{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4H6OUACRFGD3VFMN6PWJL266NZ","short_pith_number":"pith:4H6OUACR","schema_version":"1.0","canonical_sha256":"e1fcea00512987ba958df3ec95ebde6e6298dd2413555d674e1b9bb2d51c4b1c","source":{"kind":"arxiv","id":"2001.07487","version":2},"attestation_state":"computed","paper":{"title":"Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect Board","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.CY","authors_text":"Antonis Papasavva, Emiliano De Cristofaro, Gianluca Stringhini, Jeremy Blackburn, Savvas Zannettou","submitted_at":"2020-01-21T12:52:24Z","abstract_excerpt":"This paper presents a dataset with over 3.3M threads and 134.5M posts from the Politically Incorrect board (/pol/) of the imageboard forum 4chan, posted over a period of almost 3.5 years (June 2016-November 2019). To the best of our knowledge, this represents the largest publicly available 4chan dataset, providing the community with an archive of posts that have been permanently deleted from 4chan and are otherwise inaccessible. We augment the data with a set of additional labels, including toxicity scores and the named entities mentioned in each post. We also present a statistical analysis of"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2001.07487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2020-01-21T12:52:24Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"3e31a9e561b6b38e9c2d61e39c147515411054cd510e3bebc3689349f46c6f41","abstract_canon_sha256":"73913254730aba736fc60c3bb9c576e85f41bb6f953d9a18ed4a6fdd234a8bb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:52:07.030046Z","signature_b64":"ouiMGhY4iyDlyzwfv8msiykPVV5Ux8GeHexvK6CLQhBpLDVfuSack8gA1Ps8HV2VkxvSqV/YA1wWyc3sp6efDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1fcea00512987ba958df3ec95ebde6e6298dd2413555d674e1b9bb2d51c4b1c","last_reissued_at":"2026-07-05T00:52:07.029539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:52:07.029539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect Board","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.CY","authors_text":"Antonis Papasavva, Emiliano De Cristofaro, Gianluca Stringhini, Jeremy Blackburn, Savvas Zannettou","submitted_at":"2020-01-21T12:52:24Z","abstract_excerpt":"This paper presents a dataset with over 3.3M threads and 134.5M posts from the Politically Incorrect board (/pol/) of the imageboard forum 4chan, posted over a period of almost 3.5 years (June 2016-November 2019). To the best of our knowledge, this represents the largest publicly available 4chan dataset, providing the community with an archive of posts that have been permanently deleted from 4chan and are otherwise inaccessible. We augment the data with a set of additional labels, including toxicity scores and the named entities mentioned in each post. We also present a statistical analysis of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07487","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/2001.07487/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2001.07487","created_at":"2026-07-05T00:52:07.029596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07487v2","created_at":"2026-07-05T00:52:07.029596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07487","created_at":"2026-07-05T00:52:07.029596+00:00"},{"alias_kind":"pith_short_12","alias_value":"4H6OUACRFGD3","created_at":"2026-07-05T00:52:07.029596+00:00"},{"alias_kind":"pith_short_16","alias_value":"4H6OUACRFGD3VFMN","created_at":"2026-07-05T00:52:07.029596+00:00"},{"alias_kind":"pith_short_8","alias_value":"4H6OUACR","created_at":"2026-07-05T00:52:07.029596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14191","citing_title":"The Ethics of Generative AI in Anonymous Spaces: A Case Study of 4chan's /pol/ Board","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ","json":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ.json","graph_json":"https://pith.science/api/pith-number/4H6OUACRFGD3VFMN6PWJL266NZ/graph.json","events_json":"https://pith.science/api/pith-number/4H6OUACRFGD3VFMN6PWJL266NZ/events.json","paper":"https://pith.science/paper/4H6OUACR"},"agent_actions":{"view_html":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ","download_json":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ.json","view_paper":"https://pith.science/paper/4H6OUACR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07487&json=true","fetch_graph":"https://pith.science/api/pith-number/4H6OUACRFGD3VFMN6PWJL266NZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4H6OUACRFGD3VFMN6PWJL266NZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ/action/storage_attestation","attest_author":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ/action/author_attestation","sign_citation":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ/action/citation_signature","submit_replication":"https://pith.science/pith/4H6OUACRFGD3VFMN6PWJL266NZ/action/replication_record"}},"created_at":"2026-07-05T00:52:07.029596+00:00","updated_at":"2026-07-05T00:52:07.029596+00:00"}