{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ML5OMZWESOCVSFLZM4JTVKZ5RW","short_pith_number":"pith:ML5OMZWE","schema_version":"1.0","canonical_sha256":"62fae666c4938559157967133aab3d8d96f8e89823b53ddc8893435e21092304","source":{"kind":"arxiv","id":"2403.00642","version":2},"attestation_state":"computed","paper":{"title":"Rethinking The Uniformity Metric in Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Benyou Wang, Jian Li, Qiang Sun, Xianghong Fang","submitted_at":"2024-03-01T16:22:05Z","abstract_excerpt":"Uniformity plays an important role in evaluating learned representations, providing insights into self-supervised learning. In our quest for effective uniformity metrics, we pinpoint four principled properties that such metrics should possess. Namely, an effective uniformity metric should remain invariant to instance permutations and sample replications while accurately capturing feature redundancy and dimensional collapse. Surprisingly, we find that the uniformity metric proposed by \\citet{Wang2020UnderstandingCR} fails to satisfy the majority of these properties. Specifically, their metric i"},"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":"2403.00642","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T16:22:05Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"340a07fb886d504e0d66463abcddec0ee6caa66f155a22d1c35239661cafdae2","abstract_canon_sha256":"f3bfe48671d7415919bee03d8603147487d6fd51f181d75423a2bb50d0235bab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:30.376039Z","signature_b64":"9J5zMfR2eem4bs4r0xfnTTgu7vX62SAKWpv8KE/yt/KT7m/ECh49x9UJMVsNxeS5uqUMA76Qbia4C5RIyjbPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62fae666c4938559157967133aab3d8d96f8e89823b53ddc8893435e21092304","last_reissued_at":"2026-07-05T08:12:30.375586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:30.375586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking The Uniformity Metric in Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Benyou Wang, Jian Li, Qiang Sun, Xianghong Fang","submitted_at":"2024-03-01T16:22:05Z","abstract_excerpt":"Uniformity plays an important role in evaluating learned representations, providing insights into self-supervised learning. In our quest for effective uniformity metrics, we pinpoint four principled properties that such metrics should possess. Namely, an effective uniformity metric should remain invariant to instance permutations and sample replications while accurately capturing feature redundancy and dimensional collapse. Surprisingly, we find that the uniformity metric proposed by \\citet{Wang2020UnderstandingCR} fails to satisfy the majority of these properties. Specifically, their metric i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00642","kind":"arxiv","version":2},"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/2403.00642/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":"2403.00642","created_at":"2026-07-05T08:12:30.375642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00642v2","created_at":"2026-07-05T08:12:30.375642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00642","created_at":"2026-07-05T08:12:30.375642+00:00"},{"alias_kind":"pith_short_12","alias_value":"ML5OMZWESOCV","created_at":"2026-07-05T08:12:30.375642+00:00"},{"alias_kind":"pith_short_16","alias_value":"ML5OMZWESOCVSFLZ","created_at":"2026-07-05T08:12:30.375642+00:00"},{"alias_kind":"pith_short_8","alias_value":"ML5OMZWE","created_at":"2026-07-05T08:12:30.375642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02929","citing_title":"OBSER: Object-Based Sub-Environment Recognition for Zero-Shot Environmental Inference","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW","json":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW.json","graph_json":"https://pith.science/api/pith-number/ML5OMZWESOCVSFLZM4JTVKZ5RW/graph.json","events_json":"https://pith.science/api/pith-number/ML5OMZWESOCVSFLZM4JTVKZ5RW/events.json","paper":"https://pith.science/paper/ML5OMZWE"},"agent_actions":{"view_html":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW","download_json":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW.json","view_paper":"https://pith.science/paper/ML5OMZWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00642&json=true","fetch_graph":"https://pith.science/api/pith-number/ML5OMZWESOCVSFLZM4JTVKZ5RW/graph.json","fetch_events":"https://pith.science/api/pith-number/ML5OMZWESOCVSFLZM4JTVKZ5RW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW/action/storage_attestation","attest_author":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW/action/author_attestation","sign_citation":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW/action/citation_signature","submit_replication":"https://pith.science/pith/ML5OMZWESOCVSFLZM4JTVKZ5RW/action/replication_record"}},"created_at":"2026-07-05T08:12:30.375642+00:00","updated_at":"2026-07-05T08:12:30.375642+00:00"}