{"schema_version":"onlylabs.public_signal.v1","title":"Google (DeepMind / Gemini) Repo: google-deepmind/anthro-benchmark","description":"Google (DeepMind / Gemini) repo signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2","json_url":"https://onlylabs.fyi/signals/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2/signal.json","generated_at":"2026-06-11T04:00:31.726814+00:00","org":{"slug":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/google-deepmind","dossier_json_url":"https://onlylabs.fyi/labs/google-deepmind/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2","signal_json":"https://onlylabs.fyi/signals/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2/signal.json","source":"https://github.com/google-deepmind/anthro-benchmark","lab_dossier":"https://onlylabs.fyi/labs/google-deepmind","lab_dossier_json":"https://onlylabs.fyi/labs/google-deepmind/dossier.json","analysis":"https://onlylabs.fyi/analysis/google-deepmind","analysis_json":"https://onlylabs.fyi/analysis/google-deepmind/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/google-deepmind/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":"Google (DeepMind / Gemini) published google-deepmind/anthro-benchmark (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo google-deepmind/anthro-benchmark · language Python · Low stars benchmark repo. 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/google-deepmind/anthro-benchmark","source_host":"github.com","occurred_at":"2025-05-06T16:13:15+00:00","first_seen_at":"2026-06-05T05:42:58.453363+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"Google (DeepMind / Gemini)","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"google-deepmind/anthro-benchmark","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Stars","value":"11","source":"traction"},{"label":"Notability","value":"Low stars benchmark repo","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"}],"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/google-deepmind/anthro-benchmark"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-06-11T04:00:31.726814+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":"Google (DeepMind / Gemini) has a repo signal matching evals and quality."},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2/signal.json","dossier_json":"https://onlylabs.fyi/labs/google-deepmind/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/google-deepmind/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/google-deepmind/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/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2/signal.json","required":true},{"label":"source","url":"https://github.com/google-deepmind/anthro-benchmark","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/google-deepmind/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/google-deepmind/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 Google (DeepMind / Gemini)'s repo signal \"google-deepmind/anthro-benchmark\" for frontier lab strategy and data-business implications."},"semantic_triples":[{"subject":"Google (DeepMind / Gemini)","predicate":"published repo","object":"google-deepmind/anthro-benchmark","text":"Google (DeepMind / Gemini) published repo google-deepmind/anthro-benchmark."},{"subject":"google-deepmind/anthro-benchmark","predicate":"is classified as","object":"repo signal","text":"google-deepmind/anthro-benchmark is classified as repo signal."},{"subject":"google-deepmind/anthro-benchmark","predicate":"belongs to","object":"repos desk","text":"google-deepmind/anthro-benchmark belongs to repos desk."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has context","object":"Python","text":"google-deepmind/anthro-benchmark has context Python."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has evidence coverage","object":"1 captured evidence page","text":"google-deepmind/anthro-benchmark has evidence coverage 1 captured evidence page."},{"subject":"google-deepmind/anthro-benchmark","predicate":"matches data-business lanes","object":"Evals and quality","text":"google-deepmind/anthro-benchmark matches data-business lanes Evals and quality."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has captured page count","object":"1","text":"google-deepmind/anthro-benchmark has captured page count 1."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has readable page count","object":"1","text":"google-deepmind/anthro-benchmark has readable page count 1."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has related signal count","object":"6","text":"google-deepmind/anthro-benchmark has related signal count 6."},{"subject":"google-deepmind/anthro-benchmark","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":"google-deepmind/anthro-benchmark 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":"google-deepmind/anthro-benchmark","predicate":"has source host","object":"github.com","text":"google-deepmind/anthro-benchmark has source host github.com."