{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFNS7Q3UENR44VCDEN6N6PJDWN","short_pith_number":"pith:XFNS7Q3U","schema_version":"1.0","canonical_sha256":"b95b2fc3742363ce5443237cdf3d23b346355f03f516ace47d1bc4b0c94ef109","source":{"kind":"arxiv","id":"2411.18822","version":5},"attestation_state":"computed","paper":{"title":"RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"eess.SP","authors_text":"Darren Forde, Gregory Darnell, Haraldur Hallgrimsson, Hyewon Jeong, James M. Rehg, Jaya Narain, Karthik J. Raghuram, Maxwell A. Xu, Richard Fineman, Shirley Ren","submitted_at":"2024-11-27T23:51:53Z","abstract_excerpt":"We present RelCon, a novel self-supervised Relative Contrastive learning approach for training a motion foundation model from wearable accelerometry sensors. First, a learnable distance measure is trained to capture motif similarity and domain-specific semantic information such as rotation invariance. Then, the learned distance provides a measurement of semantic similarity between a pair of accelerometry time-series, which we use to train our foundation model to model relative relationships across time and across subjects. The foundation model is trained on 1 billion segments from 87,376 parti"},"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":"2411.18822","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2024-11-27T23:51:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b720975d5bac384696780da51694aa8b5a6627ac4ff907ecedfb20f47b828fdc","abstract_canon_sha256":"d7adf29110f89e0c7fe8df0a9e13eeaa1d3dbf4f84e2d1f66c0daecab8d76090"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:34.021035Z","signature_b64":"kXOHQQp2Whcx/aGBMmsB0C3eG1UNv2rjvLGR1CpRBQttZBp+gdApNj8FnQDxEdXkwOjTPxijfVamf2uvdDu9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b95b2fc3742363ce5443237cdf3d23b346355f03f516ace47d1bc4b0c94ef109","last_reissued_at":"2026-07-05T10:47:34.020537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:34.020537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"eess.SP","authors_text":"Darren Forde, Gregory Darnell, Haraldur Hallgrimsson, Hyewon Jeong, James M. Rehg, Jaya Narain, Karthik J. Raghuram, Maxwell A. Xu, Richard Fineman, Shirley Ren","submitted_at":"2024-11-27T23:51:53Z","abstract_excerpt":"We present RelCon, a novel self-supervised Relative Contrastive learning approach for training a motion foundation model from wearable accelerometry sensors. First, a learnable distance measure is trained to capture motif similarity and domain-specific semantic information such as rotation invariance. Then, the learned distance provides a measurement of semantic similarity between a pair of accelerometry time-series, which we use to train our foundation model to model relative relationships across time and across subjects. The foundation model is trained on 1 billion segments from 87,376 parti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18822","kind":"arxiv","version":5},"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/2411.18822/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":"2411.18822","created_at":"2026-07-05T10:47:34.020595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18822v5","created_at":"2026-07-05T10:47:34.020595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18822","created_at":"2026-07-05T10:47:34.020595+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFNS7Q3UENR4","created_at":"2026-07-05T10:47:34.020595+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFNS7Q3UENR44VCD","created_at":"2026-07-05T10:47:34.020595+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFNS7Q3U","created_at":"2026-07-05T10:47:34.020595+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06617","citing_title":"Inertia-1: An Open Exploration of Wearable Motion Foundation Models","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07365","citing_title":"A robust PPG foundation model using multimodal physiological supervision","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02711","citing_title":"Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10172","citing_title":"Wearable AI in the Era of Large Sensor Models","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN","json":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN.json","graph_json":"https://pith.science/api/pith-number/XFNS7Q3UENR44VCDEN6N6PJDWN/graph.json","events_json":"https://pith.science/api/pith-number/XFNS7Q3UENR44VCDEN6N6PJDWN/events.json","paper":"https://pith.science/paper/XFNS7Q3U"},"agent_actions":{"view_html":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN","download_json":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN.json","view_paper":"https://pith.science/paper/XFNS7Q3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18822&json=true","fetch_graph":"https://pith.science/api/pith-number/XFNS7Q3UENR44VCDEN6N6PJDWN/graph.json","fetch_events":"https://pith.science/api/pith-number/XFNS7Q3UENR44VCDEN6N6PJDWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN/action/storage_attestation","attest_author":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN/action/author_attestation","sign_citation":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN/action/citation_signature","submit_replication":"https://pith.science/pith/XFNS7Q3UENR44VCDEN6N6PJDWN/action/replication_record"}},"created_at":"2026-07-05T10:47:34.020595+00:00","updated_at":"2026-07-05T10:47:34.020595+00:00"}