
We build insight moment for scientific research. Community Operations Based on AIPOCH Open-Science @aipoch_ai
Joined July 2026
- Tweets472
- Following255
- Followers213
- Likes1.4K
Open-source local research agent hits 46.30% on AstaBench’s hardest coding split (SUPER-Expert). Above the current official top scores.
AIPOCH Open-Science scored 46.30% on AstaBench SUPER-Expert in a local evaluation with DeepSeek Flash/max, covering all 45 tasks in the official test split. ⬇️⬇️⬇️
2
15
🚀 AIPOCH Open-Science v1.3.0 is out! 🎉
This release brings research automation, AI-powered creation, and smarter workflows.
✨ Scheduled Research Tasks for Sessions & Notebooks
✨ AI Image Generation & Editing with version history
✨ Edit PowerPoint presentations directly in Open-Science
✨ Research Film replay with independent branch outputs
✨ Smarter Agent questions with option trade-offs
✨ CodeBuddy subscription support for China & International regions
✨ Notebook process monitoring & management
⚡ Faster long Conversations, automatic recovery & improved Windows updates
AIPOCH Open-Science v1.3.0 — automate research, create more, and keep your workflows moving.
🔗 github.com/aipoch/open-scien…
⭐ Star us: github.com/aipoch/open-scien…
AIPOCH Open-Science v1.3.0 is out!
This release focuses on research automation, creative tools, and workflow reliability. It introduces Scheduled Research Tasks, AI Image Generation and Editing, editable PowerPoint presentations, Research Film replay, and smarter Agent interactions, alongside improvements to Session performance and Windows updates.
【🚀 New Features】
⏰ Scheduled Research Tasks
Open-Science now supports recurring and one-time research tasks.
- Automatically launch Sessions or Notebook runs on a schedule.
- Track each execution with its own Workspace record.
- Review run history and manage schedules.
Scheduled tasks run while the app is running, using the project's existing permissions and configured provider quota.
🎨 AI Image Generation & Editing
Generate and edit images directly through your configured model provider.
- Create images from text prompts.
- Refine images with follow-up instructions.
- Preserve each generation and edit as a new Artifact Version.
- Compare and reuse previous versions.
📊 Editable PowerPoint Presentations
PowerPoint files can now be edited directly inside Open-Science.
- Edit slide text without leaving the application.
- Adjust fonts, sizes, colors, and alignment.
- Preserve the original slide structure.
🎬 Research Film Replay & Branching
Research Film workflows now support operation replay with independent branch outputs.
- Replay Film operations on new branches without modifying the original.
- Open generated Films directly from the Session menu.
- View token usage information before generation.
🤖 Smarter Agent Questions & CodeBuddy Support
- Agent questions now explain the trade-offs between available options.
- CodeBuddy subscription sign-in supports China and International regions.
- Available CodeBuddy models are discovered through the managed CLI.
- Running Notebook processes can be monitored and stopped from the app.
- Document and Figure Skills automatically prepare required libraries on first use.
【🔧 Improvements】
- Faster loading and incremental persistence for long Conversations.
- Improved application Startup performance.
- Automatic recovery for stalled Film generation, Research Package transfers, and background deliveries.
- Transient Film generation failures can retry automatically.
- Improved scientific PDF structure recovery and reading experience.
- More responsive Composer controls and Conversation navigation.
- Faster and more reliable Windows installation and update processes.
- Reduced background Compute recovery overhead.
【🐛 Bug Fixes】
- Sessions & Agents — Fixed Session numbering, journal replay, Agent resource cleanup, Skill reload interruptions, and handoff metadata preservation.
- Research Films — Improved checkpoint recovery, timeout reporting, and imported Film playback.
- Notebook & Compute — Improved Notebook transcript pagination, remote task cancellation, and Ray job cleanup.
- Artifacts & Packages — Fixed CLI Artifact download timeouts and imported Film access.
- PDF & Interface — Improved Preview file identity, Run Mark positioning, Project navigation, and Markdown scrolling.
- Windows & Runtime — Improved installer signature validation, process cleanup, and update reliability.
