{"schema_version":"onlylabs.public_signal.v1","title":"Amazon (Nova) Repo: amazon-science/data-driven-personas","description":"Amazon (Nova) repo signal with public source context, captured evidence pages, related signals, and data-business radar classification.","url":"https://onlylabs.fyi/signals/81e2f348-2b12-4eb1-9302-31bee0875cb1","json_url":"https://onlylabs.fyi/signals/81e2f348-2b12-4eb1-9302-31bee0875cb1/signal.json","generated_at":"2026-10-24T20:20:37.821Z","evidence_latest_fetched_at":"2026-10-24T07:04:11.169545+00:00","signal_first_seen_at":"2026-10-24T07:00:37.03211+00:00","org":{"slug":"amazon","name":"Amazon (Nova)","category":"frontier-lab","category_label":"Frontier lab","dossier_url":"https://onlylabs.fyi/labs/amazon","dossier_json_url":"https://onlylabs.fyi/labs/amazon/dossier.json"},"related_urls":{"signal":"https://onlylabs.fyi/signals/81e2f348-2b12-4eb1-9302-31bee0875cb1","signal_json":"https://onlylabs.fyi/signals/81e2f348-2b12-4eb1-9302-31bee0875cb1/signal.json","source":"https://github.com/amazon-science/data-driven-personas","lab_dossier":"https://onlylabs.fyi/labs/amazon","lab_dossier_json":"https://onlylabs.fyi/labs/amazon/dossier.json","analysis":"https://onlylabs.fyi/analysis/amazon","analysis_json":"https://onlylabs.fyi/analysis/amazon/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/amazon/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":"data","label":"Data demand","url":"https://onlylabs.fyi/data-radar/data","json_url":"https://onlylabs.fyi/data-radar/data/signals.json"}]}},"answer_pack":{"answer":"Amazon (Nova) published amazon-science/data-driven-personas (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo amazon-science/data-driven-personas · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals. It also maps to Data demand in the data-business radar.","signal_desk":"repos","source_context":{"source_url":"https://github.com/amazon-science/data-driven-personas","source_host":"github.com","occurred_at":"2026-10-20T14:58:20+00:00","first_seen_at":"2026-10-24T07:00:37.03211+00:00","date_source":"source","context":"Python"},"context_markers":[{"label":"Lab","value":"Amazon (Nova)","source":"signal"},{"label":"Signal desk","value":"repos","source":"signal"},{"label":"Source host","value":"github.com","source":"source"},{"label":"Repository","value":"amazon-science/data-driven-personas","source":"source"},{"label":"Language","value":"Python","source":"source"},{"label":"Radar lane","value":"Data demand","source":"radar"},{"label":"Matched term","value":"data","source":"radar"},{"label":"Watch term","value":"RL environments","source":"evidence"},{"label":"Watch term","value":"Eval methodology","source":"evidence"},{"label":"Watch term","value":"Data pipeline","source":"evidence"},{"label":"Watch term","value":"Infrastructure","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/amazon-science/data-driven-personas"],"related_signals":6,"has_source_url":true,"latest_page_fetched_at":"2026-10-24T07:04:11.169545+00:00"},"data_business":{"matches":true,"lanes":[{"key":"data","label":"Data demand","url":"https://onlylabs.fyi/data-radar/data","json_url":"https://onlylabs.fyi/data-radar/data/signals.json"}],"matched_terms":["data"],"score":14,"reason":"Amazon (Nova) has a repo signal matching data demand."},"agent_handoff":{"signal_json":"https://onlylabs.fyi/signals/81e2f348-2b12-4eb1-9302-31bee0875cb1/signal.json","dossier_json":"https://onlylabs.fyi/labs/amazon/dossier.json","analysis_json":"https://onlylabs.fyi/analysis/amazon/analysis.json","analysis_evidence_json":"https://onlylabs.fyi/analysis/amazon/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: Data demand?","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/81e2f348-2b12-4eb1-9302-31bee0875cb1/signal.json","required":true},{"label":"source","url":"https://github.com/amazon-science/data-driven-personas","required":true},{"label":"dossier_json","url":"https://onlylabs.fyi/labs/amazon/dossier.json","required":true},{"label":"analysis_evidence_json","url":"https://onlylabs.fyi/analysis/amazon/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 Amazon (Nova)'s repo signal \"amazon-science/data-driven-personas\" for frontier lab strategy and data-business implications."},"semantic_triples":[{"subject":"Amazon (Nova)","predicate":"published repo","object":"amazon-science/data-driven-personas","text":"Amazon (Nova) published repo amazon-science/data-driven-personas."},{"subject":"amazon-science/data-driven-personas","predicate":"is classified as","object":"repo signal","text":"amazon-science/data-driven-personas is classified as repo signal."},{"subject":"amazon-science/data-driven-personas","predicate":"belongs to","object":"repos desk","text":"amazon-science/data-driven-personas belongs to repos desk."},{"subject":"amazon-science/data-driven-personas","predicate":"has context","object":"Python","text":"amazon-science/data-driven-personas has context Python."