{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W4LDYNWPWKFKQH4HWFGZ6FUO3E","short_pith_number":"pith:W4LDYNWP","canonical_record":{"source":{"id":"2401.06408","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T07:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"4225a9ce6d9f1303e06d6024ce6bdafa66fcd6f584f5380a31d5975df547a91c","abstract_canon_sha256":"d39f52fe2f6e316857706b990d58f2ec1a7ecf7fe594b7285b7f1239d161e0d2"},"schema_version":"1.0"},"canonical_sha256":"b7163c36cfb28aa81f87b14d9f168ed920643b2ec2612bc24466b9e5aed9d796","source":{"kind":"arxiv","id":"2401.06408","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06408","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06408v3","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06408","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"W4LDYNWPWKFK","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"W4LDYNWPWKFKQH4H","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"W4LDYNWP","created_at":"2026-07-05T08:34:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W4LDYNWPWKFKQH4HWFGZ6FUO3E","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06408","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T07:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"4225a9ce6d9f1303e06d6024ce6bdafa66fcd6f584f5380a31d5975df547a91c","abstract_canon_sha256":"d39f52fe2f6e316857706b990d58f2ec1a7ecf7fe594b7285b7f1239d161e0d2"},"schema_version":"1.0"},"canonical_sha256":"b7163c36cfb28aa81f87b14d9f168ed920643b2ec2612bc24466b9e5aed9d796","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:59.409421Z","signature_b64":"x1tUurv8jYi3FIvPva9ruon3/lktxMBRJE9ZJ/pEIOJcMNFTAD5D3Tktd64BkoSqZB9IYDrzkPGu//upevvzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7163c36cfb28aa81f87b14d9f168ed920643b2ec2612bc24466b9e5aed9d796","last_reissued_at":"2026-07-05T08:34:59.408972Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:59.408972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06408","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":"2026-07-05T08:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vo5Gu4BusKpPMy5G9zTxns7zZZTaJzii2WFQfa9rvodxHARK5YbRj9rbYZH9kWI3LZeUgwE6qP6vuY0icnLDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:54:33.931423Z"},"content_sha256":"bbcbc604c23015ba3698b78c0a4805f177c44ac6ec8e942432da02c746786b0d","schema_version":"1.0","event_id":"sha256:bbcbc604c23015ba3698b78c0a4805f177c44ac6ec8e942432da02c746786b0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W4LDYNWPWKFKQH4HWFGZ6FUO3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Bamman, Emma Strubell, Jesse Dodge, Lauren F. Klein, Li Lucy, Luca Soldaini, Suchin Gururangan","submitted_at":"2024-01-12T07:10:10Z","abstract_excerpt":"Large language models' (LLMs) abilities are drawn from their pretraining data, and model development begins with data curation. However, decisions around what data is retained or removed during this initial stage are under-scrutinized. In our work, we ground web text, which is a popular pretraining data source, to its social and geographic contexts. We create a new dataset of 10.3 million self-descriptions of website creators, and extract information about who they are and where they are from: their topical interests, social roles, and geographic affiliations. Then, we conduct the first study "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06408","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/2401.06408/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":"2026-07-05T08:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FQxzuFMJe87ZjlZkY7F+Dx0oko9fLWseZ5c2lEwnY9sjGNuGgjjZ5eodVJccQmjEbWu5/RptDcQmgQFzxZYnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:54:33.932345Z"},"content_sha256":"024b8eb35dce109267f8a1f2e1f2bed5c1a524dad0d29bed6859d9d53e18d954","schema_version":"1.0","event_id":"sha256:024b8eb35dce109267f8a1f2e1f2bed5c1a524dad0d29bed6859d9d53e18d954"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4LDYNWPWKFKQH4HWFGZ6FUO3E/bundle.json","state_url":"https://pith.science/pith/W4LDYNWPWKFKQH4HWFGZ6