{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FYK2JFFHSL2IMV6JPHELG7JGAV","short_pith_number":"pith:FYK2JFFH","schema_version":"1.0","canonical_sha256":"2e15a494a792f48657c979c8b37d260577c49febe4184e5ac71a08235d91e850","source":{"kind":"arxiv","id":"1808.09600","version":1},"attestation_state":"computed","paper":{"title":"The Remarkable Benefit of User-Level Aggregation for Lexical-based Population-Level Predictions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.SI","authors_text":"Anneke Buffone, Daniel Preotiuc-Pietro, Daniel Rieman, H. Andrew Schwartz, Lyle H. Ungar, Salvatore Giorgi","submitted_at":"2018-08-29T01:33:21Z","abstract_excerpt":"Nowcasting based on social media text promises to provide unobtrusive and near real-time predictions of community-level outcomes. These outcomes are typically regarding people, but the data is often aggregated without regard to users in the Twitter populations of each community. This paper describes a simple yet effective method for building community-level models using Twitter language aggregated by user. Results on four different U.S. county-level tasks, spanning demographic, health, and psychological outcomes show large and consistent improvements in prediction accuracies (e.g. from Pearson"},"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":"1808.09600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SI","submitted_at":"2018-08-29T01:33:21Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"ac3218320f1105a2b540ce2fc4b2b29bd12a673d7020729baef316ae0d67ce8a","abstract_canon_sha256":"72da6ebee85fa553d1b462feab9fdfc5ca1915dabb5eb22c0d90cb28dbe7b273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:55.043793Z","signature_b64":"+W+hUZRxz7hH25ZBF5BMBoOV9tuBfLmjl2/BbQMxpHOhPowl+vMdmzNZ/wW7sQt8Y9FLqvJESLXkIP7hZlZiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e15a494a792f48657c979c8b37d260577c49febe4184e5ac71a08235d91e850","last_reissued_at":"2026-05-18T00:06:55.043290Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:55.043290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Remarkable Benefit of User-Level Aggregation for Lexical-based Population-Level Predictions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.SI","authors_text":"Anneke Buffone, Daniel Preotiuc-Pietro, Daniel Rieman, H. Andrew Schwartz, Lyle H. Ungar, Salvatore Giorgi","submitted_at":"2018-08-29T01:33:21Z","abstract_excerpt":"Nowcasting based on social media text promises to provide unobtrusive and near real-time predictions of community-level outcomes. These outcomes are typically regarding people, but the data is often aggregated without regard to users in the Twitter populations of each community. This paper describes a simple yet effective method for building community-level models using Twitter language aggregated by user. Results on four different U.S. county-level tasks, spanning demographic, health, and psychological outcomes show large and consistent improvements in prediction accuracies (e.g. from Pearson"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09600","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":""},"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":"1808.09600","created_at":"2026-05-18T00:06:55.043384+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09600v1","created_at":"2026-05-18T00:06:55.043384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09600","created_at":"2026-05-18T00:06:55.043384+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYK2JFFHSL2I","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYK2JFFHSL2IMV6J","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYK2JFFH","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV","json":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV.json","graph_json":"https://pith.science/api/pith-number/FYK2JFFHSL2IMV6JPHELG7JGAV/graph.json","events_json":"https://pith.science/api/pith-number/FYK2JFFHSL2IMV6JPHELG7JGAV/events.json","paper":"https://pith.science/paper/FYK2JFFH"},"agent_actions":{"view_html":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV","download_json":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV.json","view_paper":"https://pith.science/paper/FYK2JFFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09600&json=true","fetch_graph":"https://pith.science/api/pith-number/FYK2JFFHSL2IMV6JPHELG7JGAV/graph.json","fetch_events":"https://pith.science/api/pith-number/FYK2JFFHSL2IMV6JPHELG7JGAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV/action/storage_attestation","attest_author":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV/action/author_attestation","sign_citation":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV/action/citation_signature","submit_replication":"https://pith.science/pith/FYK2JFFHSL2IMV6JPHELG7JGAV/action/replication_record"}},"created_at":"2026-05-18T00:06:55.043384+00:00","updated_at":"2026-05-18T00:06:55.043384+00:00"}