Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-27T18-00-02-615Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-16-06-805Z/hackernews-results.json` · `~/.openwiki/connectors/hackernews/raw/2026-07-26T18-00-02-441Z/hackernews-results.json`
## Latest update — 2026-08-10 18:00 UTC
## Latest update — 2026-08-12 18:00 UTC
- **Coverage:** 2 feeds (`top`, `best`), 6 search queries (the same simplified LLM-agent topic set from the source-specific instruction "Track organoid / CelVivo / 3Brain / Cellink / openwiki / AI agent stories": `organoid`, `CelVivo`, `3Brain`, `Cellink`, `openwiki`, `deepagents`). `top` feed returned 25 items, `best` feed returned 10; deduplication gave **30 unique items across both feeds** (5 overlap: `49271994` AI middle class software engineering, `49272832` Tailscale SQLite WAL-Reset bug, `49270953` 2026 Eclipse Webcams, `49273165` license plate warrant, `49274600` DeepSeek V4 Pro 0813). The 6-query lane produced the hit table below; the connector completed normally at `fetchedAt: 2026-08-12T18:00:30.849Z` (24-hour window).
- **Life-science lane:** **zero vendor-anchored hits across all four named vendor queries.** `CelVivo` returned `nbHits=0` (no stories indexed in 24h). `3Brain` returned 11 hits — one is a real organoid essay that was also surfaced by `organoid` (`49266068` "AI Is Dead. Organoids Are Alive", 5 pts, Wired — see "class-organoid-3d-bioprinting (refreshed this run)" below); the remaining 10 are string-collision noise on the substring "brain": `49263658` "The brain may be about to have its Ozempic moment" (114 pts, Economist — generic neuroscience essay on GLP-1-style brain drugs, outside Robin's 4 application domains); `49267390` "Dogs can tell when you're happy, sad or frustrated" (22 pts, Washington Post — consumer / veterinary neuroscience); `49272228` "Dog brains represent human facial expressions" (3 pts, Cell/iScience — veterinary); `49270499` "Big Tech Wants to Harvest Your Thoughts" (4 pts, Wired book excerpt — neurotech policy); `49271182` "Why I Play Board Games (and So Should You)" (4 pts, brainbaking.com — string hit on the "brainbaking" blog name); `49268526` "Brain scans show that dogs can distinguish various emotions in human faces" (1 pt, univie.ac.at — veterinary); `49269234` "New AI chip mimics the human brain's capacity for split-second motor control" (1 pt, LiveScience — brain-inspired computing chip, not 3Brain MEA / HD-MEA); `49269176` "My Terminal Workflow for Note-Taking, Data Engineering and Writing (Linux/macOS)" (1 pt, ssp.sh — "brain" tag slug, off-scope); `49273216` "Show HN: Kery comments on your PR with a video of the feature working" (1 pt, github.com/Kery-HQ/Kery — `Kery-HQ` slug, off-scope). `Cellink` returned 4 hits — all string-collision noise on author-name / body-text fragments: `49273922` "Show HN: OJCP an open protocol for agent-consumable job data" (8 pts, ojcp.dev — author `fraywing`, no relationship); `49275744` "Trump signs executive order calling for fewer childhood vaccines" (3 pts, CNBC — author `Fellw`, no relationship); `49265119` "Show HN: Supply-Wizard; Start Selling Data with an Easy Vendor Checklist" (3 pts, brickroad.network — string hit on "Checklist" / vendor terminology, no Cellink overlap); `49275608` "Development Mindset for AI Programming" (1 pt, no URL, author `kva`, no relationship). `organoid` returned 7 hits — **one real organoid essay** (`49266068` "AI Is Dead. Organoids Are Alive", 5 pts, Wired, by `Logans_Run`, https://www.wired.com/story/organoids-lab-grown-brains-neural-networks/ — see "class-organoid-3d-bioprinting (refreshed this run)" below) + six string-collision noise hits: `49275420` "Maintaining an organizational knowledge graph with an LLM and event sourcing" (2 pts, blog.arkency.com — "organizational" string); `49275020` "Ask HN: Responsible/trustable background check companies?" (4 pts, no URL — "organization" string); `49271578` "Show HN: Rekall an Ableton Live project management companion application" (5 pts, rekall.machinelies.eu — author `iamsaitam`, "organization" string); `49270304` "Show HN: BentoDesk Elegant Windows desktop organizer powered by Rust" (3 pts, github.com/ZRainbow1275/bentodesk — "organizer" string); `49266230` "Self-contained agents that self-organize" (3 pts, antigma.ai — "self-organize" string); `49264601` "Best Agent Gateways for Healthcare Organizations 2026" (1 pt, mintmcp.com — "Organizations" string). A title/URL regex sweep across the 30 unique top+best items also turned up zero organoid / 3D-bioprinting / CelVivo / 3Brain / Cellink / ClinoStar / ClinoReactor / MEA / spheroid / organ-on-chip items. The "no material HN footprint for the 4 vendor lines" finding still holds; the Tavily web-search lane remains the better signal for vendor news.
- **Workflow lane:** **zero positive `openwiki` brand hits; zero `deepagents` hits.** `openwiki` returned `nbHits=1``49272534` "Qwen 3.8-27B goes openweight in 2 days" (15 pts, huggingface.co/Qwen/Qwen3.8-27B, by `nateb2022`). **String collision**: the only matching tokens between the query `openwiki` and the title/url are the "open" prefix and the word "openweight" — this is **not** the `langchain-ai/openwiki` brand signal from 2026-07-16 (the original brand-signal item shipped with the literal "openwiki" GitHub-org-suffix string). The `openwiki-brand` watchlist row on `/themes.md` stays at Last seen 2026-07-16. `deepagents` returned `nbHits=0` (no stories indexed in 24h). The 30 unique top+best items include six **adjacent, high-engagement AI-agent / inference / model-launch items** that touch Robin's broader agent-stack lane but stay adjacent-not-promoted under the brief's "low-engagement items are watchlist by default; promotion requires recurrence, strong engagement, or corroboration" rule **and** the `/themes.md` scope discipline ("open-weight AI never earns a `themes.md` row" + workflow-tooling priority LOW):
- **49274600** "DeepSeek V4 Pro 0813" (274 pts top + 274 pts best, by `explosion-s` 2026-08-12, https://openrouter.ai/deepseek/deepseek-v4-pro-0813). OpenRouter hosting card for DeepSeek's V4 Pro 0813 release. Strong topical fit to the existing `MiniMax-m3` row's competitive-benchmark lane (the `benchlm.ai "DeepSeek V4 Flash vs MiniMax M3: Benchmarks & Cost" 2026-08-01` context already cited on the row, plus the 2026-08-07 ARC-AGI DeepSeek V4 Flash result). **Third observation in eight days** on the DeepSeek V4 → MiniMax-M3 / M3-H3 competitive lane (after `49214008` DeepSeek V4 Flash 0731 + the Tavily benchlm.ai result), but DeepSeek V4 Pro 0813 itself is an open-weight model, so per the existing scope rule ("open-weight AI never earns a `themes.md` row") the finding stays adjacent-not-promoted. The recurrence pattern is real, but the trigger for an annex on the `MiniMax-m3` row description (per the established "third corroborating item" criterion from the 2026-08-10 Muse Glimmer entry) is met — but the annex would track DeepSeek V4 Pro 0813 specifically, not the "always-on-agent-model cluster" framed by the 2026-08-10 Muse Glimmer. **No `/themes.md` row added, no commitment row added.** If a Hermes / MiniMax-M3 / M3-H3 vs DeepSeek V4 Pro 0813 head-to-head benchmark surfaces on a future Tavily or HN pull, that becomes the trigger for an annex. **Adjacent-not-promoted** per brief.
