{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ULLKUBGMPUAFX2IU4TBHW5XSHT","short_pith_number":"pith:ULLKUBGM","schema_version":"1.0","canonical_sha256":"a2d6aa04cc7d005be914e4c27b76f23cd3c7a8742de7cf10dc5a93c44f6b7361","source":{"kind":"arxiv","id":"2507.07033","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Learning at the Edge: The Cost of Labeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Asal Rangrazi, Charalampos Kalalas, Fernanda Fam\\'a, Marco Miozzo, Paolo Dini, Roberto Pereira","submitted_at":"2025-07-09T17:03:50Z","abstract_excerpt":"Contrastive learning (CL) has recently emerged as an alternative to traditional supervised machine learning solutions by enabling rich representations from unstructured and unlabeled data. However, CL and, more broadly, self-supervised learning (SSL) methods often demand a large amount of data and computational resources, posing challenges for deployment on resource-constrained edge devices. In this work, we explore the feasibility and efficiency of SSL techniques for edge-based learning, focusing on trade-offs between model performance and energy efficiency. In particular, we analyze how diff"},"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":"2507.07033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T17:03:50Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"f8793f13b4a0372d4cd475675f8c3baed31eef3090b70234c06b1054b7a3903e","abstract_canon_sha256":"a82de49c68c409b12b7c3a74aa2b9b7c18b04b3203511fafe9b3049da50787cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:28.000125Z","signature_b64":"D6gzu8xuE0beeqFE63N0P22O5Gd4FBS3BENuGloXmnxAorHp0/KCvbJavVK204l9Bu//iSLyALxYXA0nC7DLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d6aa04cc7d005be914e4c27b76f23cd3c7a8742de7cf10dc5a93c44f6b7361","last_reissued_at":"2026-07-05T11:34:27.999621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:27.999621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Learning at the Edge: The Cost of Labeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Asal Rangrazi, Charalampos Kalalas, Fernanda Fam\\'a, Marco Miozzo, Paolo Dini, Roberto Pereira","submitted_at":"2025-07-09T17:03:50Z","abstract_excerpt":"Contrastive learning (CL) has recently emerged as an alternative to traditional supervised machine learning solutions by enabling rich representations from unstructured and unlabeled data. However, CL and, more broadly, self-supervised learning (SSL) methods often demand a large amount of data and computational resources, posing challenges for deployment on resource-constrained edge devices. In this work, we explore the feasibility and efficiency of SSL techniques for edge-based learning, focusing on trade-offs between model performance and energy efficiency. In particular, we analyze how diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07033","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/2507.07033/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":"2507.07033","created_at":"2026-07-05T11:34:27.999681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07033v1","created_at":"2026-07-05T11:34:27.999681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07033","created_at":"2026-07-05T11:34:27.999681+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULLKUBGMPUAF","created_at":"2026-07-05T11:34:27.999681+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULLKUBGMPUAFX2IU","created_at":"2026-07-05T11:34:27.999681+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULLKUBGM","created_at":"2026-07-05T11:34:27.999681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07033","citing_title":"Self-Supervised Learning at the Edge: The Cost of Labeling","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT","json":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT.json","graph_json":"https://pith.science/api/pith-number/ULLKUBGMPUAFX2IU4TBHW5XSHT/graph.json","events_json":"https://pith.science/api/pith-number/ULLKUBGMPUAFX2IU4TBHW5XSHT/events.json","paper":"https://pith.science/paper/ULLKUBGM"},"agent_actions":{"view_html":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT","download_json":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT.json","view_paper":"https://pith.science/paper/ULLKUBGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07033&json=true","fetch_graph":"https://pith.science/api/pith-number/ULLKUBGMPUAFX2IU4TBHW5XSHT/graph.json","fetch_events":"https://pith.science/api/pith-number/ULLKUBGMPUAFX2IU4TBHW5XSHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT/action/storage_attestation","attest_author":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT/action/author_attestation","sign_citation":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT/action/citation_signature","submit_replication":"https://pith.science/pith/ULLKUBGMPUAFX2IU4TBHW5XSHT/action/replication_record"}},"created_at":"2026-07-05T11:34:27.999681+00:00","updated_at":"2026-07-05T11:34:27.999681+00:00"}