{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3CRBS6AQJ54VNXLN7WLPSUDTZX","short_pith_number":"pith:3CRBS6AQ","canonical_record":{"source":{"id":"2105.02732","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-06T14:49:43Z","cross_cats_sorted":[],"title_canon_sha256":"3294189053f6bd621d83fa4c53a5a15a769bc45d56fb41fa25666ec5144225e0","abstract_canon_sha256":"50e6982c1b2ac71cc80e07a30f2fb8886fc2d3f26eabad098ef3abea5bd3b9b3"},"schema_version":"1.0"},"canonical_sha256":"d8a21978104f7956dd6dfd96f95073cdd0eeeb6285777c7ad6ef8df52eef3c34","source":{"kind":"arxiv","id":"2105.02732","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.02732","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"2105.02732v3","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.02732","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"3CRBS6AQJ54V","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"pith_short_16","alias_value":"3CRBS6AQJ54VNXLN","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"pith_short_8","alias_value":"3CRBS6AQ","created_at":"2026-07-05T02:44:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3CRBS6AQJ54VNXLN7WLPSUDTZX","target":"record","payload":{"canonical_record":{"source":{"id":"2105.02732","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-06T14:49:43Z","cross_cats_sorted":[],"title_canon_sha256":"3294189053f6bd621d83fa4c53a5a15a769bc45d56fb41fa25666ec5144225e0","abstract_canon_sha256":"50e6982c1b2ac71cc80e07a30f2fb8886fc2d3f26eabad098ef3abea5bd3b9b3"},"schema_version":"1.0"},"canonical_sha256":"d8a21978104f7956dd6dfd96f95073cdd0eeeb6285777c7ad6ef8df52eef3c34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:58.754643Z","signature_b64":"2HYbJvbhLxmVOOriJpJUZXa7mIztrfnWSPIsQmxyDKUMowrXlvagdM6b7fJ4OUnvOysJzeNCzxnFkvRAjiecDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8a21978104f7956dd6dfd96f95073cdd0eeeb6285777c7ad6ef8df52eef3c34","last_reissued_at":"2026-07-05T02:44:58.754160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:58.754160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.02732","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8oRaGinxoMilOVC6PM9yc20z1FRJCMztAcNUDKCigDa6H6NQmFGwqqUyHZxO7UiQAevuHSCFRabWedzBfzrYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:52:08.298770Z"},"content_sha256":"405f2a610ae43452fcda074443bc07ccce3456b5fb1d8270847996e083268c54","schema_version":"1.0","event_id":"sha256:405f2a610ae43452fcda074443bc07ccce3456b5fb1d8270847996e083268c54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3CRBS6AQJ54VNXLN7WLPSUDTZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Sasha Luccioni, Joseph D. Viviano","submitted_at":"2021-05-06T14:49:43Z","abstract_excerpt":"Whereas much of the success of the current generation of neural language models has been driven by increasingly large training corpora, relatively little research has been dedicated to analyzing these massive sources of textual data. In this exploratory analysis, we delve deeper into the Common Crawl, a colossal web corpus that is extensively used for training language models. We find that it contains a significant amount of undesirable content, including hate speech and sexually explicit content, even after filtering procedures. We discuss the potential impacts of this content on language mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.02732","kind":"arxiv","version":3},"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/2105.02732/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":"2026-07-05T02:44:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vibrdyG7w1hivqtjETme04/M2WMzvMahuwf1+0lwd+/+upYd4eIMdP1jUXJAtNMvJIU3wMHCb4CmrVRB6wFlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:52:08.299249Z"},"content_sha256":"e7e317fd8eca06b1396b84e4b22d1f5de9ffea7e718d56451516b9b0179f2405","schema_version":"1.0","event_id":"sha256:e7e317fd8eca06b1396b84e4b22d1f5de9ffea7e718d56451516b9b0179f2405"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CRBS6AQJ54VNXLN7WLPSUDTZX/bundle.json","state_url":"https://pith.science/pith/3CRBS6AQJ54VNXLN7WLPSUDTZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