{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IATS3PHB42PD5EAJKFBESLQGYA","short_pith_number":"pith:IATS3PHB","schema_version":"1.0","canonical_sha256":"40272dbce1e69e3e90095142492e06c0088078d47fcbfa3e221548a55d3f99ba","source":{"kind":"arxiv","id":"2312.04000","version":1},"attestation_state":"computed","paper":{"title":"LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chen Huang, Etai Littwin, Hanlin Goh, Joshua M. Susskind, Laurent Dinh, Omid Saremi, Preetum Nakkiran, Vimal Thilak","submitted_at":"2023-12-07T02:31:28Z","abstract_excerpt":"Joint embedding (JE) architectures have emerged as a promising avenue for acquiring transferable data representations. A key obstacle to using JE methods, however, is the inherent challenge of evaluating learned representations without access to a downstream task, and an annotated dataset. Without efficient and reliable evaluation, it is difficult to iterate on architectural and training choices for JE methods. In this paper, we introduce LiDAR (Linear Discriminant Analysis Rank), a metric designed to measure the quality of representations within JE architectures. Our metric addresses several "},"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":"2312.04000","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T02:31:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7191a35eed3f62044185a6fa47bf195f2cc3e62fe02fb76c4e824e954783758d","abstract_canon_sha256":"2b238bde1911b23790845020984917fbc8c79ec31abd082a73f869c879fcae55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:18.108637Z","signature_b64":"W1q+oywcZ3qATIG4Db0CoUbj1R8TyAUejfTVSCj4JNIl8W+edJNX3e3TKqYZ3w41q2i2TxyGQr58pUVXwuS5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40272dbce1e69e3e90095142492e06c0088078d47fcbfa3e221548a55d3f99ba","last_reissued_at":"2026-07-05T07:21:18.108127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:18.108127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chen Huang, Etai Littwin, Hanlin Goh, Joshua M. Susskind, Laurent Dinh, Omid Saremi, Preetum Nakkiran, Vimal Thilak","submitted_at":"2023-12-07T02:31:28Z","abstract_excerpt":"Joint embedding (JE) architectures have emerged as a promising avenue for acquiring transferable data representations. A key obstacle to using JE methods, however, is the inherent challenge of evaluating learned representations without access to a downstream task, and an annotated dataset. Without efficient and reliable evaluation, it is difficult to iterate on architectural and training choices for JE methods. In this paper, we introduce LiDAR (Linear Discriminant Analysis Rank), a metric designed to measure the quality of representations within JE architectures. Our metric addresses several "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04000","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/2312.04000/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":"2312.04000","created_at":"2026-07-05T07:21:18.108186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04000v1","created_at":"2026-07-05T07:21:18.108186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04000","created_at":"2026-07-05T07:21:18.108186+00:00"},{"alias_kind":"pith_short_12","alias_value":"IATS3PHB42PD","created_at":"2026-07-05T07:21:18.108186+00:00"},{"alias_kind":"pith_short_16","alias_value":"IATS3PHB42PD5EAJ","created_at":"2026-07-05T07:21:18.108186+00:00"},{"alias_kind":"pith_short_8","alias_value":"IATS3PHB","created_at":"2026-07-05T07:21:18.108186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06392","citing_title":"InsideSSL: Understanding Self-Supervised Speech Representations using a Model-Centric Perspective","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21590","citing_title":"Radial Basis Function Networks as Projection Heads in Self-Supervised Learning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08544","citing_title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA","json":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA.json","graph_json":"https://pith.science/api/pith-number/IATS3PHB42PD5EAJKFBESLQGYA/graph.json","events_json":"https://pith.science/api/pith-number/IATS3PHB42PD5EAJKFBESLQGYA/events.json","paper":"https://pith.science/paper/IATS3PHB"},"agent_actions":{"view_html":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA","download_json":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA.json","view_paper":"https://pith.science/paper/IATS3PHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04000&json=true","fetch_graph":"https://pith.science/api/pith-number/IATS3PHB42PD5EAJKFBESLQGYA/graph.json","fetch_events":"https://pith.science/api/pith-number/IATS3PHB42PD5EAJKFBESLQGYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA/action/storage_attestation","attest_author":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA/action/author_attestation","sign_citation":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA/action/citation_signature","submit_replication":"https://pith.science/pith/IATS3PHB42PD5EAJKFBESLQGYA/action/replication_record"}},"created_at":"2026-07-05T07:21:18.108186+00:00","updated_at":"2026-07-05T07:21:18.108186+00:00"}