{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DNYY5ZFQNZMEPD7HIZJCPPPQTV","short_pith_number":"pith:DNYY5ZFQ","schema_version":"1.0","canonical_sha256":"1b718ee4b06e58478fe7465227bdf09d758d240055cd19a6ae866f1522c3c6cf","source":{"kind":"arxiv","id":"2606.03338","version":1},"attestation_state":"computed","paper":{"title":"IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Julie Mordacq, Steve Oudot, Vicky Kalogeiton","submitted_at":"2026-06-02T08:47:17Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard protocol for evaluating these representations, linear probing, is computationally expensive, sensitive to hyperparameters, and provides limited insight into the geometric structure of the representation space. In this work, motivated by connections between neural network generalization and intrinsic dimension (ID) we propose IdEst, a method for estimating the ID of SSL representations via the Minimum Spanning Tree dimension estimator ($\\mathrm{dim"},"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":"2606.03338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T08:47:17Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c9ead73d6b96e2ae4d5f7f980dde1c955a4c75cad22cfc93623b277cdf78679d","abstract_canon_sha256":"e67c86d10e4732037d881887a288d484e3c64e2ba5c411a9f429fbd6a7f10983"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:55.372962Z","signature_b64":"ptlD7vlqgvVkBbnL7tfRxA56GyCPdAx82iExicoL6fIk1hDIr6M8WvJb+xHSStpy2DAGzcv5vNUMN8+wiPZJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b718ee4b06e58478fe7465227bdf09d758d240055cd19a6ae866f1522c3c6cf","last_reissued_at":"2026-06-03T01:05:55.372554Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:55.372554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Julie Mordacq, Steve Oudot, Vicky Kalogeiton","submitted_at":"2026-06-02T08:47:17Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a powerful paradigm for learning meaningful representations from unlabeled data. However, the standard protocol for evaluating these representations, linear probing, is computationally expensive, sensitive to hyperparameters, and provides limited insight into the geometric structure of the representation space. In this work, motivated by connections between neural network generalization and intrinsic dimension (ID) we propose IdEst, a method for estimating the ID of SSL representations via the Minimum Spanning Tree dimension estimator ($\\mathrm{dim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03338","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/2606.03338/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":"2606.03338","created_at":"2026-06-03T01:05:55.372612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03338v1","created_at":"2026-06-03T01:05:55.372612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03338","created_at":"2026-06-03T01:05:55.372612+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNYY5ZFQNZME","created_at":"2026-06-03T01:05:55.372612+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNYY5ZFQNZMEPD7H","created_at":"2026-06-03T01:05:55.372612+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNYY5ZFQ","created_at":"2026-06-03T01:05:55.372612+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/DNYY5ZFQNZMEPD7HIZJCPPPQTV","json":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV.json","graph_json":"https://pith.science/api/pith-number/DNYY5ZFQNZMEPD7HIZJCPPPQTV/graph.json","events_json":"https://pith.science/api/pith-number/DNYY5ZFQNZMEPD7HIZJCPPPQTV/events.json","paper":"https://pith.science/paper/DNYY5ZFQ"},"agent_actions":{"view_html":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV","download_json":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV.json","view_paper":"https://pith.science/paper/DNYY5ZFQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03338&json=true","fetch_graph":"https://pith.science/api/pith-number/DNYY5ZFQNZMEPD7HIZJCPPPQTV/graph.json","fetch_events":"https://pith.science/api/pith-number/DNYY5ZFQNZMEPD7HIZJCPPPQTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV/action/storage_attestation","attest_author":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV/action/author_attestation","sign_citation":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV/action/citation_signature","submit_replication":"https://pith.science/pith/DNYY5ZFQNZMEPD7HIZJCPPPQTV/action/replication_record"}},"created_at":"2026-06-03T01:05:55.372612+00:00","updated_at":"2026-06-03T01:05:55.372612+00:00"}