🧭 Important Notes
- Scheduled tasks use existing Project permissions and may consume provider quota without additional confirmation.
- Image generation and editing send prompts and source images to the configured provider. Review sensitive material before submitting it.
2
33
Gwayne Stark retweeted
AIPOCH Open-Science v1.3.0 is out!
This release focuses on research automation, creative tools, and workflow reliability. It introduces Scheduled Research Tasks, AI Image Generation and Editing, editable PowerPoint presentations, Research Film replay, and smarter Agent interactions, alongside improvements to Session performance and Windows updates.
【🚀 New Features】
⏰ Scheduled Research Tasks
Open-Science now supports recurring and one-time research tasks.
- Automatically launch Sessions or Notebook runs on a schedule.
- Track each execution with its own Workspace record.
- Review run history and manage schedules.
Scheduled tasks run while the app is running, using the project's existing permissions and configured provider quota.
🎨 AI Image Generation & Editing
Generate and edit images directly through your configured model provider.
- Create images from text prompts.
- Refine images with follow-up instructions.
- Preserve each generation and edit as a new Artifact Version.
- Compare and reuse previous versions.
📊 Editable PowerPoint Presentations
PowerPoint files can now be edited directly inside Open-Science.
- Edit slide text without leaving the application.
- Adjust fonts, sizes, colors, and alignment.
- Preserve the original slide structure.
🎬 Research Film Replay & Branching
Research Film workflows now support operation replay with independent branch outputs.
- Replay Film operations on new branches without modifying the original.
- Open generated Films directly from the Session menu.
- View token usage information before generation.
🤖 Smarter Agent Questions & CodeBuddy Support
- Agent questions now explain the trade-offs between available options.
- CodeBuddy subscription sign-in supports China and International regions.
- Available CodeBuddy models are discovered through the managed CLI.
- Running Notebook processes can be monitored and stopped from the app.
- Document and Figure Skills automatically prepare required libraries on first use.
【🔧 Improvements】
- Faster loading and incremental persistence for long Conversations.
- Improved application Startup performance.
- Automatic recovery for stalled Film generation, Research Package transfers, and background deliveries.
- Transient Film generation failures can retry automatically.
- Improved scientific PDF structure recovery and reading experience.
- More responsive Composer controls and Conversation navigation.
- Faster and more reliable Windows installation and update processes.
- Reduced background Compute recovery overhead.
【🐛 Bug Fixes】
- Sessions & Agents — Fixed Session numbering, journal replay, Agent resource cleanup, Skill reload interruptions, and handoff metadata preservation.
- Research Films — Improved checkpoint recovery, timeout reporting, and imported Film playback.
- Notebook & Compute — Improved Notebook transcript pagination, remote task cancellation, and Ray job cleanup.
- Artifacts & Packages — Fixed CLI Artifact download timeouts and imported Film access.
- PDF & Interface — Improved Preview file identity, Run Mark positioning, Project navigation, and Markdown scrolling.
- Windows & Runtime — Improved installer signature validation, process cleanup, and update reliability.
🧭 Important Notes
- Scheduled tasks use existing Project permissions and may consume provider quota without additional confirmation.
- Image generation and editing send prompts and source images to the configured provider. Review sensitive material before submitting it.
The real gap isn’t which model can summarize papers better. It’s what happens after you have a result.
Can you explain the figure to a room, and can a collaborator later open the exact analysis that produced it?
That’s the part this comparison highlights.
Compare ChatGPT, Gemini, Claude, Perplexity, and AIPOCH Open-Science by the research task each can support and the evidence a researcher can inspect.
2
51
More specialized AI models mean more choices for researchers.
But what happens to your research history when you switch models or tools?
We're exploring model-agnostic research workflows with AIPOCH Open-Science, using .science packages to keep research context shareable.
Thoughts?
Microsoft unveiled 7 new AI models. Science will be multi-model—but research shouldn't lose its history when tools change.
AIPOCH Open-Science's .science packages preserve selected conversation branches, files and evidence for review.
aipoch.com/open-science
1
3
60
$5B for AI drug discovery is a huge signal for the future of biotech.