},{"subject":"amazon-science/data-driven-personas","predicate":"has evidence coverage","object":"1 captured evidence page","text":"amazon-science/data-driven-personas has evidence coverage 1 captured evidence page."},{"subject":"amazon-science/data-driven-personas","predicate":"matches data-business lanes","object":"Data demand","text":"amazon-science/data-driven-personas matches data-business lanes Data demand."},{"subject":"amazon-science/data-driven-personas","predicate":"has captured page count","object":"1","text":"amazon-science/data-driven-personas has captured page count 1."},{"subject":"amazon-science/data-driven-personas","predicate":"has readable page count","object":"1","text":"amazon-science/data-driven-personas has readable page count 1."},{"subject":"amazon-science/data-driven-personas","predicate":"has related signal count","object":"6","text":"amazon-science/data-driven-personas has related signal count 6."},{"subject":"amazon-science/data-driven-personas","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":"amazon-science/data-driven-personas 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":"amazon-science/data-driven-personas","predicate":"has source host","object":"github.com","text":"amazon-science/data-driven-personas has source host github.com."},{"subject":"amazon-science/data-driven-personas","predicate":"has lab","object":"Amazon (Nova)","text":"amazon-science/data-driven-personas has lab Amazon (Nova)."},{"subject":"amazon-science/data-driven-personas","predicate":"has signal desk","object":"repos","text":"amazon-science/data-driven-personas has signal desk repos."},{"subject":"amazon-science/data-driven-personas","predicate":"has source host","object":"github.com","text":"amazon-science/data-driven-personas has source host github.com."},{"subject":"amazon-science/data-driven-personas","predicate":"has repository","object":"amazon-science/data-driven-personas","text":"amazon-science/data-driven-personas has repository amazon-science/data-driven-personas."},{"subject":"amazon-science/data-driven-personas","predicate":"has language","object":"Python","text":"amazon-science/data-driven-personas has language Python."},{"subject":"amazon-science/data-driven-personas","predicate":"has radar lane","object":"Data demand","text":"amazon-science/data-driven-personas has radar lane Data demand."},{"subject":"amazon-science/data-driven-personas","predicate":"has matched term","object":"data","text":"amazon-science/data-driven-personas has matched term data."},{"subject":"amazon-science/data-driven-personas","predicate":"has watch term","object":"RL environments","text":"amazon-science/data-driven-personas has watch term RL environments."}]},"intelligence":{"signal_desk":"repos","answer":"Amazon (Nova) published amazon-science/data-driven-personas (Python). This repository signal exposes tooling, eval, infrastructure, or model-adjacent work before it may appear in a launch post. High-signal details: repo amazon-science/data-driven-personas · language Python. onlylabs links this event to 1 captured evidence page and 6 related repo signals. It also maps to Data demand in the data-business radar.","semantic_triples":[{"subject":"Amazon (Nova)","predicate":"published repo","object":"amazon-science/data-driven-personas","text":"Amazon (Nova) published repo amazon-science/data-driven-personas."},{"subject":"amazon-science/data-driven-personas","predicate":"is classified as","object":"repo signal","text":"amazon-science/data-driven-personas is classified as repo signal."},{"subject":"amazon-science/data-driven-personas","predicate":"belongs to","object":"repos desk","text":"amazon-science/data-driven-personas belongs to repos desk."},{"subject":"amazon-science/data-driven-personas","predicate":"has context","object":"Python","text":"amazon-science/data-driven-personas has context Python."},{"subject":"amazon-science/data-driven-personas","predicate":"has evidence coverage","object":"1 captured evidence page","text":"amazon-science/data-driven-personas has evidence coverage 1 captured evidence page."},{"subject":"amazon-science/data-driven-personas","predicate":"matches data-business lanes","object":"Data demand","text":"amazon-science/data-driven-personas matches data-business lanes Data demand."}]},"signal":{"id":"81e2f348-2b12-4eb1-9302-31bee0875cb1","url":"https://onlylabs.fyi/signals/81e2f348-2b12-4eb1-9302-31bee0875cb1","json_url":"https://onlylabs.fyi/signals/81e2f348-2b12-4eb1-9302-31bee0875cb1/signal.json","source_url":"https://github.com/amazon-science/data-driven-personas","title":"amazon-science/data-driven-personas","summary":"Amazon (Nova) 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":"amazon","name":"Amazon (Nova)","category":"frontier-lab"},"occurred_at":"2026-10-20T14:58:20+00:00","first_seen_at":"2026-10-24T07:00:37.03211+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/amazon-science/data-driven-personas"]},"facets":{"repo":"amazon-science/data-driven-personas","language":"Python"},"traction":{"github_stars":0,"hn_points":null,"hn_comments":null,"hn_story_id":null,"hf_downloads":null,"hf_likes":null},"data_radar":{"lanes":[{"key":"data","label":"Data demand","url":"https://onlylabs.fyi/data-radar/data"}],"score":14,"matched_terms":["data"],"reason":"Amazon (Nova) has a repo signal matching data demand."