{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6MJW5JH45SOCSDPOHUOVSVCVSD","short_pith_number":"pith:6MJW5JH4","canonical_record":{"source":{"id":"2303.12733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T17:39:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5eeeba5e2cc9976c95da6df964df8f8642bcb4341219f7d8b320d8f6826414bc","abstract_canon_sha256":"29d85cc09df685acf7a959fd38f4cca48226e4bc6c566b15e5d53aea4a6ad01d"},"schema_version":"1.0"},"canonical_sha256":"f3136ea4fcec9c290dee3d1d59545590d5c57364083cb90eaa9988ce5c76dd88","source":{"kind":"arxiv","id":"2303.12733","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6MJW5JH45SOCSDPOHUOVSVCVSD","target":"record","payload":{"canonical_record":{"source":{"id":"2303.12733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T17:39:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5eeeba5e2cc9976c95da6df964df8f8642bcb4341219f7d8b320d8f6826414bc","abstract_canon_sha256":"29d85cc09df685acf7a959fd38f4cca48226e4bc6c566b15e5d53aea4a6ad01d"},"schema_version":"1.0"},"canonical_sha256":"f3136ea4fcec9c290dee3d1d59545590d5c57364083cb90eaa9988ce5c76dd88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:44.535756Z","signature_b64":"jzQJqXlNYKXG8iswpa3WkdnuE9utzswRCbRPZ6zIFkp147ufWfs0DjJQQ653FdM2VnditzDw71axIFukw8sJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3136ea4fcec9c290dee3d1d59545590d5c57364083cb90eaa9988ce5c76dd88","last_reissued_at":"2026-07-05T05:53:44.535418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:44.535418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.12733","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:53:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HKdCshn+1PRhtRelSd4VVTyeeftaucon8WeN6uFvPGWzjlt/oAfcO+PmrlKt0HjOOFMt2QckBuuWh8rAg1vwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:37:15.507897Z"},"content_sha256":"e1ec8a3b8ec0d9cfd1d8302263e1ba8e5ce93c67a105cbca88a6501fefa1f14e","schema_version":"1.0","event_id":"sha256:e1ec8a3b8ec0d9cfd1d8302263e1ba8e5ce93c67a105cbca88a6501fefa1f14e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6MJW5JH45SOCSDPOHUOVSVCVSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the De-duplication of LAION-2B","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Frederic Jurie, Julien Rabin, Loic Simon, Ryan Webster","submitted_at":"2023-03-17T17:39:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12733","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/2303.12733/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:53:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9gUwYnCpKsOrFrZ31BfP0N6AU/1jwXtzSfAPiSITnVpEVS42plkX8NTYf3yPai2mM/t1XtM5OWD50uwFK/5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:37:15.508397Z"},"content_sha256":"17676644ceb1d36dd937037b6161d98ae23e1236bf9a5c48352a13c9ee7d3e42","schema_version":"1.0","event_id":"sha256:17676644ceb1d36dd937037b6161d98ae23e1236bf9a5c48352a13c9ee7d3e42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6MJW5JH45SOCSDPOHUOVSVCVSD/bundle.json","state_url":"https://pith.science/pith/6MJW5JH45SOCSDPOHUOVSVCVSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6MJW5JH45SOCSDPOHUOVSVCVSD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T00:37:15Z","links":{"resolver":"https://pith.science/pith/6MJW5JH45SOCSDPOHUOVSVCVSD","bundle":"https://pith.science/pith/6MJW5JH45SOCSDPOHUOVSVCVSD/bundle.json","state":"https://pith.science/pith/6MJW5JH45SOCSDPOHUOVSVCVSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6MJW5JH45SOCSDPOHUOVSVCVSD/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hP7oYzj4CeJy8cdrfpbCoBoaPDjb0Q/BGsfXuLS0sTKlqJ8+LXWoz/LYPED0SQqUiDKGhKuhcJc/XpJLQzAIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:37:15.511704Z","bundle_sha256":"d6e50549b7e5547fa84aa6638151fcc33f7d6bb10c0d660cef72b1e739656ed1"}}