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has lab","object":"Google (DeepMind / Gemini)","text":"google-deepmind/anthro-benchmark has lab Google (DeepMind / Gemini)."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has signal desk","object":"repos","text":"google-deepmind/anthro-benchmark has signal desk repos."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has source host","object":"github.com","text":"google-deepmind/anthro-benchmark has source host github.com."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has repository","object":"google-deepmind/anthro-benchmark","text":"google-deepmind/anthro-benchmark has repository google-deepmind/anthro-benchmark."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has language","object":"Python","text":"google-deepmind/anthro-benchmark has language Python."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has stars","object":"11","text":"google-deepmind/anthro-benchmark has stars 11."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has notability","object":"Low stars benchmark repo","text":"google-deepmind/anthro-benchmark has notability Low stars benchmark repo."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has radar lane","object":"Evals and quality","text":"google-deepmind/anthro-benchmark has radar lane Evals and quality."}]},"intelligence":{"signal_desk":"repos","answer":"Google (DeepMind / Gemini) published google-deepmind/anthro-benchmark (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo google-deepmind/anthro-benchmark · language Python · Low stars benchmark repo. 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":"Google (DeepMind / Gemini)","predicate":"published repo","object":"google-deepmind/anthro-benchmark","text":"Google (DeepMind / Gemini) published repo google-deepmind/anthro-benchmark."},{"subject":"google-deepmind/anthro-benchmark","predicate":"is classified as","object":"repo signal","text":"google-deepmind/anthro-benchmark is classified as repo signal."},{"subject":"google-deepmind/anthro-benchmark","predicate":"belongs to","object":"repos desk","text":"google-deepmind/anthro-benchmark belongs to repos desk."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has context","object":"Python","text":"google-deepmind/anthro-benchmark has context Python."},{"subject":"google-deepmind/anthro-benchmark","predicate":"has evidence coverage","object":"1 captured evidence page","text":"google-deepmind/anthro-benchmark has evidence coverage 1 captured evidence page."},{"subject":"google-deepmind/anthro-benchmark","predicate":"matches data-business lanes","object":"Evals and quality","text":"google-deepmind/anthro-benchmark matches data-business lanes Evals and quality."}]},"signal":{"id":"2ed1ca89-2e6d-4e05-a57f-eab68c9244a2","url":"https://onlylabs.fyi/signals/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2","json_url":"https://onlylabs.fyi/signals/2ed1ca89-2e6d-4e05-a57f-eab68c9244a2/signal.json","source_url":"https://github.com/google-deepmind/anthro-benchmark","title":"google-deepmind/anthro-benchmark","summary":"Google (DeepMind / Gemini) 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":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab"},"occurred_at":"2025-05-06T16:13:15+00:00","first_seen_at":"2026-06-05T05:42:58.453363+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/google-deepmind/anthro-benchmark"]},"facets":{"repo":"google-deepmind/anthro-benchmark","language":"Python"},"traction":{"github_stars":11,"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":"Google (DeepMind / Gemini) has a repo signal matching evals and quality."}},"primary_evidence_page":{"url":"https://github.com/google-deepmind/anthro-benchmark","final_url":"https://github.com/google-deepmind/anthro-benchmark","title":"google-deepmind/anthro-benchmark repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:00:31.726814+00:00","bytes":14996,"raw_path":"f0f32cefc4a42e59bdcef454b489a7531c22e87964ec37680f934a4283286818.json","content_hash":"5172a8695cec3de589d0ad75f4a0882f3c0b42c72552c16ccd5fcdc71c802591","excerpt_chars":1200,"truncated":true,"excerpt":"google-deepmind/anthro-benchmark Language: Python License: Apache-2.0 Stars: 12 Forks: 5 Open issues: 2 Created: 2025-05-06T16:13:15Z Pushed: 2025-11-17T20:10:58Z Default branch: main Fork: no Archived: no README: AnthroBench A library for generating, rating, and analyzing dialogues to evaluate anthropomorphic behaviors in LLMs, developed in [AnthroBench: A Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models](https://arxiv.org/abs/2502.07077). Structure The library is organized into several key packages and modules: - `anthro_benchmark/generator`: Handles dialogue generation between the user LLM and target LLM. - `anthro_benchmark/classifier`: Contains logic for classifying dialogue turns based on anthropomorphic behaviors, including the `LLMClassifier` and the `cue_definitions.py` behavior definitions. - `anthro_benchmark/core`: Core utilities, including `llm_client.py` for interacting with various LLM APIs. - `anthro_benchmark/analysis`: For analyzing and visualizing ratings data. - `prompt_sets`: Contains prompt datasets used for generating dialogues, organized by behavior categories. - `anthro_eval_cli.py`: The command-line interface script. -..."