- **49265051** "WorldClaw Agentic 3D open-world generation at scale" (265 pts best, by `EwanG`, https://tencent-hunyuan.github.io/Hunyuan3D-WorldClaw/). Tencent Hunyuan3D release for agentic 3D open-world generation at scale. Strong topical fit to the application-domain line "3D bioprinting + 3D cell culture" on the `class-organoid-3d-bioprinting` row but is **open-world 3D scene generation, not 3D bioprinting / tissue engineering** — off-scope per the brief. **Adjacent-not-promoted** per scope discipline.
- **49267928** "llama.cpp" (333 pts best, by `kristianpaul`, https://llama.app/). High-engagement promo / directory for the llama.cpp inference backend (https://llama.app domain, llama.cpp project by `ggerganov` and the broader community). **Strongest adjacents to `/themes/04-local-llm.md`** — llama.cpp is the canonical inference backend used by Ollama and LM Studio (both on Robin's local-LLM stack). However, the page is `llama.app` — a third-party domain, not the upstream `github.com/ggerganov/llama.cpp` — so the content carries an adjacent-tooling signal rather than a direct upstream-release signal. Per the brief ("open-weight AI never earns a `themes.md` row" + workflow-tooling priority LOW), the finding stays adjacent-not-promoted. Flagged here for traceability; if the upstream llama.cpp repo releases a documented breaking change on Robin's local-LLM stack, that becomes the trigger for a `local-llm-runtime-update` theme row. **Adjacent-not-promoted** per brief.
- **49273478** "Qwen/Qwen3.8-2.4T-A95B" (200 pts top, by `Philpax`, https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B). Qwen 2.4T open-weight MoE-A95B model card on HuggingFace. Companion to `49274950` "Qwen3.8-2.4T" (17 pts top, by `mmastrac`, https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B-FP8) — same model, two quantization variants. Open-weight AI; **off-scope** per brief.
- **49274894** "Wednesday, August 12: GitHub, Incident with Pull Requests and Issues" (35 pts top, by `arm32`, https://www.githubstatus.com/incidents/76t89hbfb09h). GitHub status incident. Robin's stack includes a Gitea public mirror and any personal GitHub-hosted Pages assets — real-but-incidental exposure. Off-scope per brief (not a direct change to Hermes / MiniMax / OpenWiki / RAGFlow / NocoDB / SeaFile). **Adjacent-not-promoted**.
- **49272484** "My Agent Setup" (73 pts top, by `carimura`, https://chad.cm/posts/2026-8-11-my-agent-setup). Personal blog post on agent tooling. Adjacent to the AI-agent lane but **not on Robin's named stack**. Off-scope per brief.
- **49273175** "Hax a minimalist, terminal-native coding agent written in C" (39 pts top, by `OleksandrC`, https://usehax.dev/). Show HN for a terminal-native C-implemented coding agent. Adjacent to the AI-agent lane. Off-scope per brief.
- **49272569** "Someone is running mass vulnerability scans, spoofing AI bots like ClaudeBot" (127 pts top, by `gavinhking`, https://knownagents.com/insights). Security / bot-spoofing post. Adjacent but **off-scope** per brief.
- **49273165** "License plate reader searches should require a warrant" (348 pts top+best, by `apwheele`, https://andrewpwheeler.com/2026/08/12/license-plate-reader-searches-should-require-a-warrant/). Civil-liberties policy essay. Off-scope per brief.
- **Other feed items not promoted:** 21 additional top/best items, all off-scope per the brief's scope filter — `49271994` "AI is removing the middle class of software engineering" (429 pts top+best, highest-engagement top item — generic essay on AI + software-engineering labor market, off-scope; **flagged here for traceability because the 429-pt engagement is high enough to surface in any HN digest but the item is on Robin's named stack only at the level of "AI impact on coding agents in general", not a direct change to Hermes / MiniMax code / Codex CLI / OpenWiki**); `49263497` "Compression is prediction" (628 pts best, ngrok engineering blog — informational essay on compression theory, off-scope); `49268564` "LinkedIn CringeBot 3000" (449 pts best, satire site, off-scope); `49269818` "Controversial creators are benefiting from monetization programs run by Meta" (448 pts best, ABC.net.au news, off-scope); `49272832` "Tailscale Traces Database Corruption to 16y/o SQLite WAL-Reset Bug" (423 pts top+best, tailscale.com engineering post-mortem on a SQLite WAL behavior — adjacent to the `itx-24h-host-build-2026-q3` commitment (which uses SQLite-backed services) but on a vendor-managed service, not the local ITX host stack, so off-scope); `49270953` "2026 Eclipse Webcams" (382 pts top+best, jonty.github.io, off-scope); `49272655` "Tim King, AmigaDOS developer, has died" (124 pts top, amiga-news.de obituary, off-scope); `49270621` "Delphi 13 Community Edition Is Now Available" (122 pts top, Embarcadero blog, off-scope); `49270040` "Show HN: Woxi - Open-source Mathematica / Wolfram Language reimplementation" (211 pts top, woxi.ad-si.com, off-scope); `49270022` "What sort of maths are LLMs good at?" (199 pts top, gowers.wordpress.com — Gowers's math essay, off-scope); `49275385` "SpaceXAI's Grok 4.6 Scores 61 on the Artificial Analysis Intelligence Index" (85 pts top, artificialanalysis.ai — competitor benchmark, off-scope open-weight AI adjacent); `49271757` "Shade Map" (68 pts top, shademap.app, off-scope consumer app); `49272282` "Automatic1111 for Apple metal, 40% speed up sd1.5" (46 pts top, therad.ninja — local-inference adjacent to `/themes/04-local-llm.md` but on consumer Stable Diffusion tooling, not Robin's stack); `49275465` "Reflex (YC W23) Is hiring Growth and GTM Roles" (1 pt top, YC jobs page, off-scope); `49275335` "HTML over WebSockets: real-time SPAs with barely any JavaScript" (18 pts top, dev blog, off-scope); `49274858` "We just raised $400M in Series C" (28 pts top, lovable.dev — Lovable.dev Series C announcement, off-scope); `49274854` "Bike Bureau: Report Bike Lane Obstructions" (25 pts top, loudbicycle.com, off-scope); `49274757` "Pixel Watch 5" (18 pts top, blog.google — consumer hardware, off-scope); `49274950` "Qwen3.8-2.4T FP8" (17 pts top, huggingface.co/Qwen/Qwen3.8-2.4T-A95B-FP8 — companion to `49273478`, off-scope open-weight AI); `49275132` "Glaciers on the Climate Dashboard" (41 pts top, climate.metoffice.cloud, off-scope); `49272549` "Why Tiny JPEGs Look Different in Chrome" (157 pts top, guillaumetech.github.io, off-scope). Engagement range 1628 pts across the 21 items; none matches a Robin in-scope vendor / customer / application-domain / named-stack keyword.
- **Synthesis result:** **one theme Last-seen refresh (Wired organoid feature), no commitment row, no open-question row, no personal-logistics item.** The `class-organoid-3d-bioprinting` row on `/themes.md` refreshes Last seen → 2026-08-12, Evidence count → 27+, plus a new evidence anchor for the Wired "AI Is Dead. Organoids Are Alive" feature (`49266068`, 5 pts, by `Logans_Run`, https://www.wired.com/story/organoids-lab-grown-brains-neural-networks/). The `openwiki-brand` watchlist row stays at Last seen 2026-07-16 (the single `openwiki`-query hit is a string collision on "open" + "openweight" — not the `langchain-ai/openwiki` brand signal). All nine flag-for-traceability items stay adjacent-not-promoted under the existing scope discipline. **Key call**: DeepSeek V4 Pro 0813 (`49274600`, 274 pts top+best) is the **third observation in eight days** on the DeepSeek V4 → MiniMax-M3/M3-H3 competitive lane (after `49214008` DeepSeek V4 Flash 0731 ARC-AGI result + the Tavily benchlm.ai benchmark piece). The recurrence is real but per scope discipline ("open-weight AI never earns a `themes.md` row") the observation does not earn a new theme row; per the established pattern of "third corroborating item → row description annex" (framed by the 2026-08-10 Muse Glimmer traceability entry), the trigger is met but the annex would be DeepSeek-V4-Pro-0813-specific, not the always-on-agent-model cluster as previously framed. **No annex is added this run** — the recurring pattern is closer to "competitive-benchmarks lane adjacent to `MiniMax-m3`" than to a new product release on Robin's stack. If a Hermes/MiniMax-side response (e.g. M3.5 release or new Headroom benchmark) on the same competitive pairing surfaces on a future pull, that becomes the first corroborating item for an `MiniMax-m3-row-annex-competitive-benchmarks` entry. This is the **first pull in the 6-query LLM-agent topic set that produces a confirmed organoid hit** (after six consecutive no-promotable-hits pulls since 2026-08-07 12:29); the prior 2026-07-28 owlposting drug-discovery essay (9 pts) + the 2026-07-27 Nature biocomputing article (2 pts) remain the comparison points — see "class-organoid-3d-bioprinting (refreshed this run)" below.
