{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DJVJPHJYUGWFWENWL5VIGWXWR7","short_pith_number":"pith:DJVJPHJY","schema_version":"1.0","canonical_sha256":"1a6a979d38a1ac5b11b65f6a835af68ff3fc53bbb97dceb731f401d4371d99a4","source":{"kind":"arxiv","id":"2507.00061","version":1},"attestation_state":"computed","paper":{"title":"Smooth-Distill: A Self-distillation Framework for Multitask Learning with Wearable Sensor Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Duc-Nghia Tran, Duc-Tan Tran, Hieu H. Pham, Hoang-Dieu Vu, Nicolas Vuillerme, Quang-Tu Pham","submitted_at":"2025-06-27T06:51:51Z","abstract_excerpt":"This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection using wearable sensor data. The proposed approach utilizes a unified CNN-based architecture, MTL-net, which processes accelerometer data and branches into two outputs for each respective task. Unlike conventional distillation methods that require separate teacher and student models, the proposed framework utilizes a smoothed, historical version of the model itself as the teacher, significantly reducing training computationa"},"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":"2507.00061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-27T06:51:51Z","cross_cats_sorted":["cs.AI","eess.SP"],"title_canon_sha256":"c35e57c5d9bbf1e060efabcd4254b7b657bda7c0191852f986792c7c1991d311","abstract_canon_sha256":"abd820933b11d0f73ed44433ee3349bcf542478b63d4e4eb064922400992a800"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:36.013885Z","signature_b64":"F77s7ZtOU4iGPLboFlkZ6g5R/+hwTPaYQl4NYlM/jlKShAsWhbN8HTGL9jddmaBJZT7imO72y76jh9bo2I5+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a6a979d38a1ac5b11b65f6a835af68ff3fc53bbb97dceb731f401d4371d99a4","last_reissued_at":"2026-07-05T11:29:36.013398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:36.013398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smooth-Distill: A Self-distillation Framework for Multitask Learning with Wearable Sensor Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.SP"],"primary_cat":"cs.LG","authors_text":"Duc-Nghia Tran, Duc-Tan Tran, Hieu H. Pham, Hoang-Dieu Vu, Nicolas Vuillerme, Quang-Tu Pham","submitted_at":"2025-06-27T06:51:51Z","abstract_excerpt":"This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection using wearable sensor data. The proposed approach utilizes a unified CNN-based architecture, MTL-net, which processes accelerometer data and branches into two outputs for each respective task. Unlike conventional distillation methods that require separate teacher and student models, the proposed framework utilizes a smoothed, historical version of the model itself as the teacher, significantly reducing training computationa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00061","kind":"arxiv","version":1},"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/2507.00061/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":"2507.00061","created_at":"2026-07-05T11:29:36.013465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00061v1","created_at":"2026-07-05T11:29:36.013465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00061","created_at":"2026-07-05T11:29:36.013465+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJVJPHJYUGWF","created_at":"2026-07-05T11:29:36.013465+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJVJPHJYUGWFWENW","created_at":"2026-07-05T11:29:36.013465+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJVJPHJY","created_at":"2026-07-05T11:29:36.013465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06617","citing_title":"Inertia-1: An Open Exploration of Wearable Motion Foundation Models","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7","json":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7.json","graph_json":"https://pith.science/api/pith-number/DJVJPHJYUGWFWENWL5VIGWXWR7/graph.json","events_json":"https://pith.science/api/pith-number/DJVJPHJYUGWFWENWL5VIGWXWR7/events.json","paper":"https://pith.science/paper/DJVJPHJY"},"agent_actions":{"view_html":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7","download_json":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7.json","view_paper":"https://pith.science/paper/DJVJPHJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00061&json=true","fetch_graph":"https://pith.science/api/pith-number/DJVJPHJYUGWFWENWL5VIGWXWR7/graph.json","fetch_events":"https://pith.science/api/pith-number/DJVJPHJYUGWFWENWL5VIGWXWR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7/action/storage_attestation","attest_author":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7/action/author_attestation","sign_citation":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7/action/citation_signature","submit_replication":"https://pith.science/pith/DJVJPHJYUGWFWENWL5VIGWXWR7/action/replication_record"}},"created_at":"2026-07-05T11:29:36.013465+00:00","updated_at":"2026-07-05T11:29:36.013465+00:00"}