{"id":50398895,"url":"https://github.com/nachiket273/aora-light","last_synced_at":"2026-05-30T22:02:18.912Z","repository":{"id":355657604,"uuid":"1229037041","full_name":"nachiket273/aora-light","owner":"nachiket273","description":"Agreement-Aware Orthogonal Routing Attention (AORA-Light): lightweight dual-branch transformer attention for robustness to non-consensus signals.","archived":false,"fork":false,"pushed_at":"2026-05-13T10:05:39.000Z","size":11,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-13T12:13:32.724Z","etag":null,"topics":["attention-mechanism","deep-learning","experimental-ml","language-modeling","neural-network","pytorch","research","robust-ml","scientific-machine-learning","transformer"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nachiket273.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-04T16:26:58.000Z","updated_at":"2026-05-13T10:06:00.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/nachiket273/aora-light","commit_stats":null,"previous_names":["nachiket273/aora","nachiket273/aora-light"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/nachiket273/aora-light","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nachiket273%2Faora-light","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nachiket273%2Faora-light/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nachiket273%2Faora-light/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nachiket273%2Faora-light/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nachiket273","download_url":"https://codeload.github.com/nachiket273/aora-light/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nachiket273%2Faora-light/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33711018,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-30T02:00:06.278Z","response_time":92,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["attention-mechanism","deep-learning","experimental-ml","language-modeling","neural-network","pytorch","research","robust-ml","scientific-machine-learning","transformer"],"created_at":"2026-05-30T22:02:18.346Z","updated_at":"2026-05-30T22:02:18.907Z","avatar_url":"https://github.com/nachiket273.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# AORA-Light\n\nA lightweight experimental transformer architecture introducing dual-branch attention:\n\n- consensus attention\n- exclusive attention\n\nAORA-Light studies whether explicit separation of consensus and anti-consensus context improves robustness to noisy and minority signals.\n\n## Current status\n\nEarly prototype.\n\n## Planned experiments\n\n- Tiny Shakespeare\n- WikiText-2 subset\n- Needle-in-noise benchmark\n- contradiction benchmark\n- scientific image benchmark\n\n## Hardware\n\nDesigned for low-resource experimentation:\n\n- RTX 3050 6GB\n- Google Colab Free\n\n## Citation\n\nComing soon.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnachiket273%2Faora-light","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnachiket273%2Faora-light","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnachiket273%2Faora-light/lists"}