| Query lane | Queries run | Qualifying results |
| --- | --- | --- |
| Life sciences / vendors | `organoid`, `CelVivo`, `3Brain`, `Cellink` | 1 (`organoid``49266068` "AI Is Dead. Organoids Are Alive", Wired, 5 pts; `3Brain` returned the same item as `organoid`; the remaining 10 `3Brain` + 4 `Cellink` items are string-collision noise) |
| AI workflow | `openwiki`, `deepagents` | 0 (`openwiki` → 1 string collision on Qwen 3.8-27B openweight title, not OpenWiki brand; `deepagents` → 0) |
Raw dump: `~/.openwiki/connectors/hackernews/raw/2026-08-12T18-00-01-956Z/hackernews-results.json`.
### class-organoid-3d-bioprinting (refreshed this run)
- **49266068** — score 5 — search hit (`organoid`, also returned by `3Brain`) — "AI Is Dead. Organoids Are Alive" by `Logans_Run`. https://www.wired.com/story/organoids-lab-grown-brains-neural-networks/. Wired feature on lab-grown brain organoids ("computation in meat") versus the AI software-only paradigm — explicitly anchored to brain organoids as the neural-network substrate that outlasts / out-parallels the silicon equivalent. The piece covers the **biocomputing-on-organoid research thread** that the 2026-07-27 Nature biocomputing article (`49071596`) and the 2026-07-28 owlposting "Why haven't organoids solved all of drug discovery?" essay (`49083799`) also spoke to. It directly maps to the **organoid + neuroscience-in-vitro** intersection already documented on the `class-organoid-3d-bioprinting` row. Engagement is low (5 pts) so it does **not** qualify for a new theme row, but it does refresh the Last seen on `/themes.md` so the theme does not go stale on the application-domain side. The `class-organoid-3d-bioprinting` row Last seen → 2026-08-12, Evidence count → 27+, plus a Wired source anchor in the Evidence cell. No new commitment row (no follow-up needed; the Wired feature is a third-party piece, not a product launch or a customer win).
### Flag-for-traceability: DeepSeek V4 Pro 0813, WorldClaw 3D, llama.cpp, GitHub PR/Issues incident — adjacent, off-scope
- **49274600** (274 pts top + 274 pts best) DeepSeek V4 Pro 0813 — **third competitive-benchmark observation in eight days** on the DeepSeek V4 → MiniMax-M3/M3-H3 lane (after `49214008` DeepSeek V4 Flash 0731 ARC-AGI + the Tavily benchlm.ai comparison). The existing `MiniMax-m3` row already cites the DeepSeek V4 Flash vs MiniMax-M3 competitive lane via Tavily (pull 11 of 2026-08-03). The DeepSeek V4 Pro 0813 release is one more open-weight competitor in the same lane; per the brief ("open-weight AI never earns a `themes.md` row" + workflow-tooling priority LOW) the finding stays adjacent-not-promoted. If a Hermes Agent / MiniMax-M3 / M3-H3 head-to-head benchmark or M3.5 response against DeepSeek V4 Pro 0813 surfaces on a future pull, that becomes the first corroborating item for an `MiniMax-m3-row-annex-competitive-benchmarks` description extension.
- **49265051** (265 pts best) WorldClaw Agentic 3D open-world generation at scale — Tencent Hunyuan3D release. Strong topical fit to the 3D-bioprinting + 3D-cell-culture line on `class-organoid-3d-bioprinting` but is open-world 3D scene generation, not 3D bioprinting / tissue engineering. Off-scope per brief.
- **49267928** (333 pts best) llama.cpp — high-engagement promo / directory for the llama.cpp inference backend. Strongest adjacents to `/themes/04-local-llm.md` (llama.cpp is the canonical inference backend used by Ollama and LM Studio). However, `https://llama.app` is a third-party domain, not the upstream `github.com/ggerganov/llama.cpp`, so the content carries an adjacent-tooling signal rather than a direct upstream-release signal. Per the brief ("open-weight AI never earns a `themes.md` row" + workflow-tooling priority LOW), the finding stays adjacent-not-promoted. If the upstream llama.cpp repo releases a documented breaking change on Robin's local-LLM stack on a future pull, that becomes the trigger for a `local-llm-runtime-update` row.
- **49274894** (35 pts top) GitHub PR/Issues incident — workflow-infra adjacent. Real-but-incidental exposure to Robin's Gitea public mirror + any personal GitHub-hosted Pages assets. No operational impact confirmed. Off-scope per brief.
## Update — 2026-08-10 18:00 UTC
- **Coverage:** 2 feeds (`top`, `best`), 6 search queries (the same simplified LLM-agent topic set from the source-specific instruction "Track organoid / CelVivo / 3Brain / Cellink / openwiki / AI agent stories": `organoid`, `CelVivo`, `3Brain`, `Cellink`, `openwiki`, `deepagents`). `top` feed returned 27 items, `best` feed returned 9; deduplication gave **31 unique items across both feeds** (5 overlap: `49241679` Muse Glimmer, `49244569` Kinney Drugs AI phone-assistant, `49245023` Mars Bar 1991, `49245359` Cognitive Commons, `49246057` Stoa Markets GPU marketplace). The 6-query lane produced the hit table below; the connector completed normally at `fetchedAt: 2026-08-10T18:00:52.763Z` (24-hour window).
- **Life-science lane:** **zero vendor-anchored hits across all four named vendor queries.** `organoid` returned 3 hits — all string-collision noise (substring matches on "organiz-" / "organic-"): `49245612` "Show HN: PicPocket Dedicated 'chats' for photo-sharing (share to organize)" (2 pts, https://picpocket.io/); `49245185` "Show HN: Slashscore, an open developer graph built from public GitHub activity" (2 pts, https://www.slashscore.com, "organizations" string hit); `49238127` "Show HN: SynapsCLI lightweight agent runtime in Rust, control an agent swarm" (2 pts, https://github.com/HaseebKhalid1507/SynapsCLI, "organically" string hit). `CelVivo` returned `nbHits=0` (no stories indexed in 24h). `3Brain` returned 7 hits — all string-collision noise on the substring "brain" (none relate to the 3Brain HD-MEA / Accura-3D product line): `49244943` "Real Identity in AI: Why Your AI Agent Should Be More Than a Prompt Box" (3 pts, https://brainmox.com/blog/real-identity-in-ai/, brand "brainmox" string hit); `49243294` "To Begin, Begin" (2 pts, https://brainbaking.com/post/2026/08/to-begin-begin/, brand "brainbaking" string hit); `49243269` "Defending my own brain against enshittification" (90 pts, https://mrmarket.lol/..., personal-essay string hit); `49243199` "Would you trust your boss with data about your brain?" (5 pts, https://calmatters.org/..., neurotech-policy string hit); `49243195` "Show HN: Edgi Letterboxd or Strava for your brain" (4 pts, https://app.edgi.tv/, consumer-product string hit); `49240957` "Brain activity reveals the melodies that people imagine" (4 pts, https://medicalxpress.com/news/2026-07-brain-reveals-melodies-people.html, neuroscience-press string hit); `49236312` "My Brain Doesn't Have Git Worktrees" (2 pts, https://eliasson.me/articles/my-brain-doesnt-have-git-worktrees, dev-essay string hit). `Cellink` returned 5 hits — all string-collision noise on substring "Cell" or author-name fragments (none relate to CELLINK bioprinters): `49246057` "Launch HN: Stoa Markets (YC S26) A Marketplace for GPUs and AI Servers" (24 pts, https://www.stoaexchange.com, body-text "cell" hit); `49242894` "Wellington second-hand bookstore's mysterious orders" (5 pts, https://www.rnz.co.nz/life/books/..., substring hit); `49241749` "Muse Glimmer: Meta's open model built for always-on local agents. 30B parameters" (9 pts, https://developer.meta.com/ai/models/muse-glimmer/, author-name substring hit — same Meta release as the high-engagement top-feed item `49241679`); `49240499` "Let's Stop Calling Everything 'Linear Attention'" (2 pts, https://htor.inf.ethz.ch/blog/..., substring "Lin" → "Cellin" hit); `49239213` "A second-hand bookstore's mysterious orders" (5 pts, https://www.rnz.co.nz/..., substring hit). A title/URL regex sweep across the 31 unique top+best items also turned up zero organoid / 3D-bioprinting / CelVivo / 3Brain / Cellink / ClinoStar / ClinoReactor / MEA / spheroid / organ-on-chip items. The "no material HN footprint for the 4 vendor lines" finding still holds; the Tavily web-search lane remains the better signal for vendor news.