But scientific breakthroughs need more than promising predictions.
How can we make AI-driven drug research easier to verify, reproduce, and build upon?
That's the idea behind our .science packages.
Isomorphic Labs raised $5B for AI drug discovery. But a molecule is only part of the story—what data and analyses produced it?
AIPOCH Open-Science's .science packages carry selected files, research history and evidence for others to inspect.
aipoch.com/open-science
2
132
GPT-6.2 Astra is pushing the boundaries of AI-powered science.
But here's a question for researchers: if an AI agent makes a discovery, how much of its process should be reproducible?
That's exactly why we're exploring shareable .science research packages. 🔬
GPT-6.2 Astra topped Terminal-Bench-Science. But benchmark wins aren't reproducible research.
AIPOCH Open-Science's .science packages preserve research branches, files and evidence—so collaborators can inspect the work behind a result.
aipoch.com/open-science
1
30
🚀 AIPOCH Open-Science v1.2.2 is out! 🎉
This release brings stronger Notebook security, resumable research workflows, and more reliable PDF processing.
✨ Strict Notebook Networking with customizable whitelist rules
✨ Research Film generation resumes from checkpoints
✨ More accurate PDF Figures, Tables & reading order
✨ Improved PDF translation with better layout fidelity
✨ Safer Windows folder grants & update recovery
✨ Qwen4 Max Preview with 1M context + multimodal input
⚡ Stronger Notebook, Session, CLI & Runtime stability
AIPOCH Open-Science v1.2.2 — safer execution, more reliable recovery, and better research workflows.
🔗 github.com/aipoch/open-scien…
⭐ Star us: github.com/aipoch/open-scien…
AIPOCH Open-Science v1.2.2 is out! This release focuses on Notebook network security, research workflow recovery, and PDF processing reliability. It introduces Strict Notebook Networking, resumable Research Film generation, improved PDF extraction and translation, safer Windows permissions, and Qwen4 Max Preview support.
【🚀 New Features】
🔐 Strict Notebook Networking
Notebook networking now supports an optional Strict Mode with a manually managed whitelist.
- Allow requests only when they match approved protocols, hosts/IPs, and ports.
- Block unmatched requests without prompting for authorization.
- Manage persistent whitelist rules with provenance information.
- Keep Relaxed Mode as the default with existing approval behavior.
🎬 Resumable Research Film Generation
Research Film generation can now resume from validated checkpoints after interruptions or application restarts.
- Preserve completed scenes, narration, and timing information.
- Track progress across five generation steps.
- Choose between resuming previous work or starting fresh.
📄 Improved PDF Extraction & Translation
Scientific PDF processing now preserves document structure more accurately.
- Recover complete Figures, Captions, Tables, and reading order.
- Improve extraction of complex scientific layouts.
- Preserve original PDF structure during translation.
- Retain original content when translated placement cannot be reliably verified.
🛡️ Safer Windows Folder Permissions
Windows Protected Mode now validates folder permissions before saving access grants.
Unusable folders are rejected with clear explanations, preventing unexpected Notebook execution failures.
🤖 Qwen4 Max Preview Support
Qwen4 Max Preview joins Bailian Token Plans in Beijing and Singapore.
- 1M-token context window
- Multimodal input support
- Low, Medium, and XHigh reasoning efforts
【🔧 Improvements】
- More reliable Windows updates, uninstall processes, and installation recovery.
- Clearer Session Package import errors and retry guidance.
- Improved mobile Preview layouts.
- Updated default models for official Provider connections.
- More reliable CLI credentials, Artifact downloads, and console handling.
- Support for registered aliases of configured data roots.
【🐛 Bug Fixes】
- Windows & Updates — Improved process detection, installation handoff, cleanup, and diagnostic preservation.
- Notebook & Runtime — Fixed interrupted Kernel recovery, PowerShell output handling, and unrelated folder grants blocking startup.
- Sessions & Agents — Improved Session persistence, Provider error reporting, prompt cancellation, and recovery after connection loss.
- PDF & Preview — Improved translation layout fidelity and Preview stability.
- Remote Compute — Improved SSH job cancellation handling.
