{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6MJW5JH45SOCSDPOHUOVSVCVSD","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":"29d85cc09df685acf7a959fd38f4cca48226e4bc6c566b15e5d53aea4a6ad01d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T17:39:06Z","title_canon_sha256":"5eeeba5e2cc9976c95da6df964df8f8642bcb4341219f7d8b320d8f6826414bc"},"schema_version":"1.0","source":{"id":"2303.12733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.12733","created_at":"2026-07-05T05:53:44Z"},{"alias_kind":"arxiv_version","alias_value":"2303.12733v1","created_at":"2026-07-05T05:53:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12733","created_at":"2026-07-05T05:53:44Z"},{"alias_kind":"pith_short_12","alias_value":"6MJW5JH45SOC","created_at":"2026-07-05T05:53:44Z"},{"alias_kind":"pith_short_16","alias_value":"6MJW5JH45SOCSDPO","created_at":"2026-07-05T05:53:44Z"},{"alias_kind":"pith_short_8","alias_value":"6MJW5JH4","created_at":"2026-07-05T05:53:44Z"}],"graph_snapshots":[{"event_id":"sha256:17676644ceb1d36dd937037b6161d98ae23e1236bf9a5c48352a13c9ee7d3e42","target":"graph","created_at":"2026-07-05T05:53:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.12733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models, such as DALL-E, Midjourney, and Stable Diffusion, have societal implications that extend beyond the field of computer science. These models require large image databases like LAION-2B, which contain two billion images. At this scale, manual inspection is difficult and automated analysis is challenging. In addition, recent studies show that duplicated images pose copyright problems for models trained on LAION2B, which hinders its usability. This paper proposes an algorithmic chain that runs with modest compute, that compresses CLIP features to enable efficient duplicate detec","authors_text":"Frederic Jurie, Julien Rabin, Loic Simon, Ryan Webster","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T17:39:06Z","title":"On the De-duplication of LAION-2B"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12733","kind":"arxiv","version":1},"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:e1ec8a3b8ec0d9cfd1d8302263e1ba8e5ce93c67a105cbca88a6501fefa1f14e","target":"record","created_at":"2026-07-05T05:53:44Z","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":"29d85cc09df685acf7a959fd38f4cca48226e4bc6c566b15e5d53aea4a6ad01d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T17:39:06Z","title_canon_sha256":"5eeeba5e2cc9976c95da6df964df8f8642bcb4341219f7d8b320d8f6826414bc"},"schema_version":"1.0","source":{"id":"2303.12733","kind":"arxiv","version":1}},"canonical_sha256":"f3136ea4fcec9c290dee3d1d59545590d5c57364083cb90eaa9988ce5c76dd88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3136ea4fcec9c290dee3d1d59545590d5c57364083cb90eaa9988ce5c76dd88","first_computed_at":"2026-07-05T05:53:44.535418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:53:44.535418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jzQJqXlNYKXG8iswpa3WkdnuE9utzswRCbRPZ6zIFkp147ufWfs0DjJQQ653FdM2VnditzDw71axIFukw8sJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:53:44.535756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.12733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1ec8a3b8ec0d9cfd1d8302263e1ba8e5ce93c67a105cbca88a6501fefa1f14e","sha256:17676644ceb1d36dd937037b6161d98ae23e1236bf9a5c48352a13c9ee7d3e42"],"state_sha256":"9ac079f17d3edae5ef8a09bb884de5d6f80f8d1860e65f4604ae2a9e878bd879"}