+1
View File
@@ -224,3 +224,4 @@ The `Robin_Picked_Papers` table is **new as of today** — created per Robin's 2
- **Key finding**: AI Virtual Organoids (AIVOs) = 物理类器官 + AI 数字孪生; 数据-模型-交互三层架构; 6 大临床应用方向
- **Business relevance**: 4 大产品线 (CelVivo ClinoStar / 3Brain MEA / Femtobiomed CellShot / Cellink BIO X) 全部可对接 AIVOs 平台 = 完整 湿+干 实验方案
- **Tags**: 综述, 类器官, 人工智能, 虚拟器官, 数字孪生, 多组学, Bioactive-Materials-2026
| 10.1038/s41598-026-42990-2 | Sci Rep 2026 | Liver | Liang 2026 小鼠肝类器官成熟+纤维化建模平台 | obsidian-vault/04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md |
+6
View File
@@ -1,3 +1,9 @@
---
type: "Reference"
title: "NocoDB 文献库索引 — 跨 agent 数据层"
openwiki_generated: true
---
# NocoDB 文献库索引 — 跨 agent 数据层
> 数据源: NocoDB 13 个文献库 + 2 个公司库 (实时,每次 OpenWiki cron 跑时更新)
+6
View File
@@ -1,3 +1,9 @@
---
type: "Reference"
title: "RAGFlow 全文检索索引 (Robin KB system)"
openwiki_generated: true
---
# RAGFlow 全文检索索引 (Robin KB system)
> 数据源: RAGFlow (http://10.10.10.254:9980/) 14 个 KB 全文检索结果
+6
View File
@@ -1,3 +1,9 @@
---
type: "Reference"
title: "SeaFile 大文件存储索引"
openwiki_generated: true
---
# SeaFile 大文件存储索引
> 数据源: SeaFile (http://10.10.10.254:9898/) 共 N 个资料库
+10 -2
View File
@@ -2,12 +2,20 @@
type: "Reference"
title: "Web Search Evidence"
description: "Compact, source-backed evidence and ingestion coverage for the web-search-1 Tavily lane tracking CelVivo, 3Brain, Cellink, and related organoid news."
tags: [source, web-search, tavily, celvivo, 3brain, cellink, organoids]
tags: [source, web-search, tavily, celvivo, 3brain, cellink, organoids, 2026-08-12]
---
# Web Search Evidence
> Connector: `web-search-1` (Tavily). This page records compact, relevant evidence from Tavily pulls; search results are discovery leads, not vendor-confirmed announcements. Latest successful pull: 2026-08-03 18:08 UTC. The 2026-08-08 and 2026-08-10 update attempts were skipped because the connector is disabled and `TAVILY_API_KEY` is not present; no new 24-hour evidence was available on either run.
> Connector: `web-search-1` (Tavily). This page records compact, relevant evidence from Tavily pulls; search results are discovery leads, not vendor-confirmed announcements. Latest successful pull: 2026-08-03 18:08 UTC. The 2026-08-08, 2026-08-10, and 2026-08-12 update attempts were skipped because the connector is disabled and `TAVILY_API_KEY` is not present; no new 24-hour evidence was available on any of these three runs.
## 2026-08-12 attempted update — skipped
- **Status:** skipped. `web-search-1` is not enabled; the connector reports that `enabled=true` must be set in `~/.openwiki/connectors/web-search/config.json`.
- **Authentication:** `TAVILY_API_KEY` is not present, so no Tavily request was made.
- **Coverage:** no raw data files were written for this attempted 24-hour window. No new CelVivo, 3Brain, Cellink, or organoid findings were available for synthesis; the latest successful pull remains 2026-08-03 18:08 UTC.
- **Synthesis:** no changes were made to `/themes.md`, `/commitments.md`, `/open-questions.md`, or `/personal-logistics.md` from this source attempt.
- **Operational note (cross-check):** the on-disk `~/.openwiki/connectors/web-search/config.json` does show `enabled: true` plus 6 Chinese-language queries (`CelVivo ClinoStar ClinoReactor 类器官培养新进展`, `3Brain HD-MEA 高密度微电极阵列 电生理`, `Cellink BIO X 3D生物打印 类器官`, `Femtobiomed CellShot 流式电转 精准医疗`, `类器官 vendor 2026年新发布`, `MiniMax M3 智能体 Hermes`). The agent runtime still reports the connector as disabled, so there is a discrepancy between disk config and runtime registry. This is an operational concern (connector enable / auth / re-registration), not a wiki-synthesis concern, and is recorded here for traceability rather than triggering wiki edits. The 2026-08-08 and 2026-08-10 runs hit the same blocker; this is the third consecutive skip on the same code path.
