{"schema_version":"onlylabs.public_signal.v1","title":"Microsoft Repo: microsoft/AsgardBench","description":"Microsoft repo signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c","json_url":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c/signal.json","generated_at":"2026-06-11T02:53:14.987999+00:00","org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/microsoft","dossier_json_url":"https://onlylabs.fyi/labs/microsoft/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c","signal_json":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c/signal.json","source":"https://github.com/microsoft/AsgardBench","lab_dossier":"https://onlylabs.fyi/labs/microsoft","lab_dossier_json":"https://onlylabs.fyi/labs/microsoft/dossier.json","analysis":"https://onlylabs.fyi/analysis/microsoft","analysis_json":"https://onlylabs.fyi/analysis/microsoft/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/microsoft/evidence.json","category":"https://onlylabs.fyi/frontier","category_json":"https://onlylabs.fyi/frontier.json","category_feed":"https://onlylabs.fyi/frontier/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json","topic":null,"topic_signals_json":null,"topic_feed":null,"data_business":{"radar":"https://onlylabs.fyi/data-radar","radar_json":"https://onlylabs.fyi/data-radar.json","opportunities":"https://onlylabs.fyi/opportunities","opportunities_json":"https://onlylabs.fyi/opportunities.json","lanes":[{"key":"evals","label":"Evals and quality","url":"https://onlylabs.fyi/data-radar/evals","json_url":"https://onlylabs.fyi/data-radar/evals/signals.json"}]}},"answer_pack":{"answer":"Microsoft published microsoft/AsgardBench (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo microsoft/AsgardBench · language Python · New repo with few stars. onlylabs links this event to 1 captured evidence page and 6 related repo signals. It also maps to Evals and quality in the data-business radar.","signal_desk":"repos","source_context":{"source_url":"https://github.com/microsoft/AsgardBench","source_host":"github.com","occurred_at":"2026-01-28T22:22:31+00:00","first_seen_at":"2026-06-06T01:49:41.740219+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"Microsoft","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"microsoft/AsgardBench","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"5","source":"traction"},{"label":"Notability","value":"New repo with few stars","source":"signal"},{"label":"Radar lane","value":"Evals and quality","source":"radar"},{"label":"Matched term","value":"benchmark","source":"radar"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Data pipeline","source":"evidence"},{"label":"Watch term","value":"Agents and tool use","source":"evidence"}],"evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/microsoft/AsgardBench"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T02:53:14.987999+00:00"},"data_business":{"matches":true,"lanes":[{"key":"evals","label":"Evals and quality","url":"https://onlylabs.fyi/data-radar/evals","json_url":"https://onlylabs.fyi/data-radar/evals/signals.json"}],"matched_terms":["benchmark"],"score":14,"reason":"Microsoft has a repo signal matching evals and quality."},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c/signal.json","dossier_json":"https://onlylabs.fyi/labs/microsoft/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/microsoft/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/microsoft/evidence.json","topic_signals_json":null,"topic_feed":null,"category_signals_json":"https://onlylabs.fyi/signals.json","data_radar_json":"https://onlylabs.fyi/data-radar.json","opportunities_json":"https://onlylabs.fyi/opportunities.json"},"analysis_playbook":{"objective":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","evidence_focus":["repo name","owner","description","language","stars","source URL","first seen time","data, eval, infra, safety, and product terms"],"extraction_questions":["What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Is the repo new evidence for a lab direction that is not yet in writing or releases?","Which related signals should an analyst inspect next?"],"signal_questions":["What does this new repository reveal before a formal announcement exists?","What technical area does this repository expose?","Does the repo imply eval, data, infrastructure, agent, or deployment work?","Which data-business lane explains this signal: Evals and quality?","Do the 6 related repo signals show a repeated pattern?"],"output_fields":["org","repo","technical_theme","data_business_lane","evidence_url"],"data_business_relevance":"New repositories can expose organization build priorities early, especially around internal tooling, eval infrastructure, data systems, deployment, and agent workflows.