{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:K363A5CN2RUT3KUZ4NPXXTKDNV","short_pith_number":"pith:K363A5CN","canonical_record":{"source":{"id":"2104.08758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T07:42:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db0c0b1292077a2c325bde18d8fe41295efed59245e5abecaebd9842cb829b2f","abstract_canon_sha256":"2852274258dec02b23e4531ae87f38bba236576216392db92852df7e466936dc"},"schema_version":"1.0"},"canonical_sha256":"56fdb0744dd4693daa99e35f7bcd436d7200a69d201af397047c128b946b914b","source":{"kind":"arxiv","id":"2104.08758","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08758","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08758v2","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08758","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"pith_short_12","alias_value":"K363A5CN2RUT","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"pith_short_16","alias_value":"K363A5CN2RUT3KUZ","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"pith_short_8","alias_value":"K363A5CN","created_at":"2026-07-05T03:18:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:K363A5CN2RUT3KUZ4NPXXTKDNV","target":"record","payload":{"canonical_record":{"source":{"id":"2104.08758","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T07:42:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db0c0b1292077a2c325bde18d8fe41295efed59245e5abecaebd9842cb829b2f","abstract_canon_sha256":"2852274258dec02b23e4531ae87f38bba236576216392db92852df7e466936dc"},"schema_version":"1.0"},"canonical_sha256":"56fdb0744dd4693daa99e35f7bcd436d7200a69d201af397047c128b946b914b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:54.693428Z","signature_b64":"ArFAH9MS+3+/mCnRAnCnudt+ys3cDMWwPogf+m5+WI6JV7auQr4WYMkhzdB6eaxhX9VkcW70h92aWK8DYrRuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56fdb0744dd4693daa99e35f7bcd436d7200a69d201af397047c128b946b914b","last_reissued_at":"2026-07-05T03:18:54.692872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:54.692872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.08758","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:18:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yde4yV5ykIjUHPmJzUrgQ04wt40Yr/vdJCizd/WmYuEdyByxHGqQ+N1lLdv/pj1kN7mFTtb+PmBNBGZD5IrXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:18:53.792283Z"},"content_sha256":"e8c3384ebbb8aaab6989859079934d019f62f0fa0eaf4f5905a8c932c0aedb39","schema_version":"1.0","event_id":"sha256:e8c3384ebbb8aaab6989859079934d019f62f0fa0eaf4f5905a8c932c0aedb39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:K363A5CN2RUT3KUZ4NPXXTKDNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ana Marasovi\\'c, Dirk Groeneveld, Gabriel Ilharco, Jesse Dodge, Maarten Sap, Margaret Mitchell, Matt Gardner, William Agnew","submitted_at":"2021-04-18T07:42:52Z","abstract_excerpt":"Large language models have led to remarkable progress on many NLP tasks, and researchers are turning to ever-larger text corpora to train them. Some of the largest corpora available are made by scraping significant portions of the internet, and are frequently introduced with only minimal documentation. In this work we provide some of the first documentation for the Colossal Clean Crawled Corpus (C4; Raffel et al., 2020), a dataset created by applying a set of filters to a single snapshot of Common Crawl. We begin by investigating where the data came from, and find a significant amount of text "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08758","kind":"arxiv","version":2},"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/2104.08758/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":"2026-07-05T03:18:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gd/WuAAB0hK4VrBrPiIK6dHopXUz63LsqLklT0tstG6jtqF3uANVBSOMfA5XaXRS+nSRp65iGrxw30V681JpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:18:53.792677Z"},"content_sha256":"72ae72d13dfcef9c1c9812b1077a539222d7e33fed3a7efad8e0d29d47cbd250","schema_version":"1.0","event_id":"sha256:72ae72d13dfcef9c1c9812b1077a539222d7e33fed3a7efad8e0d29d47cbd250"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K363A5CN2RUT3KUZ4NPXXTKDNV/bundle.json","state_url":"https://pith.science/pith/K