## 2026-08-10 attempted update — skipped
+6
View File
@@ -1,3 +1,9 @@
---
type: "Reference"
title: "Wiki.js 索引 — 跨 agent 文档发布层"
openwiki_generated: true
---
# Wiki.js 索引 — 跨 agent 文档发布层
> 数据源: Wiki.js (http://10.10.10.254:3000/graphql) Biokingdom 实例
+1 -1
View File
@@ -13,7 +13,7 @@ Index kept narrow by design: only themes that map to Robin's actual work (life-s
| Topic key | Theme / Signal | First seen | Last seen | Confidence | Sources | Evidence count | Status | Evidence |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| `class-organoid-3d-bioprinting` | Recurring organoid, 3D bioprinting, and 3D-cell-culture automation coverage; this window adds a 2026-07-28 HN drug-discovery essay (owlposting "Why haven't organoids solved all of drug discovery?", 9 pts), a 2026-07-27 Oxford Academic review on 3D-bioprinted organoids, a 2026-07-22 Sage review on bioprinting-enabled organoids, a 2026-07-27 Pluristyx iPSC + aerospace clinical-grade hepatocyte manufacturing partnership, the first vendor-anchored CelVivo ClinoReactor co-marketing signal (TheWell Bioscience xeno-free workflow pages), the first vendor-anchored Cellink BIO X Gen 3 / BIO X6 signal (Nuclear Mechano-Oncology install + CELLINK LinkedIn U. Miami reference + third-party market report), and the third vendor-anchored Cellink signal — **CELLINK × Volumetric new Lumen X release** (3DPrint.com 2026-07-28) — plus GEN "Large Bioprinted Tissues Get a Precision Boost" (2026-07-29) and MDPI Cells "Rapid Volumetric Bioprinting Coupled with Dynamic Perfusion Enhances Human Hepatic Organoid Toxicity Testing" (2026-07-27) on top of the prior Nature / HN evidence; pull 7 (2026-07-30) adds FDA NAMs framework (2026-07-27, organ-on-chip included among New Approach Methodologies alongside June 2026 cell/gene-therapy draft guidance), Molecular Cancer patient-derived 3D-bioprinted primary liver cancer (Peking Union Medical College Hospital, 2026-07-28), and npj Biomedical Innovations microvasculature bioprinting review (2026-07-29); pull 11 (2026-08-03) re-anchors the HepatoBiliary Surgery and Nutrition "Spatial architecture and dynamic surveillance: 3D bioprinting and microfluidics converge" review (2026-08-01) as the strongest same-week cross-anchor between organ-on-chip and 3D-bioprinting; **flywheel-sync 2026-08-08** adds 3 deep-read papers: Liu 2026 Nat Biomed Eng (shape-conformal porous framework for full-coverage neural organoid e-phys, Rogers Lab — microlattice fabrication rate 5 for Cellink, HD-MEA rate 5 for 3Brain), Miao 2025 Cell v2 (co-differentiation mesoderm+endoderm for vascularized lung/gut organoids — ClinoStar rate 5, organotypic vascularization), Sharma 2026 Cell Stem Cell (vascularized retinal organoid RGC survival — HD-MEA rate 4, CelVivo ClinoStar rate 3 for extending vascular network stability); still mostly application-domain plus three vendor-channel signals (CelVivo+TheWell; Cellink BIO X Gen 3 / BIO X6; Cellink Lumen X) + three literature flywheel-sync application-domain signals (Liu/Miao/Sharma) | 2026-07-16 | 2026-08-08 | source-backed | hackernews, web-search, literature-flywheel | 26+ | active | [HN: 49083799 drug-discovery essay 2026-07-28](/sources/hackernews.md); [Tavily: 3D bioprinted organoid reviews + Pluristyx + CelVivo+TheWell 2026-07-27](/sources/web-search.md#2026-07-27-1804-pull); [Tavily: Cellink BIO X Gen 3 / BIO X6 + CN Bio / NASA AVATAR OOC + GEN bioprinting 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull); [Tavily: FDA NAMs + Peking Union 3D-bioprinted liver cancer + npj microvasculature 2026-07-30](/sources/web-search.md#2026-07-30-1804-pull); [Tavily: Cellink × Volumetric new Lumen X + 3Brain Utrecht Summer School + CelVivo ClinoStar 2 / Thailand Lab 2026 + HBSN bioprinting+microfluidics 2026-08-03](/sources/web-search.md#2026-08-03-1808-pull); [Flywheel: Liu 2026 NBME shape-conformal framework + Miao 2025 Cell v2 vascularized organoids + Sharma 2026 Cell Stem Cell vascularized retinal organoids 2026-08-08](/sources/literature.md) |
| `class-organoid-3d-bioprinting` | Recurring organoid, 3D bioprinting, and 3D-cell-culture automation coverage; this window adds a 2026-07-28 HN drug-discovery essay (owlposting "Why haven't organoids solved all of drug discovery?", 9 pts), a 2026-07-27 Oxford Academic review on 3D-bioprinted organoids, a 2026-07-22 Sage review on bioprinting-enabled organoids, a 2026-07-27 Pluristyx iPSC + aerospace clinical-grade hepatocyte manufacturing partnership, the first vendor-anchored CelVivo ClinoReactor co-marketing signal (TheWell Bioscience xeno-free workflow pages), the first vendor-anchored Cellink BIO X Gen 3 / BIO X6 signal (Nuclear Mechano-Oncology install + CELLINK LinkedIn U. Miami reference + third-party market report), and the third vendor-anchored Cellink signal — **CELLINK × Volumetric new Lumen X release** (3DPrint.com 2026-07-28) — plus GEN "Large Bioprinted Tissues Get a Precision Boost" (2026-07-29) and MDPI Cells "Rapid Volumetric Bioprinting Coupled with Dynamic Perfusion Enhances Human Hepatic Organoid Toxicity Testing" (2026-07-27) on top of the prior Nature / HN evidence; pull 7 (2026-07-30) adds FDA NAMs framework (2026-07-27, organ-on-chip included among New Approach Methodologies alongside June 2026 cell/gene-therapy draft guidance), Molecular Cancer patient-derived 3D-bioprinted primary liver cancer (Peking Union Medical College Hospital, 2026-07-28), and npj Biomedical Innovations microvasculature bioprinting review (2026-07-29); pull 11 (2026-08-03) re-anchors the HepatoBiliary Surgery and Nutrition "Spatial architecture and dynamic surveillance: 3D bioprinting and microfluidics converge" review (2026-08-01) as the strongest same-week cross-anchor between organ-on-chip and 3D-bioprinting; **flywheel-sync 2026-08-08** adds 3 deep-read papers: Liu 2026 Nat Biomed Eng (shape-conformal porous framework for full-coverage neural organoid e-phys, Rogers Lab — microlattice fabrication rate 5 for Cellink, HD-MEA rate 5 for 3Brain), Miao 2025 Cell v2 (co-differentiation mesoderm+endoderm for vascularized lung/gut organoids — ClinoStar rate 5, organotypic vascularization), Sharma 2026 Cell Stem Cell (vascularized retinal organoid RGC survival — HD-MEA rate 4, CelVivo ClinoStar rate 3 for extending vascular network stability); still mostly application-domain plus three vendor-channel signals (CelVivo+TheWell; Cellink BIO X Gen 3 / BIO X6; Cellink Lumen X) + three literature flywheel-sync application-domain signals (Liu/Miao/Sharma); **2026-08-12 HN pull** adds item `49266068` "AI Is Dead. Organoids Are Alive" (5 pts, Wired, by `Logans_Run`) on lab-grown brain organoids vs silicon AI — application-domain reinforcement of the organoid + neuroscience-in-vitro intersection that the 2026-07-27 Nature biocomputing article (`49071596`) and the 2026-07-28 owlposting drug-discovery essay (`49083799`) already speak to | 2026-07-16 | 2026-08-12 | source-backed | hackernews, web-search, literature-flywheel | 27+ | active | [HN: 49083799 drug-discovery essay 2026-07-28](/sources/hackernews.md); [HN: 49266068 Wired "AI Is Dead. Organoids Are Alive" 2026-08-12](/sources/hackernews.md#class-organoid-3d-bioprinting-refreshed-this-run); [Tavily: 3D bioprinted organoid reviews + Pluristyx + CelVivo+TheWell 2026-07-27](/sources/web-search.md#2026-07-27-1804-pull); [Tavily: Cellink BIO X Gen 3 / BIO X6 + CN Bio / NASA AVATAR OOC + GEN bioprinting 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull); [Tavily: FDA NAMs + Peking Union 3D-bioprinted liver cancer + npj microvasculature 2026-07-30](/sources/web-search.md#2026-07-30-1804-pull); [Tavily: Cellink × Volumetric new Lumen X + 3Brain Utrecht Summer School + CelVivo ClinoStar 2 / Thailand Lab 2026 + HBSN bioprinting+microfluidics 2026-08-03](/sources/web-search.md#2026-08-03-1808-pull); [Flywheel: Liu 2026 NBME shape-conformal framework + Miao 2025 Cell v2 vascularized organoids + Sharma 2026 Cell Stem Cell vascularized retinal organoids 2026-08-08](/sources/literature.md) |