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c/signal.json","required":true},{"label":"source","url":"https://github.com/microsoft/AsgardBench","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/microsoft/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/microsoft/evidence.json","required":true},{"label":"topic_signals_json","url":null,"required":false},{"label":"data_radar_json","url":"https://onlylabs.fyi/data-radar.json","required":true}],"expected_output":["one-paragraph source-grounded interpretation","data-business implication","confidence and missing evidence","recommended next source to inspect"],"prompt_seed":"Using only the linked onlylabs JSON, captured source context, and cited evidence, analyze Microsoft's repo signal \"microsoft/AsgardBench\" for frontier lab strategy and data-business implications."},"semantic_triples":[{"subject":"Microsoft","predicate":"published repo","object":"microsoft/AsgardBench","text":"Microsoft published repo microsoft/AsgardBench."},{"subject":"microsoft/AsgardBench","predicate":"is classified as","object":"repo signal","text":"microsoft/AsgardBench is classified as repo signal."},{"subject":"microsoft/AsgardBench","predicate":"belongs to","object":"repos desk","text":"microsoft/AsgardBench belongs to repos desk."},{"subject":"microsoft/AsgardBench","predicate":"has context","object":"Python","text":"microsoft/AsgardBench has context Python."},{"subject":"microsoft/AsgardBench","predicate":"has evidence coverage","object":"1 captured evidence page","text":"microsoft/AsgardBench has evidence coverage 1 captured evidence page."},{"subject":"microsoft/AsgardBench","predicate":"matches data-business lanes","object":"Evals and quality","text":"microsoft/AsgardBench matches data-business lanes Evals and quality."},{"subject":"microsoft/AsgardBench","predicate":"has captured page count","object":"1","text":"microsoft/AsgardBench has captured page count 1."},{"subject":"microsoft/AsgardBench","predicate":"has readable page count","object":"1","text":"microsoft/AsgardBench has readable page count 1."},{"subject":"microsoft/AsgardBench","predicate":"has related signal count","object":"6","text":"microsoft/AsgardBench has related signal count 6."},{"subject":"microsoft/AsgardBench","predicate":"has analysis playbook objective","object":"Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.","text":"microsoft/AsgardBench has analysis playbook objective Turn new repository signals into early evidence of tooling, eval, infrastructure, model-adjacent, or product work before it appears in polished launch channels.."},{"subject":"microsoft/AsgardBench","predicate":"has source host","object":"github.com","text":"microsoft/AsgardBench has source host github.com."},{"subject":"microsoft/AsgardBench","predicate":"has lab","object":"Microsoft","text":"microsoft/AsgardBench has lab Microsoft."},{"subject":"microsoft/AsgardBench","predicate":"has signal desk","object":"repos","text":"microsoft/AsgardBench has signal desk repos."},{"subject":"microsoft/AsgardBench","predicate":"has source host","object":"github.com","text":"microsoft/AsgardBench has source host github.com."},{"subject":"microsoft/AsgardBench","predicate":"has repository","object":"microsoft/AsgardBench","text":"microsoft/AsgardBench has repository microsoft/AsgardBench."},{"subject":"microsoft/AsgardBench","predicate":"has language","object":"Python","text":"microsoft/AsgardBench has language Python."},{"subject":"microsoft/AsgardBench","predicate":"has stars","object":"5","text":"microsoft/AsgardBench has stars 5."},{"subject":"microsoft/AsgardBench","predicate":"has notability","object":"New repo with few stars","text":"microsoft/AsgardBench has notability New repo with few stars."