CRBS6AQJ54VNXLN7WLPSUDTZX/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":"2026-08-19T15:52:08Z","links":{"resolver":"https://pith.science/pith/3CRBS6AQJ54VNXLN7WLPSUDTZX","bundle":"https://pith.science/pith/3CRBS6AQJ54VNXLN7WLPSUDTZX/bundle.json","state":"https://pith.science/pith/3CRBS6AQJ54VNXLN7WLPSUDTZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CRBS6AQJ54VNXLN7WLPSUDTZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3CRBS6AQJ54VNXLN7WLPSUDTZX","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":"50e6982c1b2ac71cc80e07a30f2fb8886fc2d3f26eabad098ef3abea5bd3b9b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-06T14:49:43Z","title_canon_sha256":"3294189053f6bd621d83fa4c53a5a15a769bc45d56fb41fa25666ec5144225e0"},"schema_version":"1.0","source":{"id":"2105.02732","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.02732","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"arxiv_version","alias_value":"2105.02732v3","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.02732","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"pith_short_12","alias_value":"3CRBS6AQJ54V","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"pith_short_16","alias_value":"3CRBS6AQJ54VNXLN","created_at":"2026-07-05T02:44:58Z"},{"alias_kind":"pith_short_8","alias_value":"3CRBS6AQ","created_at":"2026-07-05T02:44:58Z"}],"graph_snapshots":[{"event_id":"sha256:e7e317fd8eca06b1396b84e4b22d1f5de9ffea7e718d56451516b9b0179f2405","target":"graph","created_at":"2026-07-05T02:44:58Z","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/2105.02732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Whereas much of the success of the current generation of neural language models has been driven by increasingly large training corpora, relatively little research has been dedicated to analyzing these massive sources of textual data. In this exploratory analysis, we delve deeper into the Common Crawl, a colossal web corpus that is extensively used for training language models. We find that it contains a significant amount of undesirable content, including hate speech and sexually explicit content, even after filtering procedures. We discuss the potential impacts of this content on language mod","authors_text":"Alexandra Sasha Luccioni, Joseph D. Viviano","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-06T14:49:43Z","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.02732","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":"sha256:405f2a610ae43452fcda074443bc07ccce3456b5fb1d8270847996e083268c54","target":"record","created_at":"2026-07-05T02:44:58Z","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":"50e6982c1b2ac71cc80e07a30f2fb8886fc2d3f26eabad098ef3abea5bd3b9b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-06T14:49:43Z","title_canon_sha256":"3294189053f6bd621d83fa4c53a5a15a769bc45d56fb41fa25666ec5144225e0"},"schema_version":"1.0","source":{"id":"2105.02732","kind":"arxiv","version":3}},"canonical_sha256":"d8a21978104f7956dd6dfd96f95073cdd0eeeb6285777c7ad6ef8df52eef3c34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8a21978104f7956dd6dfd96f95073cdd0eeeb6285777c7ad6ef8df52eef3c34","first_computed_at":"2026-07-05T02:44:58.754160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:58.754160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2HYbJvbhLxmVOOriJpJUZXa7mIztrfnWSPIsQmxyDKUMowrXlvagdM6b7fJ4OUnvOysJzeNCzxnFkvRAjiecDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:58.754643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.02732","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:405f2a610ae43452fcda074443bc07ccce3456b5fb1d8270847996e083268c54","sha256:e7e317fd8eca06b1396b84e4b22d1f5de9ffea7e718d56451516b9b0179f2405"],"state_sha256":"803850706faa97f71f8487a923ad869cd0b646ea628f3e2f94aa3614ac6a70d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rm2XbaGNuGF/2V5XDwpy2pP7rBx9PFHXEvX9d3CqtuN/sNstGc1UkZnBsoQ+bkeFo3Y5MckUtaSoal2jPFCbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:52:08.302906Z","bundle_sha256":"62465a67bdeac15d010fe099980ff0f1d3acb98fb31e61a360552272e4a60b13"}}