| `china-cde-cell-gene-therapy-rules-2026` | China CDE (under NMPA) published technical guidelines defining scope & classification of cell and gene therapy drugs; standardizes CMC planning for Chinese pharma/CDMO/biotech customers | 2026-07-24 | 2026-07-24 | source-backed | web-search | 1 | watchlist | [Tavily: cisema.com 2026-07-24](/sources/web-search.md) |
| `china-order-no-818-clinical-translation` | China's Order No. 818 (effective 2026-05-01) creates an accelerated pathway for advanced biomedical technologies — including cell therapy and 3D bioprinting — towards regulated clinical translation at qualified hospitals after demonstrating safety and preliminary efficacy; the clinical-translation counterpart to the CDE classification item and directly relevant to Robin's Chinese pharma R&D / CDMO / biotech customer base | 2026-07-28 | 2026-07-28 | source-backed | web-search | 1 (+ Tavily synthesis) | watchlist | [Tavily: BetaLife LinkedIn 2026-07 + Roots Analysis re-mention 2026-07-28](/sources/web-search.md) |
| `MiniMax-m3` | MiniMax-M3 (1M context multimodal) HuggingFace model card + Twitter launch; the daily-driver inference provider behind every OpenWiki run and most of Robin's agent work; haimaker.ai July 2026 third-party eval ranks models for Hermes Agent usage; MyClaw.ai 2026-07-29 confirms M3 + M2.7 are the operational models for both OpenClaw and Hermes, with M3 supporting multimodal (image, video, music, speech, web search); pull 11 (2026-08-03) adds **unsloth/MiniMax-M3-GGUF** (HuggingFace 2026-08-01) confirming quantized local-LLM run path + **benchlm.ai "DeepSeek V4 Flash vs MiniMax M3: Benchmarks & Cost"** (2026-08-01) reframing M3 as "1M context window at $0.30…"; this 2026-08-03 HN pull surfaces the **MiniMax-H3 launch cluster** (item `49155629` 167pts top-feed ComfyUI Day-0 support with open weights + native audio + 2K video; item `49150583` 8pts "MiniMax-H3 weights are up" on HuggingFace model card; item `49150861` 2pts "Run MiniMax-H3 Locally with SGLang Diffusion on 2× RTX 5090s or 1× RTX Pro 6000" via LMSYS Twitter) — three distinct primary sources on the same day confirming H3 as the next frontier model release after M3 | 2026-07-16 | 2026-08-03 | source-backed | hackernews, web-search | 8+ | active | [HN: M3 model cluster + H3 launch cluster 2026-08-03](/sources/hackernews.md); [Tavily: Hermes Agent best-models eval](/sources/web-search.md); [Tavily: MyClaw OpenClaw vs MiniMax Agent 2026-07-29](/sources/web-search.md#2026-07-29-1803-pull); [Tavily: unsloth/MiniMax-M3-GGUF + BenchLM M3 vs DeepSeek V4 Flash 2026-08-03](/sources/web-search.md#2026-08-03-1808-pull) |
+2
View File
@@ -61,6 +61,7 @@ The state diagram shows the canonical CelVivo → 3Brain workflow: 3D suspension
- **Bosnjakovic 2025 bioRxiv (PAH HepG2 3D spheroid, ClinoStar dynamic culture)** — 21-day maturation + 24h/96h BaP/BBF exposure; **4 metabolic markers (phenylalanine, TCA intermediates, GSH depletion, sphingolipid dysregulation) only appear in 3D, completely invisible in 2D**. Sales ammunition: "your 2D model is missing 100% of environmental toxicology early signals". Synthesis at [`/sources/literature-cel-bosnjakovic-2025-pah-deepread.md`](/sources/literature-cel-bosnjakovic-2025-pah-deepread.md).
- **Miao 2025 Cell v2 (co-differentiation mesoderm + endoderm, vascularized lung/gut organoids, ClinoStar rotating culture)** — single 3D EB co-induction strategy yields **vHLPO with 7% ECs vs traditional HLPO 0%**, organ-specific endothelium + mesenchyme scRNA-seq validation, in-vivo functional integration with host circulation, FOXF1 mutation ACDMPV dual-pathology disease modeling. Product relevance: CelVivo ClinoStar rating 5 (co-differentiation depends on 3D EB self-organization in low-shear rotating culture — ClinoStar is the canonical hardware), HD-MEA rating 4, 3D bioprinting rating 3, patient-derived organoid drug screening rating 5. Synthesis at [`/sources/literature-miao-2025-cell-vascularization-v2-deepread.md`](/sources/literature-miao-2025-cell-vascularization-v2-deepread.md).
- **Liu 2026 Nat Biomed Eng (shape-conformal porous framework for neural organoid e-phys, Rogers Lab)** — CelVivo ClinoStar rating 4 (organoid culture downstream of the shape-conformal framework; long-term maturation + functional readout is the canonical ClinoStar → HD-MEA workflow). Synthesis at [`/sources/literature-liu-2026-nbme-shape-conformal-organoid-deepread.md`](/sources/literature-liu-2026-nbme-shape-conformal-organoid-deepread.md). See 3Brain evidence for the HD-MEA read side.
- **Liang 2026 Sci Rep (mouse liver organoid 3-轨道 + fibrosis modeling, 2026-08-12)** — CelVivo ClinoStar rating 4 (P1-P10 长程扩增对应旋转培养 30+ 天无剪切; single DAPT only sustains P5, DAPT+Dex 协同才实现 P10 稳定成熟), CelVivo ClinoReactor rating 4 (单组织 3 轨道 [Hep/Cho/HSC] 分通道灌流; TGFβ 时间程序精确切换实现纤维化激活模型), CelVivo PhaseHolographic 成像 rating 3 (3D 球体直径/CV 实时 QC), 3Brain HD-MEA rating 3 (肝-神经互作延伸场景). 3 轨道 from 单份小鼠肝组织 (密度梯度离心 + 差速贴壁) → DAPT+Dex P1-P10 长程稳定成熟 (ALB / PAS / LDL / CYP 跨代保持) → TGFβ 5-7 天激活 qHSC → aHSC (Acta2/Col1a1 上调) → aHSC 共培养诱导 Hep-Orgs EMT (Snail/Twist/Vimentin ↑; ALB/CK8 ↓; Lgr5/EpCAM ↓; Ki67 ↓) = 体外肝纤维化模型. Wiki.js Id=1716, NocoDB Id=770, PMID 41857098. Page 946 9 项 SOP 重写版 + page 934 修齐 标杆 (4-commit LDR cycle 2026-08-12). **First deep-read whose `related:` field already names `[[MOC-类器官与3D培养]]`** on the day of publication — confirms MOC pattern in active use on real deep-reads. Vault path: `04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md` (170 lines). Sales ammunition: "你的肝类器官只能短期培养? DAPT+Dex P1-P10 稳定成熟 + 单组织 3 轨道 + 14 天纤维化模型 — ClinoStar + ClinoReactor 一站搞定". Customer entry: 药企临床前 (抗纤维化药筛 14+ 天 3D 多细胞模型) + 临床肝活检中心 (1-2 mg 组织 → 3 周药敏 → ClinoReactor 6 通道一次测 6 药). Tracks in `/commitments.md` as `liang-2026-celvivo-clinostar-positioning`.
- **Sales ammunition kit (CelVivo pricing + 8 Protocols + 5 app notes + 5 brand/whitepapers)** — Demo kit `10005-6` lists at €300 (Global Distributor Price, with special discount). 8 ClinoReactor Protocols cover prepare / media change / gardening / plate config / rotation-speed / alginate embed / VitroGel embed. 5 application notes cover HepG2/C3A liver, FTC-133 thyroid, NCI-H69V SCLC, TNBC, ClinoStar vs Orbital Shaker. Synthesis at [`/sources/sales-ammunition.md`](/sources/sales-ammunition.md).
- **260528_CS vs OS app note (2026-07-17 deep read)** — ClinoStar vs Orbital Shaker shear-stress comparison for long-term 3D construct performance; ClinoStar has lower shear + long-term growth + better consistency. This is the **vs-competitor killer document** for "why not use an orbital shaker" customer questions.
- **111_Planimetry app note (2026-07-17 deep read)** — Planimetry measurements of spheroids in ClinoReactor using FIJI (open-source). Standard answer for "how to quantify spheroids".
