{"schema_version":"onlylabs.public_signal.v1","title":"AI21 Labs Repo: AI21Labs/lm-evaluation","description":"AI21 Labs repo signal with public source context, captured evidence pages, related signals, and category-scoped analysis context.","url":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a","json_url":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a/signal.json","generated_at":"2026-06-11T04:20:01.984942+00:00","org":{"slug":"ai21","name":"AI21 Labs","category":"neolab","category_label":"Neolab","dossier_url":"https://onlylabs.fyi/labs/ai21","dossier_json_url":"https://onlylabs.fyi/labs/ai21/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a","signal_json":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a/signal.json","source":"https://github.com/AI21Labs/lm-evaluation","lab_dossier":"https://onlylabs.fyi/labs/ai21","lab_dossier_json":"https://onlylabs.fyi/labs/ai21/dossier.json","analysis":"https://onlylabs.fyi/analysis/ai21","analysis_json":"https://onlylabs.fyi/analysis/ai21/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/ai21/evidence.json","category":"https://onlylabs.fyi/neolabs","category_json":"https://onlylabs.fyi/neolabs.json","category_feed":"https://onlylabs.fyi/neolabs/feed.xml","category_signals_json":"https://onlylabs.fyi/signals.json?category=neolab","topic":null,"topic_signals_json":null,"topic_feed":null,"data_business":null},"answer_pack":{"answer":"AI21 Labs published AI21Labs/lm-evaluation (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo AI21Labs/lm-evaluation · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","signal_desk":"repos","source_context":{"source_url":"https://github.com/AI21Labs/lm-evaluation","source_host":"github.com","occurred_at":"2021-08-05T13:22:20+00:00","first_seen_at":"2026-06-05T20:58:44.654825+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"AI21 Labs","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"AI21Labs/lm-evaluation","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"130","source":"traction"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Data pipeline","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/AI21Labs/lm-evaluation"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T04:20:01.984942+00:00"},"data_business":{"matches":false,"lanes":[],"matched_terms":[],"score":null,"reason":null},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a/signal.json","dossier_json":"https://onlylabs.fyi/labs/ai21/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/ai21/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/ai21/evidence.json","topic_signals_json":null,"topic_feed":null,"category_signals_json":"https://onlylabs.fyi/signals.json?category=neolab","data_radar_json":null,"opportunities_json":null},"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?","Do the 6 related repo signals show a repeated pattern?"],"output_fields":["org","repo","technical_theme","evidence_url"],"data_business_relevance":"Data-business lane extraction is scoped to frontier labs; for this category, interpret the repository as source-grounded category strategy evidence.","required_sources":[{"label":"signal_json","url":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a/signal.json","required":true},{"label":"source","url":"https://github.com/AI21Labs/lm-evaluation","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/ai21/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/ai21/evidence.json","required":true},{"label":"topic_signals_json","url":null,"required":false},{"label":"data_radar_json","url":null,"required":false}],"expected_output":["one-paragraph source-grounded interpretation","category-specific 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 AI21 Labs's repo signal \"AI21Labs/lm-evaluation\" for neolab strategy."},"semantic_triples":[{"subject":"AI21 Labs","predicate":"published repo","object":"AI21Labs/lm-evaluation","text":"AI21 Labs published repo AI21Labs/lm-evaluation."},{"subject":"AI21Labs/lm-evaluation","predicate":"is classified as","object":"repo signal","text":"AI21Labs/lm-evaluation is classified as repo signal."},{"subject":"AI21Labs/lm-evaluation","predicate":"belongs to","object":"repos desk","text":"AI21Labs/lm-evaluation belongs to repos desk."},{"subject":"AI21Labs/lm-evaluation","predicate":"has context","object":"Python","text":"AI21Labs/lm-evaluation has context Python."},{"subject":"AI21Labs/lm-evaluation","predicate":"has evidence coverage","object":"1 captured evidence page","text":"AI21Labs/lm-evaluation has evidence coverage 1 captured evidence page."},{"subject":"AI21Labs/lm-evaluation","predicate":"has captured page count","object":"1","text":"AI21Labs/lm-evaluation has captured page count 1."