- Interface — Fixed contrast issues across themes and improved review status messages.
3
97
From a .science research package to a film you can share.
Start with the research you already have → Give the audience a question they can see → Bring the film into the conversation.
From a .science research package to a film you can share
- Start with the research you already have
- Give the audience a question they can see
- Bring the film into the conversation
Read the full article here: aipoch.com/blog/research-fil…
2
38
AIPOCH guide shows how their Open-Science workbench turns that problem into a concrete provenance + reproduction workflow. Solid read for anyone doing (or reviewing) AI-assisted research.
A practical guide to inspecting research evidence, reconstructing scripts, and checking reproducibility in AIPOCH Open-Science.
2
94
The Project Suncatcher .science package lets you check the sign change against the saved report and fixed-area table, then use a writable copy in the AIPOCH Open-Science desktop app to test whether a different absorbed flux would leave enough capacity for the computer’s 1 kW load.
Explore how environmental heating changes the radiator area needed to reject a fixed 1 kW heat load in an AIPOCH Open-Science study inspired by Project Suncatcher.
2
54
AIPOCH Open-Science reports 145 successful runs out of 210 on Terminal-Bench-Science 0.1. Read the result, the dated leaderboard comparison, and the limits of a local evaluation.
AIPOCH Open-Science achieved a 69.05% local pass rate on Terminal-Bench-Science 0.1 with GPT-6 Astra at max reasoning effort: 145 successful executions out of 210.
TB-Science 0.1 contains 70 expert-designed tasks across life, physical, earth, mathematical, and engineering sciences. Agents work with supplied data and tools, carry out scientific computation, and deliver outputs assessed against each task’s verification requirements.
The workflows test method selection, scientific programming, data analysis, statistical inference, modeling, simulation, optimization, and result validation.
For reference, the official leaderboard snapshot from November 13, 2026, at 10:55 Beijing time listed:
- Codex × GPT-6 Astra — 68.10%
- Claude Code × Opus 5.5 — 63.33%
- Claude Code × Fable 5.1 — 40.00%
The AIPOCH Open-Science local result is 0.95 percentage points above the highest official score in that snapshot. This is a numerical comparison of a local evaluation with published results—not an official leaderboard placement or a claim of a statistically significant lead.
4
303
AI meets the knapsack problem.
AIPOCH Open-Science examined a 20 kg packing limit: a hand-worked plan scored 162 vs 152 for the saved AI choice. Both fit the limit; the archived solver run was blocked.
Explore the study → aipoch.com/open-science/use-…
I asked AIPOCH Open-Science to choose what to pack under a 20 kg luggage limit.
It picked 20 items worth 152 points. A manual comparison fit 23 items worth 162 points, still under the same limit.
The workflow compares the packing lists and saves the scores, calculations, and verification code in a .science session. The solver failed to run, so the exact optimum remains unverified.
youtube.com/watch?v=8prtWhmW…
2
47
I asked AIPOCH Open-Science to track tree-cover loss in a patch of Peru’s Amazon.
It analyzed 24 years of satellite data. Three different canopy thresholds all pointed to the same peak year: 2024.
The workflow starts with satellite data, compares the thresholds, plots the loss over time, then packages the code, data, and charts into a shareable .science file.
aipoch.com/
Explore an Amazon deforestation case near Iberia, Peru: see why a stricter canopy cutoff reduces mapped tree-cover loss in hectares but raises its baseline share.
1
146
Is Amazon tree-cover loss changing, or is it how we define a forest?
Using AIPOCH Open-Science, we analyzed satellite data from 2001–2024 across different canopy thresholds.
The results? Loss estimates shifted with the definition, but 2024 remained the peak year across all thresholds.
With a reproducible .science package, every dataset, analysis, and conclusion can be traced and verified.
🔗 Explore the research:
aipoch.com/open-science/use-…
#OpenScience #AIforScience #AmazonRainforest
Is the Amazon losing more forest, or are we changing how we measure it?
youtube.com/watch?v=5MPZkm9A…
What if the definition of a forest changes the numbers, but not the story?
