{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HKRD3LSSFYTK2BMJW3ZYRRVMUY","short_pith_number":"pith:HKRD3LSS","schema_version":"1.0","canonical_sha256":"3aa23dae522e26ad0589b6f388c6aca61c97e2c18b964e6936399170564c89e2","source":{"kind":"arxiv","id":"2209.11750","version":2},"attestation_state":"computed","paper":{"title":"Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fran\\c{c}ois Portet, Philippe Lalanda, Sannara Ek","submitted_at":"2022-09-22T09:42:08Z","abstract_excerpt":"Human Activity Recognition (HAR) on mobile devices has been demonstrated to be possible using neural models trained on data collected from the device's inertial measurement units. These models have used Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), Transformers or a combination of these to achieve state-of-the-art results with real-time performance. However, these approaches have not been extensively evaluated in real-world situations where the input data may be different from the training data. This paper highlights the issue of data heterogeneity in machine learning a"},"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":"2209.11750","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-22T09:42:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"01192a25a518e5778643540fddcae1e9286f289f53e55ca5c8648552614c51de","abstract_canon_sha256":"7e13cbd83457ca780cb0c78b386838cf5c6b6014d2fcd1685a874b8cbccfe982"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:51.586323Z","signature_b64":"AGoUh2Bs8RD+hwU6MzSXpUgQDHhCQTng1UarOH7i8zRM266eq8GNZPeKsyAxHOVazZHHqOZcv/jvcqyXVIcjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aa23dae522e26ad0589b6f388c6aca61c97e2c18b964e6936399170564c89e2","last_reissued_at":"2026-07-05T11:57:51.585792Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:51.585792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Fran\\c{c}ois Portet, Philippe Lalanda, Sannara Ek","submitted_at":"2022-09-22T09:42:08Z","abstract_excerpt":"Human Activity Recognition (HAR) on mobile devices has been demonstrated to be possible using neural models trained on data collected from the device's inertial measurement units. These models have used Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTMs), Transformers or a combination of these to achieve state-of-the-art results with real-time performance. However, these approaches have not been extensively evaluated in real-world situations where the input data may be different from the training data. This paper highlights the issue of data heterogeneity in machine learning a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11750","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/2209.11750/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":"2209.11750","created_at":"2026-07-05T11:57:51.585860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11750v2","created_at":"2026-07-05T11:57:51.585860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11750","created_at":"2026-07-05T11:57:51.585860+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKRD3LSSFYTK","created_at":"2026-07-05T11:57:51.585860+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKRD3LSSFYTK2BMJ","created_at":"2026-07-05T11:57:51.585860+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKRD3LSS","created_at":"2026-07-05T11:57:51.585860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05671","citing_title":"GraMFedDHAR: Graph Based Multimodal Differentially Private Federated HAR","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY","json":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY.json","graph_json":"https://pith.science/api/pith-number/HKRD3LSSFYTK2BMJW3ZYRRVMUY/graph.json","events_json":"https://pith.science/api/pith-number/HKRD3LSSFYTK2BMJW3ZYRRVMUY/events.json","paper":"https://pith.science/paper/HKRD3LSS"},"agent_actions":{"view_html":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY","download_json":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY.json","view_paper":"https://pith.science/paper/HKRD3LSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11750&json=true","fetch_graph":"https://pith.science/api/pith-number/HKRD3LSSFYTK2BMJW3ZYRRVMUY/graph.json","fetch_events":"https://pith.science/api/pith-number/HKRD3LSSFYTK2BMJW3ZYRRVMUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY/action/storage_attestation","attest_author":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY/action/author_attestation","sign_citation":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY/action/citation_signature","submit_replication":"https://pith.science/pith/HKRD3LSSFYTK2BMJW3ZYRRVMUY/action/replication_record"}},"created_at":"2026-07-05T11:57:51.585860+00:00","updated_at":"2026-07-05T11:57:51.585860+00:00"}