},{"subject":"AI21Labs/lm-evaluation","predicate":"has readable page count","object":"1","text":"AI21Labs/lm-evaluation has readable page count 1."},{"subject":"AI21Labs/lm-evaluation","predicate":"has related signal count","object":"6","text":"AI21Labs/lm-evaluation has related signal count 6."},{"subject":"AI21Labs/lm-evaluation","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":"AI21Labs/lm-evaluation 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":"AI21Labs/lm-evaluation","predicate":"has source host","object":"github.com","text":"AI21Labs/lm-evaluation has source host github.com."},{"subject":"AI21Labs/lm-evaluation","predicate":"has lab","object":"AI21 Labs","text":"AI21Labs/lm-evaluation has lab AI21 Labs."},{"subject":"AI21Labs/lm-evaluation","predicate":"has signal desk","object":"repos","text":"AI21Labs/lm-evaluation has signal desk repos."},{"subject":"AI21Labs/lm-evaluation","predicate":"has source host","object":"github.com","text":"AI21Labs/lm-evaluation has source host github.com."},{"subject":"AI21Labs/lm-evaluation","predicate":"has repository","object":"AI21Labs/lm-evaluation","text":"AI21Labs/lm-evaluation has repository AI21Labs/lm-evaluation."},{"subject":"AI21Labs/lm-evaluation","predicate":"has language","object":"Python","text":"AI21Labs/lm-evaluation has language Python."},{"subject":"AI21Labs/lm-evaluation","predicate":"has stars","object":"130","text":"AI21Labs/lm-evaluation has stars 130."},{"subject":"AI21Labs/lm-evaluation","predicate":"has watch term","object":"Eval methodology","text":"AI21Labs/lm-evaluation has watch term Eval methodology."},{"subject":"AI21Labs/lm-evaluation","predicate":"has watch term","object":"Data pipeline","text":"AI21Labs/lm-evaluation has watch term Data pipeline."}]},"intelligence":{"signal_desk":"repos","answer":"AI21 Labs published AI21Labs/lm-evaluation (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo AI21Labs/lm-evaluation · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals.","semantic_triples":[{"subject":"AI21 Labs","predicate":"published repo","object":"AI21Labs/lm-evaluation","text":"AI21 Labs published repo AI21Labs/lm-evaluation."},{"subject":"AI21Labs/lm-evaluation","predicate":"is classified as","object":"repo signal","text":"AI21Labs/lm-evaluation is classified as repo signal."},{"subject":"AI21Labs/lm-evaluation","predicate":"belongs to","object":"repos desk","text":"AI21Labs/lm-evaluation belongs to repos desk."},{"subject":"AI21Labs/lm-evaluation","predicate":"has context","object":"Python","text":"AI21Labs/lm-evaluation has context Python."},{"subject":"AI21Labs/lm-evaluation","predicate":"has evidence coverage","object":"1 captured evidence page","text":"AI21Labs/lm-evaluation has evidence coverage 1 captured evidence page."}]},"signal":{"id":"69e15875-922b-4d38-a2be-4015751f183a","url":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a","json_url":"https://onlylabs.fyi/signals/69e15875-922b-4d38-a2be-4015751f183a/signal.json","source_url":"https://github.com/AI21Labs/lm-evaluation","title":"AI21Labs/lm-evaluation","summary":"AI21 Labs 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":"ai21","name":"AI21 Labs","category":"neolab"},"occurred_at":"2021-08-05T13:22:20+00:00","first_seen_at":"2026-06-05T20:58:44.654825+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/AI21Labs/lm-evaluation"]},"facets":{"repo":"AI21Labs/lm-evaluation","language":"Python"},"traction":{"github_stars":130,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":null},"primary_evidence_page":{"url":"https://github.com/AI21Labs/lm-evaluation","final_url":"https://github.com/AI21Labs/lm-evaluation","title":"AI21Labs/lm-evaluation repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:20:01.984942+00:00","bytes":11257,"raw_path":"28bc2bc5b52dc33bca127cc7ccee0e7fd153d8a6476bf5e1783cd0a999acaa82.json","content_hash":"c35ddb729222f96c52fd1d5f7f779d4ccd88462653f0516a57b5b72519596301","excerpt_chars":1200,"truncated":true,"excerpt":"AI21Labs/lm-evaluation Description: Evaluation suite for large-scale language models. Language: Python License: Apache-2.0 Stars: 130 Forks: 15 Open issues: 2 Created: 2021-08-05T13:22:20Z Pushed: 2021-08-15T13:49:52Z Default branch: main Fork: no Archived: yes README: LM Evaluation Test Suite This repo contains code for running the evaluations and reproducing the results from the [Jurassic-1 Technical Paper](https://uploads-ssl.webflow.com/60fd4503684b466578c0d307/61138924626a6981ee09caf6_jurassic_tech_paper.pdf) (see [blog post](https://www.ai21.com/blog/announcing-ai21-studio-and-jurassic-1)), with current support for running the tasks through both the [AI21 Studio API](https://studio.ai21.com/) and [OpenAI's GPT3 API](https://beta.openai.com/). Citation Please use the following bibtex entry: ``` @techreport{J1WhitePaper, author = {Lieber, Opher and Sharir, Or and Lenz, Barak and Shoham, Yoav}, title = {Jurassic-1: Technical Details And Evaluation}, institution = {AI21 Labs}, year = 2021, month = aug, } ``` Installation ``` git clone https://github.com/AI21Labs/lm-evaluation.git cd lm-evaluation pip install -e . ``` Usage The entry point for running the evaluations is..."