FUO3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4LDYNWPWKFKQH4HWFGZ6FUO3E/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":"2026-08-09T07:54:33Z","links":{"resolver":"https://pith.science/pith/W4LDYNWPWKFKQH4HWFGZ6FUO3E","bundle":"https://pith.science/pith/W4LDYNWPWKFKQH4HWFGZ6FUO3E/bundle.json","state":"https://pith.science/pith/W4LDYNWPWKFKQH4HWFGZ6FUO3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4LDYNWPWKFKQH4HWFGZ6FUO3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W4LDYNWPWKFKQH4HWFGZ6FUO3E","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":"d39f52fe2f6e316857706b990d58f2ec1a7ecf7fe594b7285b7f1239d161e0d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T07:10:10Z","title_canon_sha256":"4225a9ce6d9f1303e06d6024ce6bdafa66fcd6f584f5380a31d5975df547a91c"},"schema_version":"1.0","source":{"id":"2401.06408","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06408","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06408v3","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06408","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"W4LDYNWPWKFK","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"W4LDYNWPWKFKQH4H","created_at":"2026-07-05T08:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"W4LDYNWP","created_at":"2026-07-05T08:34:59Z"}],"graph_snapshots":[{"event_id":"sha256:024b8eb35dce109267f8a1f2e1f2bed5c1a524dad0d29bed6859d9d53e18d954","target":"graph","created_at":"2026-07-05T08:34:59Z","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/2401.06408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models' (LLMs) abilities are drawn from their pretraining data, and model development begins with data curation. However, decisions around what data is retained or removed during this initial stage are under-scrutinized. In our work, we ground web text, which is a popular pretraining data source, to its social and geographic contexts. We create a new dataset of 10.3 million self-descriptions of website creators, and extract information about who they are and where they are from: their topical interests, social roles, and geographic affiliations. Then, we conduct the first study ","authors_text":"David Bamman, Emma Strubell, Jesse Dodge, Lauren F. Klein, Li Lucy, Luca Soldaini, Suchin Gururangan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T07:10:10Z","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06408","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:bbcbc604c23015ba3698b78c0a4805f177c44ac6ec8e942432da02c746786b0d","target":"record","created_at":"2026-07-05T08:34:59Z","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":"d39f52fe2f6e316857706b990d58f2ec1a7ecf7fe594b7285b7f1239d161e0d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-12T07:10:10Z","title_canon_sha256":"4225a9ce6d9f1303e06d6024ce6bdafa66fcd6f584f5380a31d5975df547a91c"},"schema_version":"1.0","source":{"id":"2401.06408","kind":"arxiv","version":3}},"canonical_sha256":"b7163c36cfb28aa81f87b14d9f168ed920643b2ec2612bc24466b9e5aed9d796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7163c36cfb28aa81f87b14d9f168ed920643b2ec2612bc24466b9e5aed9d796","first_computed_at":"2026-07-05T08:34:59.408972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:59.408972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x1tUurv8jYi3FIvPva9ruon3/lktxMBRJE9ZJ/pEIOJcMNFTAD5D3Tktd64BkoSqZB9IYDrzkPGu//upevvzDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:59.409421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06408","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbcbc604c23015ba3698b78c0a4805f177c44ac6ec8e942432da02c746786b0d","sha256:024b8eb35dce109267f8a1f2e1f2bed5c1a524dad0d29bed6859d9d53e18d954"],"state_sha256":"3f4a7ba07c2d052ba855b0a85eb88b3bea3b965ae1eda556099a629dc8caf483"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpKspe61EX+TiWtmQb/jshoQBQ0QP+tRfpdRav1iyaNH1OlOteSFbJpd29TwMj0F2zuyF/OiaOEysO2nDUKxAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:54:33.938481Z","bundle_sha256":"26e96830eaa94378b7c2c076a1d1be48bb0ed4176fde2a1f73d968088304108c"}}