{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:O6FNK2VNMHKVLLGYFOPVUF6VGL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7cec0d4952d6a84527c52df0fb9342f92fb46237525aeef199af03ff5095044a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T17:53:24Z","title_canon_sha256":"0ed5dddaabe391706c3b85fa3d85c958f7f436db834195e6cc1b6b279d95d504"},"schema_version":"1.0","source":{"id":"2303.09540","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09540","created_at":"2026-05-18T02:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09540v3","created_at":"2026-05-18T02:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09540","created_at":"2026-05-18T02:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"O6FNK2VNMHKV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"O6FNK2VNMHKVLLGY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"O6FNK2VN","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0d3bf307625f6103de769f6b05f5d703b10bba473647bb8921d60ce432640ce7","target":"graph","created_at":"2026-05-18T02:38:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Progress in machine learning has been driven in large part by massive increases in data. However, large web-scale datasets such as LAION are largely uncurated beyond searches for exact duplicates, potentially leaving much redundancy. Here, we introduce SemDeDup, a method which leverages embeddings from pre-trained models to identify and remove semantic duplicates: data pairs which are semantically similar, but not exactly identical. Removing semantic duplicates preserves performance and speeds up learning. Analyzing a subset of LAION, we show that SemDeDup can remove 50% of the data with minim","authors_text":"Amro Abbas, Ari S. Morcos, D\\'aniel Simig, Kushal Tirumala, Surya Ganguli","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T17:53:24Z","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09540","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:272dff3b68417ae597aa0d09ac7a280af8e246fb439009c9c9336283568ce61e","target":"record","created_at":"2026-05-18T02:38:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7cec0d4952d6a84527c52df0fb9342f92fb46237525aeef199af03ff5095044a","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T17:53:24Z","title_canon_sha256":"0ed5dddaabe391706c3b85fa3d85c958f7f436db834195e6cc1b6b279d95d504"},"schema_version":"1.0","source":{"id":"2303.09540","kind":"arxiv","version":3}},"canonical_sha256":"778ad56aad61d555acd82b9f5a17d532eb3abffd7a1bbdf9d1edb37912796d1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"778ad56aad61d555acd82b9f5a17d532eb3abffd7a1bbdf9d1edb37912796d1e","first_computed_at":"2026-05-18T02:38:34.943495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:38:34.943495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/62vzBQ8OTMoQiVQheAuz+QTlE3bnrLsqHY04owsrV0SYvkZkwJI2oWWd2b1UliOE9bULKee1yBHfZVdegicCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:38:34.944125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09540","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:272dff3b68417ae597aa0d09ac7a280af8e246fb439009c9c9336283568ce61e","sha256:0d3bf307625f6103de769f6b05f5d703b10bba473647bb8921d60ce432640ce7"],"state_sha256":"6fa705fea62767fb0e7c4a91b6065b7da8b397e788316522c6d46938c7423fc0"}