},{"subject":"microsoft/AsgardBench","predicate":"has radar lane","object":"Evals and quality","text":"microsoft/AsgardBench has radar lane Evals and quality."}]},"intelligence":{"signal_desk":"repos","answer":"Microsoft published microsoft/AsgardBench (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo microsoft/AsgardBench · language Python · New repo with few stars. onlylabs links this event to 1 captured evidence page and 6 related repo signals. It also maps to Evals and quality in the data-business radar.","semantic_triples":[{"subject":"Microsoft","predicate":"published repo","object":"microsoft/AsgardBench","text":"Microsoft published repo microsoft/AsgardBench."},{"subject":"microsoft/AsgardBench","predicate":"is classified as","object":"repo signal","text":"microsoft/AsgardBench is classified as repo signal."},{"subject":"microsoft/AsgardBench","predicate":"belongs to","object":"repos desk","text":"microsoft/AsgardBench belongs to repos desk."},{"subject":"microsoft/AsgardBench","predicate":"has context","object":"Python","text":"microsoft/AsgardBench has context Python."},{"subject":"microsoft/AsgardBench","predicate":"has evidence coverage","object":"1 captured evidence page","text":"microsoft/AsgardBench has evidence coverage 1 captured evidence page."},{"subject":"microsoft/AsgardBench","predicate":"matches data-business lanes","object":"Evals and quality","text":"microsoft/AsgardBench matches data-business lanes Evals and quality."}]},"signal":{"id":"c371c894-4313-48e3-b693-9bd90c16560c","url":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c","json_url":"https://onlylabs.fyi/signals/c371c894-4313-48e3-b693-9bd90c16560c/signal.json","source_url":"https://github.com/microsoft/AsgardBench","title":"microsoft/AsgardBench","summary":"Microsoft published a new repository. onlylabs watches repos for tooling, eval, infra, and model-adjacent work.","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab"},"occurred_at":"2026-01-28T22:22:31+00:00","first_seen_at":"2026-06-06T01:49:41.740219+00:00","date_source":"source","evidence_coverage":{"target_pages":1,"captured_pages":1,"readable_pages":1,"capture_methods":["plain"],"missing_page_urls":[],"failed_page_urls":[],"blocked_page_urls":[],"page_urls":["https://github.com/microsoft/AsgardBench"]},"facets":{"repo":"microsoft/AsgardBench","language":"Python"},"traction":{"github_stars":5,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":{"lanes":[{"key":"evals","label":"Evals and quality","url":"https://onlylabs.fyi/data-radar/evals"}],"score":14,"matched_terms":["benchmark"],"reason":"Microsoft has a repo signal matching evals and quality."}},"primary_evidence_page":{"url":"https://github.com/microsoft/AsgardBench","final_url":"https://github.com/microsoft/AsgardBench","title":"microsoft/AsgardBench repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T02:53:14.987999+00:00","bytes":15893,"raw_path":"a537d9f2c58e509a6561352760055feefac61bfc8f373addda9ea4c5551f1ca7.json","content_hash":"d0b1d83f9a6fb63a8af69e9b6f52143d6fb64395d03500e3c1519a60aca65d34","excerpt_chars":1200,"truncated":true,"excerpt":"microsoft/AsgardBench Description: Visually grounded planning benchmark for multimodal agents Language: Python License: MIT Stars: 5 Forks: 0 Open issues: 9 Created: 2026-01-28T22:22:31Z Pushed: 2026-06-11T01:26:20Z Default branch: main Fork: no Archived: no README: AsgardBench A benchmark for evaluating Vision-Language Models (VLMs) on embodied household tasks. 📄 **Paper:** [AsgardBench - Evaluating Visually Grounded Interactive Planning Under Minimal Feedback](https://arxiv.org/abs/2603.15888) Overview AsgardBench evaluates how well VLMs can act as embodied agents completing multi-step household tasks. Given a task description (e.g., \"Make coffee\") and egocentric visual observations, the model must output actions to accomplish the goal. **Key features:** - 🏠 108 task instances across 12 task types and 3 scene types in AI2-THOR - 👁️ Egocentric visual observations - 🎯 Automatic success evaluation via goal checking - 🔧 Works with any OpenAI-compatible API endpoint For detailed methodology, ablation studies, and results, please see our paper. Quick Start Prerequisites - [uv](https://docs.astral.sh/uv/) - An OpenAI-compatible API endpoint (OpenAI, Azure OpenAI, OpenRouter, vLLM,..."