{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L3JF2JY3CAOKCOHNGASBB4XPDV","short_pith_number":"pith:L3JF2JY3","schema_version":"1.0","canonical_sha256":"5ed25d271b101ca138ed302410f2ef1d7659bc407134c20f1c0edb65950c79ea","source":{"kind":"arxiv","id":"2605.01369","version":2},"attestation_state":"computed","paper":{"title":"MU-SHOT-Fi: Self-Supervised Multi-User Wi-Fi Sensing with Source-free Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MU-SHOT-Fi adapts a pre-trained Wi-Fi model to new rooms and frequencies using only unlabeled target CSI and self-supervision.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"eess.SP","authors_text":"Ahmed Y. Radwan, Hina Tabassum","submitted_at":"2026-05-02T10:29:40Z","abstract_excerpt":"Deep learning has been widely adopted for WiFi CSI-based human activity recognition (HAR) due to its ability to learn spatio-temporal features in a privacy-preserving and cost-effective manner. However, DL-based models generalize poorly across environments, a challenge amplified in multi-user settings where overlapping activities cause CSI entanglement and domain shifts. Practical deployments often limit access to labeled source data due to privacy constraints, motivating source-free adaptation using only unlabeled target-domain CSI and a pre-trained source model. In this paper, we propose MU-"},"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":"2605.01369","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2026-05-02T10:29:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"88da9ded9568f2d079fc04ca23fc3d58397ea1b4e0a735e7ecbea01ac5eb7567","abstract_canon_sha256":"981d0567238b2480aeb767f974b8a940411e44437362b68962d5941afe0869d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:41.495188Z","signature_b64":"UQgNofGFTF24qbA/Y8mDSJ0t6jRum79gtkQapeP7rLA1kJvvmKueuZxsXAo+uUH/GL2l8e3fLIlJ9bWzMUZ1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ed25d271b101ca138ed302410f2ef1d7659bc407134c20f1c0edb65950c79ea","last_reissued_at":"2026-05-22T02:04:41.494382Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:41.494382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MU-SHOT-Fi: Self-Supervised Multi-User Wi-Fi Sensing with Source-free Unsupervised Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MU-SHOT-Fi adapts a pre-trained Wi-Fi model to new rooms and frequencies using only unlabeled target CSI and self-supervision.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"eess.SP","authors_text":"Ahmed Y. Radwan, Hina Tabassum","submitted_at":"2026-05-02T10:29:40Z","abstract_excerpt":"Deep learning has been widely adopted for WiFi CSI-based human activity recognition (HAR) due to its ability to learn spatio-temporal features in a privacy-preserving and cost-effective manner. However, DL-based models generalize poorly across environments, a challenge amplified in multi-user settings where overlapping activities cause CSI entanglement and domain shifts. Practical deployments often limit access to labeled source data due to privacy constraints, motivating source-free adaptation using only unlabeled target-domain CSI and a pre-trained source model. In this paper, we propose MU-"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MU-SHOT-Fi effectively recovers multi-user exact-activity classification performance under large domain shifts while maintaining accurate occupancy estimation and preventing collapse toward dominant classes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the pre-trained source model provides a sufficiently rich feature backbone that frozen-classifier adaptation plus the proposed self-supervision signals can recover performance without any target labels or source data access.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MU-SHOT-Fi recovers multi-user activity classification accuracy under domain shifts in WiFi CSI sensing using source-free adaptation with Hungarian matching, occupancy-weighted entropy regularization, and rotation prediction self-supervision.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MU-SHOT-Fi adapts a pre-trained Wi-Fi model to new rooms and frequencies using only unlabeled target CSI and self-supervision.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a0a4b92ef26cbd98b4fac6079dee81764581237f31c3babd3b60467ad96e852b"},"source":{"id":"2605.01369","kind":"arxiv","version":2},"verdict":{"id":"85633487-9b57-4685-bc60-cdcde02dd6ac","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T18:30:53.813995Z","strongest_claim":"MU-SHOT-Fi effectively recovers multi-user exact-activity classification performance under large domain shifts while maintaining accurate occupancy estimation and preventing collapse toward dominant classes.","one_line_summary":"MU-SHOT-Fi recovers multi-user activity classification accuracy under domain shifts in WiFi CSI sensing using source-free adaptation with Hungarian matching, occupancy-weighted entropy regularization, and rotation prediction self-supervision.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the pre-trained source model provides a sufficiently rich feature backbone that frozen-classifier adaptation plus the proposed self-supervision signals can recover performance without any target labels or source data access.","pith_extraction_headline":"MU-SHOT-Fi adapts a pre-trained Wi-Fi model to new rooms and frequencies using only unlabeled target CSI and self-supervision."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01369/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T18:34:35.230989Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:19:52.161541Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d9e6b8e3d7e17331639e87be08fe9c79bc96bedef8d3b16d350b5e262e097bdc"},"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":"2605.01369","created_at":"2026-05-22T02:04:41.494503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.01369v2","created_at":"2026-05-22T02:04:41.494503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01369","created_at":"2026-05-22T02:04:41.494503+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3JF2JY3CAOK","created_at":"2026-05-22T02:04:41.494503+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3JF2JY3CAOKCOHN","created_at":"2026-05-22T02:04:41.494503+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3JF2JY3","created_at":"2026-05-22T02:04:41.494503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV","json":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV.json","graph_json":"https://pith.science/api/pith-number/L3JF2JY3CAOKCOHNGASBB4XPDV/graph.json","events_json":"https://pith.science/api/pith-number/L3JF2JY3CAOKCOHNGASBB4XPDV/events.json","paper":"https://pith.science/paper/L3JF2JY3"},"agent_actions":{"view_html":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV","download_json":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV.json","view_paper":"https://pith.science/paper/L3JF2JY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.01369&json=true","fetch_graph":"https://pith.science/api/pith-number/L3JF2JY3CAOKCOHNGASBB4XPDV/graph.json","fetch_events":"https://pith.science/api/pith-number/L3JF2JY3CAOKCOHNGASBB4XPDV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV/action/storage_attestation","attest_author":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV/action/author_attestation","sign_citation":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV/action/citation_signature","submit_replication":"https://pith.science/pith/L3JF2JY3CAOKCOHNGASBB4XPDV/action/replication_record"}},"created_at":"2026-05-22T02:04:41.494503+00:00","updated_at":"2026-05-22T02:04:41.494503+00:00"}