{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LHZQWOZDUB3SS432YLHTC4A7UZ","short_pith_number":"pith:LHZQWOZD","canonical_record":{"source":{"id":"2110.01963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2021-10-05T11:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"b7f0ec8645ae810dd6ebcbaf4fbe4b7c7f6eccf85335ae8bdf58df572e683613","abstract_canon_sha256":"ff85fe5890dbf43eafd527f0ef3851b89dbb868c322a1e19ae8cbdb8706eee1f"},"schema_version":"1.0"},"canonical_sha256":"59f30b3b23a07729737ac2cf31701fa64d1806eec3169349b0e22d0d062df837","source":{"kind":"arxiv","id":"2110.01963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01963","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01963v1","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01963","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"LHZQWOZDUB3S","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"LHZQWOZDUB3SS432","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"LHZQWOZD","created_at":"2026-07-05T03:20:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LHZQWOZDUB3SS432YLHTC4A7UZ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.01963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2021-10-05T11:47:27Z","cross_cats_sorted":[],"title_canon_sha256":"b7f0ec8645ae810dd6ebcbaf4fbe4b7c7f6eccf85335ae8bdf58df572e683613","abstract_canon_sha256":"ff85fe5890dbf43eafd527f0ef3851b89dbb868c322a1e19ae8cbdb8706eee1f"},"schema_version":"1.0"},"canonical_sha256":"59f30b3b23a07729737ac2cf31701fa64d1806eec3169349b0e22d0d062df837","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:08.207590Z","signature_b64":"cTmTFOPEG260tFoj3vwWcOgpVD384drNaB9lFBBlgGhZdZLl47i57YrbMEXlCpl3r20S5kmynPiK11kMDdDyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59f30b3b23a07729737ac2cf31701fa64d1806eec3169349b0e22d0d062df837","last_reissued_at":"2026-07-05T03:20:08.207146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:08.207146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.01963","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":"2026-07-05T03:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1DxFYv9sFYt7nL86mSnF8PLLN52Wu326NWICajmb/sIV+ZU/tapTNKa/3XsmDuJPN6uKhKLw+DZ48C2adF84Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:02:02.386806Z"},"content_sha256":"bbf2b8f527ad0d0e3a39da5c8b48034f6b4b204857c993fafd3d79ddcd040639","schema_version":"1.0","event_id":"sha256:bbf2b8f527ad0d0e3a39da5c8b48034f6b4b204857c993fafd3d79ddcd040639"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LHZQWOZDUB3SS432YLHTC4A7UZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Abeba Birhane, Emmanuel Kahembwe, Vinay Uday Prabhu","submitted_at":"2021-10-05T11:47:27Z","abstract_excerpt":"We have now entered the era of trillion parameter machine learning models trained on billion-sized datasets scraped from the internet. The rise of these gargantuan datasets has given rise to formidable bodies of critical work that has called for caution while generating these large datasets. These address concerns surrounding the dubious curation practices used to generate these datasets, the sordid quality of alt-text data available on the world wide web, the problematic content of the CommonCrawl dataset often used as a source for training large language models, and the entrenched biases in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01963","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/2110.01963/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":"2026-07-05T03:20:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ot0XjvbWfOA7XL8uuBKNajI1RpEaZHakcPwjJUAKD/WxB6X5CiukIdbfWLJEc0Nfq/lFfIwKm+WXtJ2edpkXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:02:02.387102Z"},"content_sha256":"64e1d815a508b5280abc0f5da26d1be1d874f37bb0b8b811510b6c5902d5d891","schema_version":"1.0","event_id":"sha256:64e1d815a508b5280abc0f5da26d1be1d874f37bb0b8b811510b6c5902d5d891"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LHZQWOZDUB3SS432YLHTC4A7UZ/bundle.json","state_url":"https://pith.science/pith/LHZQWOZDUB3SS432YLHTC4A7UZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