}},"primary_evidence_page":{"is_primary":true,"source_match":true,"url":"https://github.com/amazon-science/data-driven-personas","final_url":"https://github.com/amazon-science/data-driven-personas","title":"amazon-science/data-driven-personas repository metadata","http_status":200,"content_type":"application/json","capture_method":"plain","fetched_at":"2026-10-24T07:04:11.169545+00:00","bytes":26017,"raw_path":"bd3b1139f67fabf78924748ff5e732861c440cc2012e8878fe6395994c202d6d.json","content_hash":"6a38c3295d4f3981b76d78327857dcad0d553731f5766514dcad3e0dcce2eb65","excerpt_chars":1200,"truncated":true,"excerpt":"amazon-science/data-driven-personas Language: Python License: Apache-2.0 Stars: 0 Forks: 0 Open issues: 0 Created: 2026-10-20T14:58:20Z Pushed: 2026-10-21T10:35:50Z Default branch: main Fork: no Archived: no README: Data-Driven Persona Simulation This code is being released solely for academic and scientific reproducibility purposes, in support of the methods and findings described in the associated publication. Pull requests are not being accepted in order to maintain the code exactly as it was used in the paper. A framework for generating and evaluating synthetic personas (induced from human behavior data) to simulate survey responses across demographic groups using Large Language Models (LLMs). Overview This project enables researchers to: - Generate diverse, realistic personas induced from human behavior data (e.g., movie reviews, shopping history, survey responses) - Simulate survey responses using persona-conditioned LLMs - Evaluate simulation quality using multiple statistical metrics (TVD, KL-divergence, Wasserstein distance) - Analyze results across demographic groups and datasets Project Structure ```text data-driven-personas/ ├── src/ # Core source code and example run..."},"evidence_pages":[],"related_signals":[{"id":"c9033296-9906-4442-b6a9-e3223a4a0c89","url":"https://onlylabs.fyi/signals/c9033296-9906-4442-b6a9-e3223a4a0c89","source_url":"https://github.com/amazon-science/PurpleAudit","title":"amazon-science/PurpleAudit","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"amazon","name":"Amazon (Nova)","category":"frontier-lab"},"occurred_at":"2026-10-22T17:48:57+00:00","first_seen_at":"2026-10-23T07:00:36.960309+00:00","date_source":"source"},{"id":"e90daecf-0838-4660-9a8e-000fd8d43ea5","url":"https://onlylabs.fyi/signals/e90daecf-0838-4660-9a8e-000fd8d43ea5","source_url":"https://github.com/amazon-science/agent-ecc","title":"amazon-science/agent-ecc","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"amazon","name":"Amazon (Nova)","category":"frontier-lab"},"occurred_at":"2026-10-21T08:16:13+00:00","first_seen_at":"2026-10-22T07:00:37.834063+00:00","date_source":"source"},{"id":"8adc9223-000b-45ed-a975-8a92b0ed03cd","url":"https://onlylabs.fyi/signals/8adc9223-000b-45ed-a975-8a92b0ed03cd","source_url":"https://github.com/amazon-science/HypAgent","title":"amazon-science/HypAgent","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"amazon","name":"Amazon (Nova)","category":"frontier-lab"},"occurred_at":"2026-10-16T22:18:18+00:00","first_seen_at":"2026-10-20T07:00:38.102697+00:00","date_source":"source"},{"id":"6edd8f49-d725-4051-b89a-ab2591a1169e","url":"https://onlylabs.fyi/signals/6edd8f49-d725-4051-b89a-ab2591a1169e","source_url":"https://github.com/amazon-science/ListQA-Eval","title":"amazon-science/ListQA-Eval","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"amazon","name":"Amazon (Nova)","category":"frontier-lab"},"occurred_at":"2026-10-12T22:56:22+00:00","first_seen_at":"2026-10-13T07:00:39.039069+00:00","date_source":"source"},{"id":"5334795d-9810-4d77-88eb-661c7c0a71cc","url":"https://onlylabs.fyi/signals/5334795d-9810-4d77-88eb-661c7c0a71cc","source_url":"https://github.com/amazon-science/attune","title":"amazon-science/attune","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"amazon","name":"Amazon (Nova)","category":"frontier-lab"},"occurred_at":"2026-10-12T21:09:30+00:00","first_seen_at":"2026-10-14T07:00:37.608755+00:00","date_source":"source"},{"id":"274cd58d-333c-46be-ac88-c21307fbe4f2","url":"https://onlylabs.fyi/signals/274cd58d-333c-46be-ac88-c21307fbe4f2","source_url":"https://github.com/amazon-science/dlm-scaling","title":"amazon-science/dlm-scaling","context":"Python","kind":{"key":"repo_new","label":"Repo"},"org":{"slug":"amazon","name":"Amazon (Nova)","category":"frontier-lab"},"occurred_at":"2026-10-09T02:32:16+00:00","first_seen_at":"2026-10-15T07:00:37.265551+00:00","date_source":"source"}]}