Using AIPOCH Open-Science, we investigated tree-cover loss in a fixed area of the western Amazon, Peru, analyzing satellite data from 2001–2024.
Here's what we uncovered:
• At a 30% canopy threshold, mapped tree-cover loss reached 25,133 hectares (55.54%).
• Raising the threshold to 75% reduced the measured loss area by just 1.08%, while the percentage of eligible baseline area lost actually increased.
• Across all three thresholds (30%, 50%, 75%), 2024 remained the peak year for tree-cover loss.
The lesson? Scientific conclusions depend on how we define, measure, and interpret the data. Some findings shift with our assumptions. Others remain remarkably consistent.
With AIPOCH Open-Science, we turned this question into a reproducible research workflow, preserving the analysis code, datasets, visualizations, and research history in a shareable .science package.
Because good science isn't just about finding answers. It's about making those answers verifiable.
2
162
🚀 AIPOCH Open-Science v1.2.1 is out! 🎉
This release brings smarter resource management, stronger AI Agents, and more reliable research workflows.
✨ Unified Resource Center for Skills, Connectors & Specialists
✨ Scientific Prompt Optimization with review, edit & undo
✨ Codex subscription support in the built-in Agent
✨ Claude Fable 5.2 with 1M-token context
✨ Faster, smaller .science exports with deduplicated evidence
✨ Improved Modal & Hugging Face Jobs authentication
✨ Literature metadata export as CSV
⚡ Better long-response handling, Runtime memory management & Windows updates
AIPOCH Open-Science v1.2.1 — smarter Agents, simpler resource management, and more efficient research.
🔗 github.com/aipoch/open-scien…
⭐ Star us: github.com/aipoch/open-scien…
AIPOCH Open-Science v1.2.1 is out!
github.com/aipoch/open-scien…
This release focuses on resource management, AI Agent capabilities, and research workflow reliability. It introduces a unified Resource Center, scientific prompt optimization, Codex subscription support, Claude Fable 5.2, compact research evidence storage, and improvements to cloud computing, Windows updates, and Runtime performance.
【🚀 New Features】
🧩 Unified Resource Center
Skills, Connectors, Specialists, and Marketplace resources are now managed in one Resource Center.
- Browse resources through unified cards, filters, and detail views.
- Install Marketplace resources directly from Desktop or Web.
- Manage multiple resources with batch selection.
- Open Skill references without interrupting the active Conversation.
✨ Scientific Prompt Optimization
The Composer now supports project-scoped scientific prompt optimization.
- Optimize research prompts with one click.
- Review and edit suggestions before applying them.
- Undo changes and restore the previous draft.
- Create custom optimization templates in Project Settings.
- Optimization runs only when manually requested, using the configured provider.
🤖 Expanded Built-in Agent Capabilities
The built-in Open-Science Agent now supports:
- Codex subscription accounts for the Main Agent and Subagents.
- Claude Fable 5.2 with a 1M-token context window.
- Longer model responses without the previous 4,096-token limit.
- Improved context management for long research Sessions.
📦 Compact Research Evidence Storage
Notebook and Compute evidence is now stored in a deduplicated, verifiable format.
Repeated evidence is stored once with verified digests, making .science exports of long research histories smaller and faster.
☁️ Improved Cloud Compute Authentication
Modal and Hugging Face Jobs now prepare a compatible Python Runtime before browser authorization.
Account verification follows the system proxy, improving connectivity and sign-in reliability.
📚 Literature CSV Export
Literature metadata can now be exported as CSV, alongside BibTeX and RIS.
Researchers can export selected references across pages or complete Projects and Collections using 16 standardized English columns.
【🔧 Improvements】
- Built-in Agent now respects provider-supported output limits and native protocols.
- Improved context usage measurement and compaction in long Sessions.
- Answered Agent questions continue without unnecessary persistence delays.
- Research Film generation continues when switching Sessions.
- Idle Python, R, REPL, and Shell Runtimes are automatically reclaimed after 15 minutes of inactivity.
- Improved Resource Center presentation and context-reset notifications.