},"evidence_pages":[{"url":"https://github.com/AI21Labs/lm-evaluation","final_url":"https://github.com/AI21Labs/lm-evaluation","title":"AI21Labs/lm-evaluation repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:20:01.984942+00:00","bytes":11257,"raw_path":"28bc2bc5b52dc33bca127cc7ccee0e7fd153d8a6476bf5e1783cd0a999acaa82.json","content_hash":"c35ddb729222f96c52fd1d5f7f779d4ccd88462653f0516a57b5b72519596301","excerpt_chars":1200,"truncated":true,"excerpt":"AI21Labs/lm-evaluation Description: Evaluation suite for large-scale language models. Language: Python License: Apache-2.0 Stars: 130 Forks: 15 Open issues: 2 Created: 2021-08-05T13:22:20Z Pushed: 2021-08-15T13:49:52Z Default branch: main Fork: no Archived: yes README: LM Evaluation Test Suite This repo contains code for running the evaluations and reproducing the results from the [Jurassic-1 Technical Paper](https://uploads-ssl.webflow.com/60fd4503684b466578c0d307/61138924626a6981ee09caf6_jurassic_tech_paper.pdf) (see [blog post](https://www.ai21.com/blog/announcing-ai21-studio-and-jurassic-1)), with current support for running the tasks through both the [AI21 Studio API](https://studio.ai21.com/) and [OpenAI's GPT3 API](https://beta.openai.com/). Citation Please use the following bibtex entry: ``` @techreport{J1WhitePaper, author = {Lieber, Opher and Sharir, Or and Lenz, Barak and Shoham, Yoav}, title = {Jurassic-1: Technical Details And Evaluation}, institution = {AI21 Labs}, year = 2021, month = aug, } ``` Installation ``` git clone https://github.com/AI21Labs/lm-evaluation.git cd lm-evaluation pip install -e . ``` Usage The entry point for running the evaluations is..."}],"related_signals":[{"id":"a8d5a050-6c2c-48fc-8704-64a597e69658","url":"https://onlylabs.fyi/signals/a8d5a050-6c2c-48fc-8704-64a597e69658","source_url":"https://github.com/AI21Labs/pre-commit-hadolint","title":"AI21Labs/pre-commit-hadolint","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"ai21","name":"AI21 Labs","category":"neolab"},"occurred_at":"2026-05-12T08:34:02+00:00","first_seen_at":"2026-06-05T20:58:44.654825+00:00","date_source":"source"},{"id":"7beb24f5-17a5-4573-92ef-792037a0120f","url":"https://onlylabs.fyi/signals/7beb24f5-17a5-4573-92ef-792037a0120f","source_url":"https://github.com/AI21Labs/multi-window-chunk-size","title":"AI21Labs/multi-window-chunk-size","context":"Jupyter Notebook","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"ai21","name":"AI21 Labs","category":"neolab"},"occurred_at":"2026-01-26T12:02:59+00:00","first_seen_at":"2026-06-05T20:58:44.654825+00:00","date_source":"source"},{"id":"ac9e3f80-ea99-4dba-8929-da82435a3a34","url":"https://onlylabs.fyi/signals/ac9e3f80-ea99-4dba-8929-da82435a3a34","source_url":"https://github.com/AI21Labs/ai21-typescript","title":"AI21Labs/ai21-typescript","context":"TypeScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"ai21","name":"AI21 Labs","category":"neolab"},"occurred_at":"2024-11-05T09:44:25+00:00","first_seen_at":"2026-06-05T20:58:44.654825+00:00","date_source":"source"},{"id":"653c8c77-1a4f-4e50-8504-f5f596fb5be3","url":"https://onlylabs.fyi/signals/653c8c77-1a4f-4e50-8504-f5f596fb5be3","source_url":"https://github.com/AI21Labs/salt","title":"AI21Labs/salt","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"ai21","name":"AI21 Labs","category":"neolab"},"occurred_at":"2024-07-21T09:13:44+00:00","first_seen_at":"2026-06-05T20:58:44.654825+00:00","date_source":"source"},{"id":"d4083267-defa-4b38-8f7f-90ee756c2801","url":"https://onlylabs.fyi/signals/d4083267-defa-4b38-8f7f-90ee756c2801","source_url":"https://github.com/AI21Labs/AI21-Industry-Samples","title":"AI21Labs/AI21-Industry-Samples","context":"Jupyter Notebook","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"ai21","name":"AI21 Labs","category":"neolab"},"occurred_at":"2024-02-02T14:30:39+00:00","first_seen_at":"2026-06-05T20:58:44.654825+00:00","date_source":"source"},{"id":"3ceb6253-41fc-44c7-a33e-62f570e3922b","url":"https://onlylabs.fyi/signals/3ceb6253-41fc-44c7-a33e-62f570e3922b","source_url":"https://github.com/AI21Labs/ai21-python","title":"AI21Labs/ai21-python","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"ai21","name":"AI21 Labs","category":"neolab"},"occurred_at":"2023-12-10T09:20:15+00:00","first_seen_at":"2026-06-05T20:58:44.654825+00:00","date_source":"source"}]}