{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QY263XNY2ZIPXY7E3PHYYUENGJ","short_pith_number":"pith:QY263XNY","canonical_record":{"source":{"id":"2311.03449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-11-06T19:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"847a127cec56f2654012cd0877caab5f7f0cae4cf2d5d86fdc90357c1378d5ec","abstract_canon_sha256":"033d3756f147a8ee106b9ea8bf3c6a2bcca64a14ac0c0d823a768065191b0ab0"},"schema_version":"1.0"},"canonical_sha256":"8635edddb8d650fbe3e4dbcf8c508d3249407d08e893825d30a75278fb9b0547","source":{"kind":"arxiv","id":"2311.03449","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03449","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03449v1","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03449","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"QY263XNY2ZIP","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"pith_short_16","alias_value":"QY263XNY2ZIPXY7E","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"pith_short_8","alias_value":"QY263XNY","created_at":"2026-07-05T07:09:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QY263XNY2ZIPXY7E3PHYYUENGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.03449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-11-06T19:00:05Z","cross_cats_sorted":[],"title_canon_sha256":"847a127cec56f2654012cd0877caab5f7f0cae4cf2d5d86fdc90357c1378d5ec","abstract_canon_sha256":"033d3756f147a8ee106b9ea8bf3c6a2bcca64a14ac0c0d823a768065191b0ab0"},"schema_version":"1.0"},"canonical_sha256":"8635edddb8d650fbe3e4dbcf8c508d3249407d08e893825d30a75278fb9b0547","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:58.451839Z","signature_b64":"keIntHdKOMh+aPQtkYjuT4Vd6OC8cV4IKGbkqi+kNfcuquGtzJBrnujD5Opw7TGM2J1wlJHFqap5bObUFFXhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8635edddb8d650fbe3e4dbcf8c508d3249407d08e893825d30a75278fb9b0547","last_reissued_at":"2026-07-05T07:09:58.451263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:58.451263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.03449","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":"2026-07-05T07:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWvXyBKS4yHMWpVFWkm1aD1XiobkprbvDttNcWglLN38xgjv7yT93Z2SI74a2rE5PqrvMXxysvjkXeKixAX+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:07:07.235558Z"},"content_sha256":"6846ccd96578e3d8efec52f13d16815ab87ad455812429a79f0ed8b9b85b36e1","schema_version":"1.0","event_id":"sha256:6846ccd96578e3d8efec52f13d16815ab87ad455812429a79f0ed8b9b85b36e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QY263XNY2ZIPXY7E3PHYYUENGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Into the LAIONs Den: Investigating Hate in Multimodal Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Abeba Birhane, Alexandra Sasha Luccioni, Sang Han, Vinay Prabhu, Vishnu Naresh Boddeti","submitted_at":"2023-11-06T19:00:05Z","abstract_excerpt":"'Scale the model, scale the data, scale the compute' is the reigning sentiment in the world of generative AI today. While the impact of model scaling has been extensively studied, we are only beginning to scratch the surface of data scaling and its consequences. This is especially of critical importance in the context of vision-language datasets such as LAION. These datasets are continually growing in size and are built based on large-scale internet dumps such as the Common Crawl, which is known to have numerous drawbacks ranging from quality, legality, and content. The datasets then serve as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03449","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/2311.03449/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":"2026-07-05T07:09:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dJHUq2I9Ncd7PSh0DPmTa2fyeuekrlyDaOqhpQCNRxjnOnWsxzG+iipeQzDFXEwXZLKMa+5/UvzmszeWCBhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:07:07.236286Z"},"content_sha256":"94c47850f0ca961325984e9054c8d1fba6be3fb76723d1ea80e3dcf377889931","schema_version":"1.0","event_id":"sha256:94c47850f0ca961325984e9054c8d1fba6be3fb76723d1ea80e3dcf377889931"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QY263XNY2ZIPXY7E3PHYYUENGJ/bundle.json","state_url":"https://pith.science/pith/QY263XNY2ZIPXY7