【🐛 Bug Fixes】
- Windows & Updates — Fixed signed update packaging, installation blockers, process detection, and recovery diagnostics.
- Agents & Providers — Improved provider error reporting, OpenCode request handling, and Conversation completion.
- Notebook & Compute — Restored Notebook attachment previews, local file links, and Linux Runtime recovery.
- Literature & PDF — Fixed DOI capitalization, reference import routing, damaged PDF extraction, and translation isolation.
- Sessions & Packages — Fixed local CLI package imports, Conversation persistence, and first-message navigation.
- Web & Interface — Improved mobile pairing, remote-control error reporting, and responsive source previews.
1
4
298
Can we reproduce Chinchilla scaling?
AIPOCH Open-Science closely matched Epoch AI’s fit using reconstructed data.
Optimizer settings affected uncertainty; ~20 tokens per parameter remained compatible with the main fit.
Can We Reproduce Chinchilla Scaling?
youtube.com/watch?v=U78VT1-n…
Chinchilla’s “20 tokens per parameter” rule deserves a closer look. With AIPOCH Open-Science, we revisited the public evidence behind compute-optimal AI training and made the analysis available to inspect and replay.
1️⃣ Start with the evidence: 245 points reconstructed by Epoch AI from Chinchilla’s Figure 4. Use 240 for the main fit and retain five unusually undertrained runs for a sensitivity check.
2️⃣ Refit the scaling law: Model loss as a function of parameter count and training tokens, using 4,500 initializations and a robust log-space objective. The result closely matches Epoch AI’s fitted parameters.
3️⃣ Compare on equal terms: On the same 240 observations, the original paper’s rounded Approach 3 parameters produce about 4× the refit’s log-space Huber error.
4️⃣ Investigate uncertainty: Run 2,000 bootstrap resamples and a separate 100-repeat, 80%-subsample analysis. The latter’s 10th–90th percentile interval for the model-size allocation exponent is about 26× wider than originally reported. Optimizer diagnostics show how early stopping can artificially narrow intervals; they do not establish what happened in the original study.
5️⃣ Test the “20” rule: At 10²⁶ FLOP, the main fit projects 15.5 tokens per parameter, with a 95% bootstrap interval of 4.5–42.4. Including all five extreme runs shifts the estimate to 3.5. These are extrapolations far beyond the observed compute range.
6️⃣ Keep the work inspectable: AIPOCH Open-Science preserves the report, six figures, code, data and comparison runs together, including the earlier implementation revised during the investigation.
This reproduces a fit to reconstructed data; it does not retrain Chinchilla.
2
76
🚀 AIPOCH Open-Science v1.2.0 is out! 🎉
This release brings cloud computing, a built-in AI Agent, and more flexible research workflows.
✨ Run approved jobs on Kubernetes, Hugging Face Jobs, Modal & Ray
✨ Built-in Open-Science Agent becomes the default for new setups
✨ Claude Code, OpenCode, Codex, CodeBuddy & Pi remain supported
✨ Faster macOS updates with differential downloads
✨ Step-linked discussions for imported .science research
✨ Cleaner Workspace navigation & Session management
✨ Source Link Previews with metadata
⚡ Improved Notebook, PDF translation & cross-platform stability
AIPOCH Open-Science v1.2.0 — more compute options, smarter Agents, and more connected research workflows.
🔗 github.com/aipoch/open-scien…
⭐ Star us: github.com/aipoch/open-scien…
AIPOCH Open-Science v1.2.0 is out!
github.com/aipoch/open-scien…
This release focuses on cloud computing, AI Agent capabilities, and research workflow continuity. It introduces four new remote compute backends, a built-in Open-Science Agent, faster macOS updates, step-linked discussions for imported research, and improvements to Workspace navigation, Notebook performance, and PDF translation.
【🚀 New Features】
☁️ Four New Remote Compute Backends
Open-Science now supports running approved research jobs on four additional compute platforms:
- Kubernetes
- Hugging Face Jobs
- Modal
- Ray
Alongside existing SSH and Slurm support, researchers can submit jobs with explicit approval of the target, command, resources, and outputs.