@@ -110,6 +111,7 @@ The state diagram shows the canonical CelVivo → 3Brain workflow: 3D suspension
| What is Miao 2025's vascularized lung/gut organoid story? | [`/sources/literature-miao-2025-cell-vascularization-v2-deepread.md`](/sources/literature-miao-2025-cell-vascularization-v2-deepread.md) |
| What is Liu 2026's shape-conformal neural organoid e-phys story? | [`/sources/literature-liu-2026-nbme-shape-conformal-organoid-deepread.md`](/sources/literature-liu-2026-nbme-shape-conformal-organoid-deepread.md) |
| What is Sharma 2026's vascularized retinal organoid RGC story? | [`/sources/literature-sharma-2026-cell-stem-cell-vascularized-retinal-organoid-rgc-deepread.md`](/sources/literature-sharma-2026-cell-stem-cell-vascularized-retinal-organoid-rgc-deepread.md) |
| What is Liang 2026's liver organoid fibrosis platform story? | `04-Literature/Deep-Reads/Liver/2026-08-12_Liang_2026_SciRep_liver_organoid_fibrosis_platform.md` (vault path; deep-read synthesis not yet split out to `/sources/`) |
| What distributors am I actually working with? | [`/sources/agents.md`](/sources/agents.md) |
| Which Chinese dealers carry our brand? | [`/sources/distributors-china-2026.md`](/sources/distributors-china-2026.md) |
| What regulatory shifts affect our Chinese pharma deals? | [`/commitments.md`](/commitments.md) China CDE / Order No. 818 / China CGT items |
+14 -13
View File
@@ -22,7 +22,7 @@ This is the synthesis page for **Robin 个人研究项目** — the durable body
```mermaid
erDiagram
VAULT["Obsidian vault (d97b39ed)"] ||--o{ DEEPREADS["Deep-read notes ~1,202"]
VAULT["Obsidian vault (297f106d)"] ||--o{ DEEPREADS["Deep-read notes ~1,204"]
VAULT ||--o{ TRAIN["Sales training (CelVivo赋能培训 v1-v9)"]
VAULT ||--o{ SALES["Active sales pipeline (惠百生物 PO + 中间商)"]
VAULT ||--o{ CRM["Distributor profiles (董慧群 + 待补)"]
@@ -49,18 +49,18 @@ The diagram shows Robin's research substrate: a single Obsidian vault with 8 buc
## Knowledge substrate: Obsidian vault
Snapshot from [`/sources/git-repo.md`](/sources/git-repo.md) (last fetch 2026-08-10T18:06:19Z):
Snapshot from [`/sources/git-repo.md`](/sources/git-repo.md) (last fetch 2026-08-12T18:08:49Z):
| Field | Value |
| --- | --- |
| Repo path | `/home/ldw/workspace` |
| Branch | `main` |
| HEAD | `d97b39edb328b7e15d28de4a54a6d0bc2dd51274` (2026-08-10) |
| Ahead of origin/main | 12 commits new since 2026-08-03 fetch (Fernandez Vallone 2026 + Microbioreactor 2026 + Liu 2026 v2-v11 + 4 经销商 hook 升级 + Wang 2024 Theranostics + **Phase A metadata batch + 2 sample runs**); plus 19 untracked files in working tree |
| HEAD | `297f106d2b137af3480261052ff080cbc48d5b48` (2026-08-12) |
| Ahead of origin/main | 13 commits new since 2026-08-03 fetch (Fernandez Vallone 2026 + Microbioreactor 2026 + Liu 2026 v2-v11 + 4 经销商 hook 升级 + Wang 2024 Theranostics + **Phase A metadata batch + 2 sample runs** + **Liang 2026 liver organoid fibrosis platform 4-commit LDR cycle**); plus 19 untracked files in working tree |
| Auth | local path only — no remote, no credentials |
| Working-tree state | dirty (1 nested-submodule + 1 untracked dir + 19 untracked files including 8 new `02-Clients/Agents/区域-2026-0807.md`) |
| Raw manifest | `~/.openwiki/connectors/git-repo/raw/2026-08-10T18-06-18-966Z/manifest.json` |
| **Latest cluster (2026-08-10)** | **Phase A metadata batch** (`d97b39ed`) + **MOC 方案 1 样品** (`6b717aef`, first MOC `MOC-类器官与3D培养.md`) + **wang2024 方案 2 样品** (`3b929c2f`, 7 image alt descriptions) — frontmatter-hygiene + MOC-discipline sprint, no new external evidence |
| Raw manifest | `~/.openwiki/connectors/git-repo/raw/2026-08-12T18-08-49-138Z/manifest.json` |
| **Latest cluster (2026-08-12)** | **Liang 2026 Sci Rep liver organoid fibrosis platform 4-commit LDR cycle** (`e542c977` adds file 186 lines → `8699a154` page 946 9 项 SOP 重写版 105+/122- → `aacba7aa` frontmatter title 改中文 1 line → `297f106d` page 934 修齐 5+/4-) **net-new external evidence** (DOI 10.1038/s41598-026-42990-2, PMID 41857098, mouse liver 3-轨道 Hep-Orgs + Cho-Orgs + HSC + DAPT+Dex P1-P10 长程成熟 + TGFβ 激活体外纤维化模型) |
### Vault navigation index (top-level folders)
@@ -98,7 +98,7 @@ Snapshot from [`/sources/git-repo.md`](/sources/git-repo.md) (last fetch 2026-08
| `Brain/` | 11 | brain organoid focus |
| `Brain-Tumor/` | 9 | brain tumor organoid |
| `Cancer/` | 6 | cancer organoid |
| `Liver/` | 6 | liver organoid / HepG2 |
| `Liver/` | 7 | liver organoid / HepG2 (Liang 2026 4-commit LDR cycle 2026-08-12) |
| `Other/` | 6 | uncategorised |
| `RegenMed/` | 1 | Ronawk Bio-Block MSC 4-week (added 2026-07-28) |
| `3Brain MEA/` | 3 | 3Brain HD-MEA papers |
@@ -106,7 +106,7 @@ Snapshot from [`/sources/git-repo.md`](/sources/git-repo.md) (last fetch 2026-08
| `Kidney/` | 2 | kidney organoid |
| `Retinal/` | 1 | retinal organoid |
Total ≈ 1,202 deep-read notes. The 4 vendor subfolders (Celvivo / 3Brain / Cellink / Organoid) cover the canonical product KB per the wiki goal focus areas.
Total ≈ 1,203 deep-read notes (the 2026-08-12 Liang 2026 liver organoid fibrosis platform file is the net-new entry since the 2026-08-10 fetch). The 4 vendor subfolders (Celvivo / 3Brain / Cellink / Organoid) cover the canonical product KB per the wiki goal focus areas.
