{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z2TYEIIZ66Q4UG6RZ4ALF2IOAY","short_pith_number":"pith:Z2TYEIIZ","schema_version":"1.0","canonical_sha256":"cea7822119f7a1ca1bd1cf00b2e90e06100519ce13dad360dcb8f64140459fc4","source":{"kind":"arxiv","id":"2412.00479","version":1},"attestation_state":"computed","paper":{"title":"Beyond time delays: How web scraping distorts measures of online news consumption","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Felix Schmidt, Frank Mangold, Judith Gilsbach, Roberto Ulloa, Sebastian Stier","submitted_at":"2024-11-30T13:36:48Z","abstract_excerpt":"As the exploration of digital behavioral data revolutionizes communication research, understanding the nuances of data collection methodologies becomes increasingly pertinent. This study focuses on one prominent data collection approach, web scraping, and more specifically, its application in the growing field of research relying on web browsing data. We investigate discrepancies between content obtained directly during user interaction with a website (in-situ) and content scraped using the URLs of participants' logged visits (ex-situ) with various time delays (0, 30, 60, and 90 days). We find"},"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":"2412.00479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-11-30T13:36:48Z","cross_cats_sorted":[],"title_canon_sha256":"fe6447627b957b6b1f1f311736a6855d8dd843a0ee5b90ce95bd5cb28a70d936","abstract_canon_sha256":"0d8e8be51f8d7fb18145e0062d3da15aaa870cc63b112edebbd4f6c0bbd7cd05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:42.120533Z","signature_b64":"akng2DTIEzvw+v47lGLFSrpqWzMP5ZBs9aITYH7FSNOYHnM5zxqhg1QzGYlzTSHojhebn0FowqAdg/1ybgkECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cea7822119f7a1ca1bd1cf00b2e90e06100519ce13dad360dcb8f64140459fc4","last_reissued_at":"2026-07-05T09:42:42.119997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:42.119997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond time delays: How web scraping distorts measures of online news consumption","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Felix Schmidt, Frank Mangold, Judith Gilsbach, Roberto Ulloa, Sebastian Stier","submitted_at":"2024-11-30T13:36:48Z","abstract_excerpt":"As the exploration of digital behavioral data revolutionizes communication research, understanding the nuances of data collection methodologies becomes increasingly pertinent. This study focuses on one prominent data collection approach, web scraping, and more specifically, its application in the growing field of research relying on web browsing data. We investigate discrepancies between content obtained directly during user interaction with a website (in-situ) and content scraped using the URLs of participants' logged visits (ex-situ) with various time delays (0, 30, 60, and 90 days). We find"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00479","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/2412.00479/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":"2412.00479","created_at":"2026-07-05T09:42:42.120056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00479v1","created_at":"2026-07-05T09:42:42.120056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00479","created_at":"2026-07-05T09:42:42.120056+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2TYEIIZ66Q4","created_at":"2026-07-05T09:42:42.120056+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2TYEIIZ66Q4UG6R","created_at":"2026-07-05T09:42:42.120056+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2TYEIIZ","created_at":"2026-07-05T09:42:42.120056+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/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY","json":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY.json","graph_json":"https://pith.science/api/pith-number/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/graph.json","events_json":"https://pith.science/api/pith-number/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/events.json","paper":"https://pith.science/paper/Z2TYEIIZ"},"agent_actions":{"view_html":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY","download_json":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY.json","view_paper":"https://pith.science/paper/Z2TYEIIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00479&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/action/storage_attestation","attest_author":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/action/author_attestation","sign_citation":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/action/citation_signature","submit_replication":"https://pith.science/pith/Z2TYEIIZ66Q4UG6RZ4ALF2IOAY/action/replication_record"}},"created_at":"2026-07-05T09:42:42.120056+00:00","updated_at":"2026-07-05T09:42:42.120056+00:00"}