{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JPPAL6ZCLUZAWBVHNT56CTQOFH","short_pith_number":"pith:JPPAL6ZC","schema_version":"1.0","canonical_sha256":"4bde05fb225d320b06a76cfbe14e0e29f8eb193cb0b1850f96a87f97c196eb89","source":{"kind":"arxiv","id":"2404.18984","version":1},"attestation_state":"computed","paper":{"title":"\"I'm in the Bluesky Tonight\": Insights from a Year Worth of Social Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.SI","authors_text":"Andrea Failla, Giulio Rossetti","submitted_at":"2024-04-29T16:43:39Z","abstract_excerpt":"Pollution of online social spaces caused by rampaging d/misinformation is a growing societal concern. However, recent decisions to reduce access to social media APIs are causing a shortage of publicly available, recent, social media data, thus hindering the advancement of computational social science as a whole. We present a large, high-coverage dataset of social interactions and user-generated content from Bluesky Social to address this pressing issue. The dataset contains the complete post history of over 4M users (81% of all registered accounts), totalling 235M posts. We also make available"},"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":"2404.18984","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SI","submitted_at":"2024-04-29T16:43:39Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"6d13ec6ca2cf13da65120771288d5db7f2e62be6796bb4878fa54a53a33aebf2","abstract_canon_sha256":"96b67e73c78ff38cc361f48c409737fc0bba5bb0de9dc298509bee7f88654c6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:06.261205Z","signature_b64":"LQs+5d2NtB+nhh9r5pMT7MkYTW2LJyoCLBwlxFqvT8XEXGtz2+eqBQTcB7+fargdedS7B5/qFt2E3M1Ads9MCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bde05fb225d320b06a76cfbe14e0e29f8eb193cb0b1850f96a87f97c196eb89","last_reissued_at":"2026-07-05T09:39:06.260702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:06.260702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"I'm in the Bluesky Tonight\": Insights from a Year Worth of Social Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.SI","authors_text":"Andrea Failla, Giulio Rossetti","submitted_at":"2024-04-29T16:43:39Z","abstract_excerpt":"Pollution of online social spaces caused by rampaging d/misinformation is a growing societal concern. However, recent decisions to reduce access to social media APIs are causing a shortage of publicly available, recent, social media data, thus hindering the advancement of computational social science as a whole. We present a large, high-coverage dataset of social interactions and user-generated content from Bluesky Social to address this pressing issue. The dataset contains the complete post history of over 4M users (81% of all registered accounts), totalling 235M posts. We also make available"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18984","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/2404.18984/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":"2404.18984","created_at":"2026-07-05T09:39:06.260756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18984v1","created_at":"2026-07-05T09:39:06.260756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18984","created_at":"2026-07-05T09:39:06.260756+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPPAL6ZCLUZA","created_at":"2026-07-05T09:39:06.260756+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPPAL6ZCLUZAWBVH","created_at":"2026-07-05T09:39:06.260756+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPPAL6ZC","created_at":"2026-07-05T09:39:06.260756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27710","citing_title":"Social Media Data Toolkit: Standardization and Anonymization of Social Network Datasets","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH","json":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH.json","graph_json":"https://pith.science/api/pith-number/JPPAL6ZCLUZAWBVHNT56CTQOFH/graph.json","events_json":"https://pith.science/api/pith-number/JPPAL6ZCLUZAWBVHNT56CTQOFH/events.json","paper":"https://pith.science/paper/JPPAL6ZC"},"agent_actions":{"view_html":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH","download_json":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH.json","view_paper":"https://pith.science/paper/JPPAL6ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18984&json=true","fetch_graph":"https://pith.science/api/pith-number/JPPAL6ZCLUZAWBVHNT56CTQOFH/graph.json","fetch_events":"https://pith.science/api/pith-number/JPPAL6ZCLUZAWBVHNT56CTQOFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH/action/storage_attestation","attest_author":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH/action/author_attestation","sign_citation":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH/action/citation_signature","submit_replication":"https://pith.science/pith/JPPAL6ZCLUZAWBVHNT56CTQOFH/action/replication_record"}},"created_at":"2026-07-05T09:39:06.260756+00:00","updated_at":"2026-07-05T09:39:06.260756+00:00"}