Job recovery records also allow result collection to resume after a restart, with published outputs accessible through Compute Preview.
🤖 Built-in Open-Science Agent
Open-Science now includes its own built-in Agent Runtime, which becomes the default for new installations.
- Provider-neutral Agent execution.
- Streaming support across major API protocols.
- Validated Tool handling and persistent execution records.
- Existing Claude Code, OpenCode, Codex, CodeBuddy, and Pi frameworks remain available.
⚡ Faster macOS Updates
macOS now supports differential application updates.
Instead of downloading the entire application, updates retrieve only changed blocks, with automatic fallback to a full download when necessary.
💬 Step-Linked Research Discussions
Imported .science packages and Replay steps now support step-linked child Conversations.
Researchers can ask questions about specific research steps or Notebook Runs while preserving the original Session identity and history.
Discussions remain available even when the parent Session is archived.
🔍 Source Link Preview
Source links now display a preview card with the destination domain and, for approved HTTPS sources, available title and description metadata.
【🔧 Improvements】
- Simplified Workspace Sidebar with Pinned, Imported Research, Active, and Recent Sessions.
- Imported research now highlights Fork to Continue as the primary next action.
- Sending a Prompt from an earlier Conversation turn preserves the reading position.
- Model Settings reorganized into Local Capabilities for PDF extraction, OCR, and research narration.
- Clearer Tool error messages with actionable recovery guidance.
- Improved Notebook responsiveness and large-source processing.
- More accurate scientific PDF text and structure extraction.
- Improved Replay navigation and research video export controls.
【🐛 Bug Fixes】
- Remote Compute & Notebook — Improved Notebook recovery, Windows R execution, Node Runtime selection, and background task handling.
- Agents & Providers — Fixed DeepSeek model routing and Codex Runtime cleanup on Windows.
- PDF & Literature — Fixed PDF translation failures so successfully translated pages remain available when individual pages encounter unsupported layouts.
- Application Updates — Improved macOS and Windows update checks, process detection, and installation recovery.
- Workspace & Interface — Fixed Windows display-scaling issues that could place input controls behind the taskbar.
- Runtime & Recovery — Improved startup diagnostics, backend restart recovery, and Windows Notebook process cleanup.
3
563
Can NVIDIA’s Lyra 2.0 generate better-looking frames while keeping a 3D scene consistent? An AIPOCH Open-Science agent audited all 35 values in the paper’s ablation table across five variants and seven metrics.
youtube.com/shorts/2NiBL2dus…
Explore the Lyra 2.0 ablation in AIPOCH Open-Science. Trace seven metric changes and the reprojection error that changes a comparison.
2
138
AIPOCH Open-Science just scored 97.30% (36/37) on CORE-Bench-Hard⁻ in a local eval with DeepSeek Flash at Max reasoning effort — beating the highest official reference scores reported so far.
GitHub: github.com/aipoch/open-scien…
AIPOCH Open-Science passed 36 of 37 tasks (97.30%) in a local evaluation on AstaBench’s CORE-Bench-Hard⁻ test split, using DeepSeek Flash (deepseek-flash) at Max reasoning effort.
Can an agent reproduce a result from a published study?
On CORE-Bench-Hard⁻, it starts with the study’s code, data, and README. It installs dependencies, runs the analysis in a container, and records the requested results in report.json.
The benchmark’s programmatic scorer checks the reported numbers, text, and lists against reference results. A task counts as correct only when every subquestion passes. The final tally includes retests and records one failure.
The highest scores in our report’s comparison:
• AIPOCH Open-Science / DeepSeek Flash (Max) — 97.30% (local)
• Ai2 ReAct / gpt-5.4-2026-03-05 — 94.59%
• Ai2 ReAct / gpt-5.5-2026-04-23 — 91.89%
• Ai2 ReAct / gemini-3.1-pro-preview and claude-opus-4-6 — 89.19% each
The local score is 2.70 percentage points above the highest official reference in the report’s snapshot, using unrounded proportions. The full chart shows all 25 official references and preserves their tied ranks. Our local result has yet to be submitted to the official leaderboard.
1
143










