{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2UONNCID2RFHEEN7GGPYGHFED2","short_pith_number":"pith:2UONNCID","schema_version":"1.0","canonical_sha256":"d51cd68903d44a7211bf319f831ca41eb1c45d704845744aa0fd0d671b0ae791","source":{"kind":"arxiv","id":"2607.29353","version":1},"attestation_state":"computed","paper":{"title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.LG","authors_text":"Charlotte Frenkel, Douwe den Blanken, Martin Lefebvre","submitted_at":"2026-07-31T12:37:48Z","abstract_excerpt":"With the ever-increasing pervasiveness of smart edge devices, the demand is growing for applications that can be tailored to users (e.g., custom keyword spotting) or patients (e.g., adaptive health monitoring). Yet, most edge devices rely on fixed inference algorithms and thus cannot learn on-device to personalize predictions. When they can, devices typically support only a specific learning scenario, such as few-shot learning (FSL): going beyond this requires resorting either to another specialized device or to cloud-based retraining, which implies significant energy and latency overheads, 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":"2607.29353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T12:37:48Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"fc9a6ca934ae6ceac80fae4935de31eec89f3e88e25f582c9a495f0c7e99e655","abstract_canon_sha256":"cd8dc5ae52d377929828b0b52684c24c4c4f5079f329170a3607034ea13ddc80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:33:15.371570Z","signature_b64":"oFTun7H6zxy00xVBRKw48RG8TJ+4XQuK++Wqgc12AsOspjRiKsTGbK1QZ7epofLrrvHJDaaRBOnnwnYbN+pPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d51cd68903d44a7211bf319f831ca41eb1c45d704845744aa0fd0d671b0ae791","last_reissued_at":"2026-08-03T01:33:15.369448Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:33:15.369448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.LG","authors_text":"Charlotte Frenkel, Douwe den Blanken, Martin Lefebvre","submitted_at":"2026-07-31T12:37:48Z","abstract_excerpt":"With the ever-increasing pervasiveness of smart edge devices, the demand is growing for applications that can be tailored to users (e.g., custom keyword spotting) or patients (e.g., adaptive health monitoring). Yet, most edge devices rely on fixed inference algorithms and thus cannot learn on-device to personalize predictions. When they can, devices typically support only a specific learning scenario, such as few-shot learning (FSL): going beyond this requires resorting either to another specialized device or to cloud-based retraining, which implies significant energy and latency overheads, a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29353","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/2607.29353/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":"2607.29353","created_at":"2026-08-03T01:33:15.370311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29353v1","created_at":"2026-08-03T01:33:15.370311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29353","created_at":"2026-08-03T01:33:15.370311+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UONNCID2RFH","created_at":"2026-08-03T01:33:15.370311+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UONNCID2RFHEEN7","created_at":"2026-08-03T01:33:15.370311+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UONNCID","created_at":"2026-08-03T01:33:15.370311+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/2UONNCID2RFHEEN7GGPYGHFED2","json":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2.json","graph_json":"https://pith.science/api/pith-number/2UONNCID2RFHEEN7GGPYGHFED2/graph.json","events_json":"https://pith.science/api/pith-number/2UONNCID2RFHEEN7GGPYGHFED2/events.json","paper":"https://pith.science/paper/2UONNCID"},"agent_actions":{"view_html":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2","download_json":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2.json","view_paper":"https://pith.science/paper/2UONNCID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29353&json=true","fetch_graph":"https://pith.science/api/pith-number/2UONNCID2RFHEEN7GGPYGHFED2/graph.json","fetch_events":"https://pith.science/api/pith-number/2UONNCID2RFHEEN7GGPYGHFED2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2/action/storage_attestation","attest_author":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2/action/author_attestation","sign_citation":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2/action/citation_signature","submit_replication":"https://pith.science/pith/2UONNCID2RFHEEN7GGPYGHFED2/action/replication_record"}},"created_at":"2026-08-03T01:33:15.370311+00:00","updated_at":"2026-08-03T01:33:15.370311+00:00"}