{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JWN6CTUZK3MCC7X5D27OG6PEAA","short_pith_number":"pith:JWN6CTUZ","schema_version":"1.0","canonical_sha256":"4d9be14e9956d8217efd1ebee379e4000bd7e8033d10131842bfb942e71a1c15","source":{"kind":"arxiv","id":"2409.06612","version":1},"attestation_state":"computed","paper":{"title":"Label-free Monitoring of Self-Supervised Learning Progress","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Isaac Xu, Scott Lowe, Thomas Trappenberg","submitted_at":"2024-09-10T16:04:10Z","abstract_excerpt":"Self-supervised learning (SSL) is an effective method for exploiting unlabelled data to learn a high-level embedding space that can be used for various downstream tasks. However, existing methods to monitor the quality of the encoder -- either during training for one model or to compare several trained models -- still rely on access to annotated data. When SSL methodologies are applied to new data domains, a sufficiently large labelled dataset may not always be available. In this study, we propose several evaluation metrics which can be applied on the embeddings of unlabelled data and investig"},"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":"2409.06612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-10T16:04:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"483da0e7ac73f1b85ca3f96707adac306325c03426029ad8f32a2511ceb27a85","abstract_canon_sha256":"8a50f4cf4f4bc3e56e00310bcae7a6bfd0fff8881037d7e5062e4a2293ad975e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:27.123707Z","signature_b64":"uwnkbVcprlRwAyoednO1B+b6ElVw02qSII5jol5oIQ3nStd//Zgevva1/qYfL7SgjYqxxQyLh2rQyO3g8zCDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d9be14e9956d8217efd1ebee379e4000bd7e8033d10131842bfb942e71a1c15","last_reissued_at":"2026-07-05T09:05:27.123252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:27.123252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-free Monitoring of Self-Supervised Learning Progress","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Isaac Xu, Scott Lowe, Thomas Trappenberg","submitted_at":"2024-09-10T16:04:10Z","abstract_excerpt":"Self-supervised learning (SSL) is an effective method for exploiting unlabelled data to learn a high-level embedding space that can be used for various downstream tasks. However, existing methods to monitor the quality of the encoder -- either during training for one model or to compare several trained models -- still rely on access to annotated data. When SSL methodologies are applied to new data domains, a sufficiently large labelled dataset may not always be available. In this study, we propose several evaluation metrics which can be applied on the embeddings of unlabelled data and investig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06612","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/2409.06612/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":"2409.06612","created_at":"2026-07-05T09:05:27.123324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06612v1","created_at":"2026-07-05T09:05:27.123324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06612","created_at":"2026-07-05T09:05:27.123324+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWN6CTUZK3MC","created_at":"2026-07-05T09:05:27.123324+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWN6CTUZK3MCC7X5","created_at":"2026-07-05T09:05:27.123324+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWN6CTUZ","created_at":"2026-07-05T09:05:27.123324+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/JWN6CTUZK3MCC7X5D27OG6PEAA","json":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA.json","graph_json":"https://pith.science/api/pith-number/JWN6CTUZK3MCC7X5D27OG6PEAA/graph.json","events_json":"https://pith.science/api/pith-number/JWN6CTUZK3MCC7X5D27OG6PEAA/events.json","paper":"https://pith.science/paper/JWN6CTUZ"},"agent_actions":{"view_html":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA","download_json":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA.json","view_paper":"https://pith.science/paper/JWN6CTUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06612&json=true","fetch_graph":"https://pith.science/api/pith-number/JWN6CTUZK3MCC7X5D27OG6PEAA/graph.json","fetch_events":"https://pith.science/api/pith-number/JWN6CTUZK3MCC7X5D27OG6PEAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA/action/storage_attestation","attest_author":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA/action/author_attestation","sign_citation":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA/action/citation_signature","submit_replication":"https://pith.science/pith/JWN6CTUZK3MCC7X5D27OG6PEAA/action/replication_record"}},"created_at":"2026-07-05T09:05:27.123324+00:00","updated_at":"2026-07-05T09:05:27.123324+00:00"}