Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

World & Business

Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

AIPOCH Open-Science packages AI-assisted research in inspectable .science files · Digg

Announcement

AIPOCH Open-Science packages AI-assisted research in inspectable.science files

AIPOCH says exports can include conversation branches, selected files and recorded evidence; imported histories remain read-only.

3 Sources, 1h ago, first seen 1h ago

TLDR

A post describes Open-Science as a desktop app whose AI agent reads papers, retrieves research data and runs Python or R code. AIPOCH says its.science packages save selected files, conversation context and recorded evidence for collaborators to inspect. Contents depend on the session and export choices. Imported histories stay read-only but can be forked, and importing a package does not itself verify or reproduce results, AIPOCH cautions.

Combined views

—

3 Sources, first seen 1h ago

Combined views

—

3 Sources, first seen 1h ago

— likes

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet

— likes

— comments

— saves

— reposts

— comments

— saves

— reposts

3 Sources

@rohanpaul_aiAn Apache-2.0 app with 4.8K GitHub stars is trying to make AI-assisted science as traceable as checksummed, versioned code. @aipoch_ai’s Open-Science is a free, open-source desktop app where an AI agent reads papers, pulls data from science databases, writes and runs Python or R code, and saves the charts and reports, all in a single workspace on your computer. Research is usually split across PDFs, spreadsheets, code editors and terminals, so results lose their link to the data and code behind them. Open-Science keeps that link: every result records its input data, code, software setup and run history, and the whole session exports as a single .science file that holds the conversation, the chosen files and the evidence, minus your API keys. A public example shows it in action: in “AI Math Citations: Do They Check Out”, the session took 5 references from each of 20 AI-written math papers and checked whether each points to a real publication. A direct check against publication records matched 80 of the 100 and found none to be fake, and after notes the researcher added, the final count was 88 matches, 7 small slips like an online date versus a print year, and 5 unresolved. Because the .science record keeps those 2 evidence sources apart, anyone opening it can see which verdicts rest on human notes, including all 6 positive verdicts in a smaller test of whether cited papers really back 10 specific claims. It is model-agnostic, so it works with whichever AI model you choose (cloud providers, custom gateways, or a Claude or Codex subscription), and local-first, so projects stay on your machine by default. The agent runs code only after you approve it, and it ships with science skills like AlphaFold2 (predicts a protein’s 3D shape) that you can extend with your own. It is Apache 2.0 licensed and runs on macOS, Windows and Linux. 🧵1/n1h

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

3 Sources

@rohanpaul_aiAn Apache-2.0 app with 4.8K GitHub stars is trying to make AI-assisted science as traceable as checksummed, versioned code. @aipoch_ai’s Open-Science is a free, open-source desktop app where an AI agent reads papers, pulls data from science databases, writes and runs Python or R code, and saves the charts and reports, all in a single workspace on your computer. Research is usually split across PDFs, spreadsheets, code editors and terminals, so results lose their link to the data and code behind them. Open-Science keeps that link: every result records its input data, code, software setup and run history, and the whole session exports as a single .science file that holds the conversation, the chosen files and the evidence, minus your API keys. A public example shows it in action: in “AI Math Citations: Do They Check Out”, the session took 5 references from each of 20 AI-written math papers and checked whether each points to a real publication. A direct check against publication records matched 80 of the 100 and found none to be fake, and after notes the researcher added, the final count was 88 matches, 7 small slips like an online date versus a print year, and 5 unresolved. Because the .science record keeps those 2 evidence sources apart, anyone opening it can see which verdicts rest on human notes, including all 6 positive verdicts in a smaller test of whether cited papers really back 10 specific claims. It is model-agnostic, so it works with whichever AI model you choose (cloud providers, custom gateways, or a Claude or Codex subscription), and local-first, so projects stay on your machine by default. The agent runs code only after you approve it, and it ships with science skills like AlphaFold2 (predicts a protein’s 3D shape) that you can extend with your own. It is Apache 2.0 licensed and runs on macOS, Windows and Linux. 🧵1/n1h