},"evidence_pages":[{"url":"https://github.com/google-deepmind/anthro-benchmark","final_url":"https://github.com/google-deepmind/anthro-benchmark","title":"google-deepmind/anthro-benchmark repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-06-11T04:00:31.726814+00:00","bytes":14996,"raw_path":"f0f32cefc4a42e59bdcef454b489a7531c22e87964ec37680f934a4283286818.json","content_hash":"5172a8695cec3de589d0ad75f4a0882f3c0b42c72552c16ccd5fcdc71c802591","excerpt_chars":1200,"truncated":true,"excerpt":"google-deepmind/anthro-benchmark Language: Python License: Apache-2.0 Stars: 12 Forks: 5 Open issues: 2 Created: 2025-05-06T16:13:15Z Pushed: 2025-11-17T20:10:58Z Default branch: main Fork: no Archived: no README: AnthroBench A library for generating, rating, and analyzing dialogues to evaluate anthropomorphic behaviors in LLMs, developed in [AnthroBench: A Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models](https://arxiv.org/abs/2502.07077). Structure The library is organized into several key packages and modules: - `anthro_benchmark/generator`: Handles dialogue generation between the user LLM and target LLM. - `anthro_benchmark/classifier`: Contains logic for classifying dialogue turns based on anthropomorphic behaviors, including the `LLMClassifier` and the `cue_definitions.py` behavior definitions. - `anthro_benchmark/core`: Core utilities, including `llm_client.py` for interacting with various LLM APIs. - `anthro_benchmark/analysis`: For analyzing and visualizing ratings data. - `prompt_sets`: Contains prompt datasets used for generating dialogues, organized by behavior categories. - `anthro_eval_cli.py`: The command-line interface script. -..."}],"related_signals":[{"id":"02f8701d-7bfd-41b5-aabe-1ad72a880dfb","url":"https://onlylabs.fyi/signals/02f8701d-7bfd-41b5-aabe-1ad72a880dfb","source_url":"https://github.com/google-deepmind/unpic","title":"google-deepmind/unpic","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab"},"occurred_at":"2026-06-04T14:37:24+00:00","first_seen_at":"2026-06-05T05:42:58.453363+00:00","date_source":"source"},{"id":"35320cac-ddbe-4f25-a3b5-384a0ca0030b","url":"https://onlylabs.fyi/signals/35320cac-ddbe-4f25-a3b5-384a0ca0030b","source_url":"https://github.com/google-deepmind/seeing_without_pixels","title":"google-deepmind/seeing_without_pixels","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab"},"occurred_at":"2026-06-03T04:04:52+00:00","first_seen_at":"2026-06-05T05:42:58.453363+00:00","date_source":"source"},{"id":"62f799ef-bf1d-4aee-9f87-fa0de8bb5e81","url":"https://onlylabs.fyi/signals/62f799ef-bf1d-4aee-9f87-fa0de8bb5e81","source_url":"https://github.com/google-deepmind/nested","title":"google-deepmind/nested","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab"},"occurred_at":"2026-05-18T16:16:42+00:00","first_seen_at":"2026-06-05T05:42:58.453363+00:00","date_source":"source"},{"id":"e67b1d5f-ef62-4574-80df-a72a4bded705","url":"https://onlylabs.fyi/signals/e67b1d5f-ef62-4574-80df-a72a4bded705","source_url":"https://github.com/google-deepmind/science-skills","title":"google-deepmind/science-skills","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab"},"occurred_at":"2026-05-13T16:17:41+00:00","first_seen_at":"2026-06-05T05:42:58.453363+00:00","date_source":"source"},{"id":"7b714793-a56e-495b-8d57-85fd2850555a","url":"https://onlylabs.fyi/signals/7b714793-a56e-495b-8d57-85fd2850555a","source_url":"https://github.com/google-deepmind/alphaproof-nexus-results","title":"google-deepmind/alphaproof-nexus-results","context":"Lean","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab"},"occurred_at":"2026-05-13T09:59:21+00:00","first_seen_at":"2026-06-05T05:42:58.453363+00:00","date_source":"source"},{"id":"dab748d2-53d6-4972-a594-eb6bfbf727ea","url":"https://onlylabs.fyi/signals/dab748d2-53d6-4972-a594-eb6bfbf727ea","source_url":"https://github.com/google-deepmind/tecci","title":"google-deepmind/tecci","context":"JavaScript","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"google-deepmind","name":"Google (DeepMind / Gemini)","category":"frontier-lab"},"occurred_at":"2026-05-05T12:22:40+00:00","first_seen_at":"2026-06-05T05:42:58.453363+00:00","date_source":"source"}]}