{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2VHAUBIRIXT2BDBYYFKWVJCQ3R","short_pith_number":"pith:2VHAUBIR","schema_version":"1.0","canonical_sha256":"d54e0a051145e7a08c38c1556aa450dc7f8e089d9db27532e48379f7da47993f","source":{"kind":"arxiv","id":"2402.13349","version":2},"attestation_state":"computed","paper":{"title":"Aria Everyday Activities Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Alexander Gamino, Carl Ren, Cheng Peng, Chris Sweeney, Edward Miller, Huixuan Tang, Jakob Julian Engel, Jeff Meissner, Jing Dong, Kiran Somasundaram, Luis Pesqueira, Mark Schwesinger, Nicholas Charron, Omkar Parkhi, Pierre Moulon, Qiao Gu, Renzo De Nardi, Richard Newcombe, Shangyi Cheng, Steve Saarinen, Vijay Baiyya, Xiaqing Pan, Yuyang Zou, Zhaoyang Lv","submitted_at":"2024-02-20T19:53:15Z","abstract_excerpt":"We present Aria Everyday Activities (AEA) Dataset, an egocentric multimodal open dataset recorded using Project Aria glasses. AEA contains 143 daily activity sequences recorded by multiple wearers in five geographically diverse indoor locations. Each of the recording contains multimodal sensor data recorded through the Project Aria glasses. In addition, AEA provides machine perception data including high frequency globally aligned 3D trajectories, scene point cloud, per-frame 3D eye gaze vector and time aligned speech transcription. In this paper, we demonstrate a few exemplar research applica"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.13349","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-20T19:53:15Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"2e97f4de08a182ef4f8120eaafeb28e73584f3ea55d9b96e6fecec0f5ae54639","abstract_canon_sha256":"686fbeb69fbb3341efd092aaaf4c7237e9ab5279e78660dc323c69c64b8a984e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:04.266079Z","signature_b64":"z18BJRBAD7sVAgqgLdggMZti7q7uiyICT7v7UDOghVKh9mt6ERpQe//faOuqiv8bSgXky3MrFX21w9YCswwOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d54e0a051145e7a08c38c1556aa450dc7f8e089d9db27532e48379f7da47993f","last_reissued_at":"2026-07-05T07:48:04.265469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:04.265469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aria Everyday Activities Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Alexander Gamino, Carl Ren, Cheng Peng, Chris Sweeney, Edward Miller, Huixuan Tang, Jakob Julian Engel, Jeff Meissner, Jing Dong, Kiran Somasundaram, Luis Pesqueira, Mark Schwesinger, Nicholas Charron, Omkar Parkhi, Pierre Moulon, Qiao Gu, Renzo De Nardi, Richard Newcombe, Shangyi Cheng, Steve Saarinen, Vijay Baiyya, Xiaqing Pan, Yuyang Zou, Zhaoyang Lv","submitted_at":"2024-02-20T19:53:15Z","abstract_excerpt":"We present Aria Everyday Activities (AEA) Dataset, an egocentric multimodal open dataset recorded using Project Aria glasses. AEA contains 143 daily activity sequences recorded by multiple wearers in five geographically diverse indoor locations. Each of the recording contains multimodal sensor data recorded through the Project Aria glasses. In addition, AEA provides machine perception data including high frequency globally aligned 3D trajectories, scene point cloud, per-frame 3D eye gaze vector and time aligned speech transcription. In this paper, we demonstrate a few exemplar research applica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13349","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.13349/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.13349","created_at":"2026-07-05T07:48:04.265535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13349v2","created_at":"2026-07-05T07:48:04.265535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13349","created_at":"2026-07-05T07:48:04.265535+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VHAUBIRIXT2","created_at":"2026-07-05T07:48:04.265535+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VHAUBIRIXT2BDBY","created_at":"2026-07-05T07:48:04.265535+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VHAUBIR","created_at":"2026-07-05T07:48:04.265535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08083","citing_title":"HeadRoom: Lightweight, Edge-deployable Pipeline for Adaptive Notification Routing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02075","citing_title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03890","citing_title":"OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05945","citing_title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00825","citing_title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00825","citing_title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05945","citing_title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19004","citing_title":"EgoTraj: Real-World Egocentric Human Trajectory Dataset for Multimodal Prediction","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2508.00088","citing_title":"The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.17622","citing_title":"Memento: Towards Proactive Visualization of Everyday Memories with Personal Wearable AR Assistant","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00793","citing_title":"SpeechLess: Micro-utterance with Personalized Spatial Memory-aware Assistant in Everyday Augmented Reality","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05945","citing_title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05945","citing_title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05945","citing_title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10936","citing_title":"Personal Visual Context Learning in Large Multimodal Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05945","citing_title":"MobileEgo Anywhere: Open Infrastructure for long horizon egocentric data on commodity hardware","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16624","citing_title":"SAM 3D: 3Dfy Anything in Images","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09535","citing_title":"EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09886","citing_title":"Not Your Stereo-Typical Estimator: Combining Vision and Language for Volume Perception","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08342","citing_title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R","json":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R.json","graph_json":"https://pith.science/api/pith-number/2VHAUBIRIXT2BDBYYFKWVJCQ3R/graph.json","events_json":"https://pith.science/api/pith-number/2VHAUBIRIXT2BDBYYFKWVJCQ3R/events.json","paper":"https://pith.science/paper/2VHAUBIR"},"agent_actions":{"view_html":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R","download_json":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R.json","view_paper":"https://pith.science/paper/2VHAUBIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13349&json=true","fetch_graph":"https://pith.science/api/pith-number/2VHAUBIRIXT2BDBYYFKWVJCQ3R/graph.json","fetch_events":"https://pith.science/api/pith-number/2VHAUBIRIXT2BDBYYFKWVJCQ3R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R/action/storage_attestation","attest_author":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R/action/author_attestation","sign_citation":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R/action/citation_signature","submit_replication":"https://pith.science/pith/2VHAUBIRIXT2BDBYYFKWVJCQ3R/action/replication_record"}},"created_at":"2026-07-05T07:48:04.265535+00:00","updated_at":"2026-07-05T07:48:04.265535+00:00"}