LHZQWOZDUB3SS432YLHTC4A7UZ/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":"2026-08-05T18:02:02Z","links":{"resolver":"https://pith.science/pith/LHZQWOZDUB3SS432YLHTC4A7UZ","bundle":"https://pith.science/pith/LHZQWOZDUB3SS432YLHTC4A7UZ/bundle.json","state":"https://pith.science/pith/LHZQWOZDUB3SS432YLHTC4A7UZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LHZQWOZDUB3SS432YLHTC4A7UZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LHZQWOZDUB3SS432YLHTC4A7UZ","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":"ff85fe5890dbf43eafd527f0ef3851b89dbb868c322a1e19ae8cbdb8706eee1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2021-10-05T11:47:27Z","title_canon_sha256":"b7f0ec8645ae810dd6ebcbaf4fbe4b7c7f6eccf85335ae8bdf58df572e683613"},"schema_version":"1.0","source":{"id":"2110.01963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01963","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01963v1","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01963","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"pith_short_12","alias_value":"LHZQWOZDUB3S","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"pith_short_16","alias_value":"LHZQWOZDUB3SS432","created_at":"2026-07-05T03:20:08Z"},{"alias_kind":"pith_short_8","alias_value":"LHZQWOZD","created_at":"2026-07-05T03:20:08Z"}],"graph_snapshots":[{"event_id":"sha256:64e1d815a508b5280abc0f5da26d1be1d874f37bb0b8b811510b6c5902d5d891","target":"graph","created_at":"2026-07-05T03:20:08Z","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/2110.01963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We have now entered the era of trillion parameter machine learning models trained on billion-sized datasets scraped from the internet. The rise of these gargantuan datasets has given rise to formidable bodies of critical work that has called for caution while generating these large datasets. These address concerns surrounding the dubious curation practices used to generate these datasets, the sordid quality of alt-text data available on the world wide web, the problematic content of the CommonCrawl dataset often used as a source for training large language models, and the entrenched biases in ","authors_text":"Abeba Birhane, Emmanuel Kahembwe, Vinay Uday Prabhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2021-10-05T11:47:27Z","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01963","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:bbf2b8f527ad0d0e3a39da5c8b48034f6b4b204857c993fafd3d79ddcd040639","target":"record","created_at":"2026-07-05T03:20:08Z","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":"ff85fe5890dbf43eafd527f0ef3851b89dbb868c322a1e19ae8cbdb8706eee1f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2021-10-05T11:47:27Z","title_canon_sha256":"b7f0ec8645ae810dd6ebcbaf4fbe4b7c7f6eccf85335ae8bdf58df572e683613"},"schema_version":"1.0","source":{"id":"2110.01963","kind":"arxiv","version":1}},"canonical_sha256":"59f30b3b23a07729737ac2cf31701fa64d1806eec3169349b0e22d0d062df837","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59f30b3b23a07729737ac2cf31701fa64d1806eec3169349b0e22d0d062df837","first_computed_at":"2026-07-05T03:20:08.207146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:08.207146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cTmTFOPEG260tFoj3vwWcOgpVD384drNaB9lFBBlgGhZdZLl47i57YrbMEXlCpl3r20S5kmynPiK11kMDdDyCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:08.207590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.01963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbf2b8f527ad0d0e3a39da5c8b48034f6b4b204857c993fafd3d79ddcd040639","sha256:64e1d815a508b5280abc0f5da26d1be1d874f37bb0b8b811510b6c5902d5d891"],"state_sha256":"8519ce887d94276cbd9c399c2e2f0ce68520b454590671627e17bbd35cab017e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d7xx7aiHMeTPRReNLGb5MwvuBVc2Q3dWhCEsT2lb2CY/rHfGjyATMggjH7+sMcVI9lTGtpwxqZM4+PlWVhiICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:02:02.389957Z","bundle_sha256":"7400d1967a63f44ec8cf3e868760c77c12fec2d040c294335cd09c86d9cbbe09"}}