{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2PPZXT4GRVWBWJLEC36THHXWN7","short_pith_number":"pith:2PPZXT4G","schema_version":"1.0","canonical_sha256":"d3df9bcf868d6c1b256416fd339ef66fcb1cef619e2709db68065943c0cb297e","source":{"kind":"arxiv","id":"1911.05371","version":3},"attestation_state":"computed","paper":{"title":"Self-labelling via simultaneous clustering and representation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Christian Rupprecht, Yuki Markus Asano","submitted_at":"2019-11-13T09:47:49Z","abstract_excerpt":"Combining clustering and representation learning is one of the most promising approaches for unsupervised learning of deep neural networks. However, doing so naively leads to ill posed learning problems with degenerate solutions. In this paper, we propose a novel and principled learning formulation that addresses these issues. The method is obtained by maximizing the information between labels and input data indices. We show that this criterion extends standard crossentropy minimization to an optimal transport problem, which we solve efficiently for millions of input images and thousands of la"},"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":"1911.05371","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-13T09:47:49Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"8e8a75918ff17e28eb6f7c160dc0c0f88af4c0bef9fe3db569f09a4210413e8e","abstract_canon_sha256":"18fefa66767d88d601f855400c537caa774dd6de3064d1404f25b8f63d74dc16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:21.507384Z","signature_b64":"bLrxkC2ANGV5hJCVreUYaOy0luDmCBoW1cgcp7XKf/8KT9GtoPkZmrrGAi4hYYOWB/RUfj5NIaeSv8degyVaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3df9bcf868d6c1b256416fd339ef66fcb1cef619e2709db68065943c0cb297e","last_reissued_at":"2026-07-05T00:42:21.506832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:21.506832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-labelling via simultaneous clustering and representation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Christian Rupprecht, Yuki Markus Asano","submitted_at":"2019-11-13T09:47:49Z","abstract_excerpt":"Combining clustering and representation learning is one of the most promising approaches for unsupervised learning of deep neural networks. However, doing so naively leads to ill posed learning problems with degenerate solutions. In this paper, we propose a novel and principled learning formulation that addresses these issues. The method is obtained by maximizing the information between labels and input data indices. We show that this criterion extends standard crossentropy minimization to an optimal transport problem, which we solve efficiently for millions of input images and thousands of la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05371","kind":"arxiv","version":3},"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/1911.05371/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":"1911.05371","created_at":"2026-07-05T00:42:21.506890+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05371v3","created_at":"2026-07-05T00:42:21.506890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05371","created_at":"2026-07-05T00:42:21.506890+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PPZXT4GRVWB","created_at":"2026-07-05T00:42:21.506890+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PPZXT4GRVWBWJLE","created_at":"2026-07-05T00:42:21.506890+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PPZXT4G","created_at":"2026-07-05T00:42:21.506890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.08471","citing_title":"Revisiting Feature Prediction for Learning Visual Representations from Video","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09963","citing_title":"Learning to Perceive \"Where\": Spatial Pretext Tasks for Robust Self-Supervised Learning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20392","citing_title":"Self-supervised pretraining for an iterative image size agnostic vision transformer","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7","json":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7.json","graph_json":"https://pith.science/api/pith-number/2PPZXT4GRVWBWJLEC36THHXWN7/graph.json","events_json":"https://pith.science/api/pith-number/2PPZXT4GRVWBWJLEC36THHXWN7/events.json","paper":"https://pith.science/paper/2PPZXT4G"},"agent_actions":{"view_html":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7","download_json":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7.json","view_paper":"https://pith.science/paper/2PPZXT4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05371&json=true","fetch_graph":"https://pith.science/api/pith-number/2PPZXT4GRVWBWJLEC36THHXWN7/graph.json","fetch_events":"https://pith.science/api/pith-number/2PPZXT4GRVWBWJLEC36THHXWN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7/action/storage_attestation","attest_author":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7/action/author_attestation","sign_citation":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7/action/citation_signature","submit_replication":"https://pith.science/pith/2PPZXT4GRVWBWJLEC36THHXWN7/action/replication_record"}},"created_at":"2026-07-05T00:42:21.506890+00:00","updated_at":"2026-07-05T00:42:21.506890+00:00"}