## Literature deep-read (LDR) pipeline
@@ -176,12 +176,13 @@ From [`/sources/ldr-report-template.md`](/sources/ldr-report-template.md) (Robin
| Miao 2025 Cell v2 (2026-08-08 flywheel-sync) | CelVivo (ClinoStar rating 5) | `/home/ldw/workspace/Miao2025_Cell_v2.md` | [`/sources/literature-miao-2025-cell-vascularization-v2-deepread.md`](/sources/literature-miao-2025-cell-vascularization-v2-deepread.md) |
| Liu 2026 Nat Biomed Eng (2026-08-08 flywheel-sync) | 3Brain (HD-MEA rating 5) + Cellink (microlattice rating 5) | `/home/ldw/workspace/Liu2026_NBME_shape_conformal_organoid.md` | [`/sources/literature-liu-2026-nbme-shape-conformal-organoid-deepread.md`](/sources/literature-liu-2026-nbme-shape-conformal-organoid-deepread.md) |
## Recent 30-day research output (mtime 2026-06-16 → 2026-08-10)
## Recent 30-day research output (mtime 2026-06-16 → 2026-08-12)
From [`/sources/literature.md`](/sources/literature.md) last sync, broken out by vendor and date:
| Date | DOI / slug | Vendor | Topic |
| --- | --- | --- | --- |
| 2026-08-12 | **Liang 2026 liver organoid fibrosis platform 4-commit LDR cycle** (commits `e542c977` + `8699a154` + `aacba7aa` + `297f106d`) | **CelVivo (ClinoStar rating 5 + ClinoReactor rating 5)** | Liang Y et al. (2026) A robust mouse liver organoid platform enables sustained multicellular maturation and fibrosis modeling from a single tissue sample (Sci Rep DOI 10.1038/s41598-026-42990-2, PMID 41857098; Wiki.js Id 1716, NocoDB Id 770; 3 轨道 Hep-Orgs + Cho-Orgs + HSC 同步分离; DAPT+Dex P1-P10 长程稳定成熟 [ALB/PAS/LDL/CYP 跨代保持]; TGFβ 激活 qHSC → aHSC [Acta2/Col1a1 上调]; aHSC 共培养诱导 Hep-Orgs EMT [Snail/Twist/Vimentin↑; ALB/CK8↓; Lgr5/EpCAM↓; Ki67↓] = 体外肝纤维化模型) — page 946 9 项 SOP 重写版 + page 934 修齐 标杆; 7/7 Ollama qwen2.5vl 视觉审核通过; SeaFile 7/7 公网 200 验真. First paper whose `related:` field already names `[[MOC-类器官与3D培养]]` (the 2026-08-10 first MOC) on the day of publication. |
| 2026-08-10 | **Phase A metadata batch + first MOC** (commits `d97b39ed` + `6b717aef` + `3b929c2f`) | (process discipline) | 6 deep-reads received the 6-field frontmatter (doi/journal/year/volume/pages/authors/pmid); first MOC `MOC-类器官与3D培养.md` (95 lines, 沙牛《AI 时代的 Obsidian 公开课》课时 1 pattern) created at `04-Literature/Deep-Reads/MOCs/`; 7 image alt descriptions added on `wang2024-org-on-chip.md`. No new external evidence. |
| 2026-08-09 | `10.7150/thno.90492` (Wang 2024) | (4 类共性硬件 — Organoid-on-Chip 综述) | Wang H et al. (2024) Human organoids-on-chips for biomedical research and applications (Theranostics 14(2):788-818, PMID 38169573; 7 图覆盖 7 大主题板块) — Wiki.js ID 1700 (v2 - grp:3 ghost page 累加) |
| 2026-08-08 | `10.3390/cells15110963` (Fernandez Vallone 2026) | (NAMs adjacent, hiPSC brain organoid) | THSDC chemical evaluation platform using hiPSC brain organoids (Cells, v2 5 张真图 + 双 H1; Wiki.js Id 1698) |
@@ -208,15 +209,15 @@ From [`/sources/literature.md`](/sources/literature.md) last sync, broken out by
By vendor (30-day mtime):
| Vendor | Most recent | 2026-08-08 / 2026-08-10 additions |
| Vendor | Most recent | 2026-08-08 / 2026-08-10 / 2026-08-12 additions |
| --- | --- | --- |
| CelVivo | 2026-08-08 (Miao 2025 v2 — ClinoStar rating 5) | +Miao 2025 v2 (ClinoStar co-differentiation), +Sharma 2026 (ClinoStar rating 3 adjacent), +Liu 2026 (ClinoStar rating 4 adjacent) |
| CelVivo | 2026-08-12 (Liang 2026 — ClinoStar rating 5 + ClinoReactor rating 5) | +Liang 2026 (P1-P10 长程成熟 + 单组织 3 轨道分通道灌流 + TGFβ 时间程序精确切换 — liver organoid fibrosis platform), +Miao 2025 v2 (ClinoStar co-differentiation), +Sharma 2026 (ClinoStar rating 3 adjacent), +Liu 2026 (ClinoStar rating 4 adjacent) |
| 3Brain | 2026-08-08 (Liu 2026 — HD-MEA rating 5) | +Liu 2026 (shape-conformal framework, next-gen HD-MEA), +Sharma 2026 (HD-MEA rating 4 adjacent), +Shin 2024 (Phase A frontmatter hygiene on existing note) |
| Cellink | 2026-07-27 (Tasevska 2025) | +Liu 2026 (microlattice fabrication rating 5 adjacent) |
| Adjacent (no vendor) | 2026-08-08 (Sharma 2026 retinal vascularization) | +Sharma 2026 (retinal organoid application domain) |
| (Process discipline) | 2026-08-10 (Phase A batch + first MOC) | +6 deep-reads received 6-field frontmatter; +first MOC `MOC-类器官与3D培养.md` created; +7 image alt descriptions on Wang 2024 — no new external evidence |
The pipeline is **vendor-balanced** — CelVivo, 3Brain, Cellink each have a recent deep read, and the 2026-08-08 flywheel-sync adds **3 papers spanning all 3 primary vendors + the retinal organoid application domain** (Sharma), all 3 rated 4-5 on at least one vendor's product line. The 2026-08-10 cluster is **process discipline** (Phase A metadata batch + first MOC creation + Wang 2024 alt-description sample), not new external evidence — the 6 deep-reads already existed on `main`; the 3 commits only normalize their metadata and add a knowledge-graph index layer. The **first entry in the new NocoDB table `Robin_Picked_Papers`** is Liu 2026 (created 2026-08-08 per Robin instruction to capture papers Robin hand-picks / provides outside the regular PubMed triage). The **first MOC** `MOC-类器官与3D培养.md` is the start of a Map-of-Content layer Robin appears to be building (the MOC's own `related:` already names `[[MOC-3Brain-HD-MEA]]` as the next planned MOC).
The pipeline is **vendor-balanced** — CelVivo, 3Brain, Cellink each have a recent deep read, and the 2026-08-08 flywheel-sync adds **3 papers spanning all 3 primary vendors + the retinal organoid application domain** (Sharma), all 3 rated 4-5 on at least one vendor's product line. The 2026-08-10 cluster is **process discipline** (Phase A metadata batch + first MOC creation + Wang 2024 alt-description sample), not new external evidence — the 6 deep-reads already existed on `main`; the 3 commits only normalize their metadata and add a knowledge-graph index layer. The 2026-08-12 cluster adds **net-new external evidence**: Liang 2026 Sci Rep liver organoid fibrosis platform (4-commit LDR cycle on a single paper, CelVivo ClinoStar ⭐⭐⭐⭐ + ClinoReactor ⭐⭐⭐⭐); this is the **first paper on `main` whose `related:` field already names `[[MOC-类器官与3D培养]]` on the day of publication**, confirming the MOC pattern is in active use on real deep-reads (vs the prior 2026-08-10 "MOC `related:` lists future MOCs" framing which was only prospective). The **first entry in the new NocoDB table `Robin_Picked_Papers`** is Liu 2026 (created 2026-08-08 per Robin instruction to capture papers Robin hand-picks / provides outside the regular PubMed triage). The **first MOC** `MOC-类器官与3D培养.md` is the start of a Map-of-Content layer Robin appears to be building (the MOC's own `related:` already names `[[MOC-3Brain-HD-MEA]]` as the next planned MOC).
## Sales ammunition pipeline
@@ -391,4 +392,4 @@ These are source-anchored but not vendor-anchored — they live here for traceab
| How does the agent stack consume this output? | [`/themes/03-ai-agents.md`](/themes/03-ai-agents.md) |
| How does the local-LLM fleet host this evidence? | [`/themes/04-local-llm.md`](/themes/04-local-llm.md) |
| Where does CelVivo + 3Brain output land? | [`/themes/01-organoid-equipment.md`](/themes/01-organoid-equipment.md) |
| Where does Cellink output land? | [`/themes/02-bioprinting.md`](/themes/02-bioprinting.md) |
| Where does Cellink output land? | [`/themes/02-bioprinting.md`](/themes/02-bioprinting.md) ||