363A5CN2RUT3KUZ4NPXXTKDNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K363A5CN2RUT3KUZ4NPXXTKDNV/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":"2026-08-21T23:18:53Z","links":{"resolver":"https://pith.science/pith/K363A5CN2RUT3KUZ4NPXXTKDNV","bundle":"https://pith.science/pith/K363A5CN2RUT3KUZ4NPXXTKDNV/bundle.json","state":"https://pith.science/pith/K363A5CN2RUT3KUZ4NPXXTKDNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K363A5CN2RUT3KUZ4NPXXTKDNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:K363A5CN2RUT3KUZ4NPXXTKDNV","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":"2852274258dec02b23e4531ae87f38bba236576216392db92852df7e466936dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T07:42:52Z","title_canon_sha256":"db0c0b1292077a2c325bde18d8fe41295efed59245e5abecaebd9842cb829b2f"},"schema_version":"1.0","source":{"id":"2104.08758","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08758","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08758v2","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08758","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"pith_short_12","alias_value":"K363A5CN2RUT","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"pith_short_16","alias_value":"K363A5CN2RUT3KUZ","created_at":"2026-07-05T03:18:54Z"},{"alias_kind":"pith_short_8","alias_value":"K363A5CN","created_at":"2026-07-05T03:18:54Z"}],"graph_snapshots":[{"event_id":"sha256:72ae72d13dfcef9c1c9812b1077a539222d7e33fed3a7efad8e0d29d47cbd250","target":"graph","created_at":"2026-07-05T03:18:54Z","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/2104.08758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have led to remarkable progress on many NLP tasks, and researchers are turning to ever-larger text corpora to train them. Some of the largest corpora available are made by scraping significant portions of the internet, and are frequently introduced with only minimal documentation. In this work we provide some of the first documentation for the Colossal Clean Crawled Corpus (C4; Raffel et al., 2020), a dataset created by applying a set of filters to a single snapshot of Common Crawl. We begin by investigating where the data came from, and find a significant amount of text ","authors_text":"Ana Marasovi\\'c, Dirk Groeneveld, Gabriel Ilharco, Jesse Dodge, Maarten Sap, Margaret Mitchell, Matt Gardner, William Agnew","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T07:42:52Z","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08758","kind":"arxiv","version":2},"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:e8c3384ebbb8aaab6989859079934d019f62f0fa0eaf4f5905a8c932c0aedb39","target":"record","created_at":"2026-07-05T03:18:54Z","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":"2852274258dec02b23e4531ae87f38bba236576216392db92852df7e466936dc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T07:42:52Z","title_canon_sha256":"db0c0b1292077a2c325bde18d8fe41295efed59245e5abecaebd9842cb829b2f"},"schema_version":"1.0","source":{"id":"2104.08758","kind":"arxiv","version":2}},"canonical_sha256":"56fdb0744dd4693daa99e35f7bcd436d7200a69d201af397047c128b946b914b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56fdb0744dd4693daa99e35f7bcd436d7200a69d201af397047c128b946b914b","first_computed_at":"2026-07-05T03:18:54.692872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:18:54.692872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ArFAH9MS+3+/mCnRAnCnudt+ys3cDMWwPogf+m5+WI6JV7auQr4WYMkhzdB6eaxhX9VkcW70h92aWK8DYrRuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:18:54.693428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08758","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8c3384ebbb8aaab6989859079934d019f62f0fa0eaf4f5905a8c932c0aedb39","sha256:72ae72d13dfcef9c1c9812b1077a539222d7e33fed3a7efad8e0d29d47cbd250"],"state_sha256":"5f7fd1c03ca7d8b4b48e2eb98a9ce76f5b32253e4fdc1e170d3b3e3d33a1a701"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zc0KVqOLU4OJgH4S/63CrJlEqELu0WJg5quwjAn3somAJu/dU79Bf/m7/LbuplPTtuhcpYHPtpQeXso2PcGcCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T23:18:53.795366Z","bundle_sha256":"4dfbf3492c0442e8551d604423dee25ba707d4bbdc9712567afd5f8791e6545d"}}