},"evidence_pages":[{"url":"https://github.com/microsoft/AsgardBench","final_url":"https://github.com/microsoft/AsgardBench","title":"microsoft/AsgardBench repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T02:53:14.987999+00:00","bytes":15893,"raw_path":"a537d9f2c58e509a6561352760055feefac61bfc8f373addda9ea4c5551f1ca7.json","content_hash":"d0b1d83f9a6fb63a8af69e9b6f52143d6fb64395d03500e3c1519a60aca65d34","excerpt_chars":1200,"truncated":true,"excerpt":"microsoft/AsgardBench Description: Visually grounded planning benchmark for multimodal agents Language: Python License: MIT Stars: 5 Forks: 0 Open issues: 9 Created: 2026-01-28T22:22:31Z Pushed: 2026-06-11T01:26:20Z Default branch: main Fork: no Archived: no README: AsgardBench A benchmark for evaluating Vision-Language Models (VLMs) on embodied household tasks. 📄 **Paper:** [AsgardBench - Evaluating Visually Grounded Interactive Planning Under Minimal Feedback](https://arxiv.org/abs/2603.15888) Overview AsgardBench evaluates how well VLMs can act as embodied agents completing multi-step household tasks. Given a task description (e.g., \"Make coffee\") and egocentric visual observations, the model must output actions to accomplish the goal. **Key features:** - 🏠 108 task instances across 12 task types and 3 scene types in AI2-THOR - 👁️ Egocentric visual observations - 🎯 Automatic success evaluation via goal checking - 🔧 Works with any OpenAI-compatible API endpoint For detailed methodology, ablation studies, and results, please see our paper. Quick Start Prerequisites - [uv](https://docs.astral.sh/uv/) - An OpenAI-compatible API endpoint (OpenAI, Azure OpenAI, OpenRouter, vLLM,..."}],"related_signals":[{"id":"8afe79f4-378b-4748-9e2a-3cf5e3253fdb","url":"https://onlylabs.fyi/signals/8afe79f4-378b-4748-9e2a-3cf5e3253fdb","source_url":"https://github.com/microsoft/Dev-Trio","title":"microsoft/Dev-Trio","context":null,"kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab"},"occurred_at":"2026-06-08T03:41:01+00:00","first_seen_at":"2026-06-08T07:01:04.198092+00:00","date_source":"source"},{"id":"9e75fa50-dba7-4b77-9faf-166c323e3dff","url":"https://onlylabs.fyi/signals/9e75fa50-dba7-4b77-9faf-166c323e3dff","source_url":"https://github.com/microsoft/amplifier-app-paperclip","title":"microsoft/amplifier-app-paperclip","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab"},"occurred_at":"2026-06-04T21:13:41+00:00","first_seen_at":"2026-06-05T20:58:41.438741+00:00","date_source":"source"},{"id":"76cacf33-54b2-4074-bec0-23944d8fb67c","url":"https://onlylabs.fyi/signals/76cacf33-54b2-4074-bec0-23944d8fb67c","source_url":"https://github.com/microsoft/create-github-app-token-via-key-vault","title":"microsoft/create-github-app-token-via-key-vault","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab"},"occurred_at":"2026-06-04T18:22:49+00:00","first_seen_at":"2026-06-05T20:58:41.438741+00:00","date_source":"source"},{"id":"b2f7bcbd-9db3-4785-8a2a-2e0e0cb22ed2","url":"https://onlylabs.fyi/signals/b2f7bcbd-9db3-4785-8a2a-2e0e0cb22ed2","source_url":"https://github.com/microsoft/Enterprise-AI-Analytics-Pipeline","title":"microsoft/Enterprise-AI-Analytics-Pipeline","context":null,"kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab"},"occurred_at":"2026-06-04T16:48:58+00:00","first_seen_at":"2026-06-05T20:58:41.438741+00:00","date_source":"source"},{"id":"51a9ec5d-5f14-45d9-b57a-db362b5d1ace","url":"https://onlylabs.fyi/signals/51a9ec5d-5f14-45d9-b57a-db362b5d1ace","source_url":"https://github.com/microsoft/fabric-org-app-template","title":"microsoft/fabric-org-app-template","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab"},"occurred_at":"2026-06-03T18:26:42+00:00","first_seen_at":"2026-06-05T20:58:41.438741+00:00","date_source":"source"},{"id":"f26025da-153f-4d27-851c-7b4892602810","url":"https://onlylabs.fyi/signals/f26025da-153f-4d27-851c-7b4892602810","source_url":"https://github.com/microsoft/amplifier-bundle-amplifier-online","title":"microsoft/amplifier-bundle-amplifier-online","context":null,"kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"microsoft","name":"Microsoft","category":"frontier-lab"},"occurred_at":"2026-06-03T17:26:20+00:00","first_seen_at":"2026-06-05T20:58:41.438741+00:00","date_source":"source"}]}