E3PHYYUENGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QY263XNY2ZIPXY7E3PHYYUENGJ/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":"2026-08-14T08:07:07Z","links":{"resolver":"https://pith.science/pith/QY263XNY2ZIPXY7E3PHYYUENGJ","bundle":"https://pith.science/pith/QY263XNY2ZIPXY7E3PHYYUENGJ/bundle.json","state":"https://pith.science/pith/QY263XNY2ZIPXY7E3PHYYUENGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QY263XNY2ZIPXY7E3PHYYUENGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QY263XNY2ZIPXY7E3PHYYUENGJ","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":"033d3756f147a8ee106b9ea8bf3c6a2bcca64a14ac0c0d823a768065191b0ab0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-11-06T19:00:05Z","title_canon_sha256":"847a127cec56f2654012cd0877caab5f7f0cae4cf2d5d86fdc90357c1378d5ec"},"schema_version":"1.0","source":{"id":"2311.03449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03449","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03449v1","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03449","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"pith_short_12","alias_value":"QY263XNY2ZIP","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"pith_short_16","alias_value":"QY263XNY2ZIPXY7E","created_at":"2026-07-05T07:09:58Z"},{"alias_kind":"pith_short_8","alias_value":"QY263XNY","created_at":"2026-07-05T07:09:58Z"}],"graph_snapshots":[{"event_id":"sha256:94c47850f0ca961325984e9054c8d1fba6be3fb76723d1ea80e3dcf377889931","target":"graph","created_at":"2026-07-05T07:09:58Z","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/2311.03449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"'Scale the model, scale the data, scale the compute' is the reigning sentiment in the world of generative AI today. While the impact of model scaling has been extensively studied, we are only beginning to scratch the surface of data scaling and its consequences. This is especially of critical importance in the context of vision-language datasets such as LAION. These datasets are continually growing in size and are built based on large-scale internet dumps such as the Common Crawl, which is known to have numerous drawbacks ranging from quality, legality, and content. The datasets then serve as ","authors_text":"Abeba Birhane, Alexandra Sasha Luccioni, Sang Han, Vinay Prabhu, Vishnu Naresh Boddeti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-11-06T19:00:05Z","title":"Into the LAIONs Den: Investigating Hate in Multimodal Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03449","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":"sha256:6846ccd96578e3d8efec52f13d16815ab87ad455812429a79f0ed8b9b85b36e1","target":"record","created_at":"2026-07-05T07:09:58Z","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":"033d3756f147a8ee106b9ea8bf3c6a2bcca64a14ac0c0d823a768065191b0ab0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-11-06T19:00:05Z","title_canon_sha256":"847a127cec56f2654012cd0877caab5f7f0cae4cf2d5d86fdc90357c1378d5ec"},"schema_version":"1.0","source":{"id":"2311.03449","kind":"arxiv","version":1}},"canonical_sha256":"8635edddb8d650fbe3e4dbcf8c508d3249407d08e893825d30a75278fb9b0547","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8635edddb8d650fbe3e4dbcf8c508d3249407d08e893825d30a75278fb9b0547","first_computed_at":"2026-07-05T07:09:58.451263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:58.451263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"keIntHdKOMh+aPQtkYjuT4Vd6OC8cV4IKGbkqi+kNfcuquGtzJBrnujD5Opw7TGM2J1wlJHFqap5bObUFFXhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:58.451839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.03449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6846ccd96578e3d8efec52f13d16815ab87ad455812429a79f0ed8b9b85b36e1","sha256:94c47850f0ca961325984e9054c8d1fba6be3fb76723d1ea80e3dcf377889931"],"state_sha256":"9e4a7fa44a4f347065ad01fc16f1e6a080ffe31f64a2508f0c346d45663d2b76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s7XzBOi4qzzIczD7OwZfSFIDUhUq5EXOSYNZQka3I9Ng3p/Zd8jG1pGNNiCUtr9crIaseByel4WUroUPQ80gBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:07:07.242577Z","bundle_sha256":"b9993893f534cd5115b18d63db8e0ce49375c83691ac1e2246f8f1dc0a04ff85"}}