{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BPRIN4VQJF2HZJFLDPQ5ERZATX","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":"d87714adb2f55bbd4301cc68b52e01a5c0c105770b39bad5900eea1bc92b4ab9","cross_cats_sorted":["cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-10-30T20:20:44Z","title_canon_sha256":"b8e7a66ace1f9afaf9a44b403a8e618ed1a93372bbd9c5fda0028c88a5c0ff80"},"schema_version":"1.0","source":{"id":"2410.23432","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23432","created_at":"2026-07-05T09:51:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23432v2","created_at":"2026-07-05T09:51:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23432","created_at":"2026-07-05T09:51:38Z"},{"alias_kind":"pith_short_12","alias_value":"BPRIN4VQJF2H","created_at":"2026-07-05T09:51:38Z"},{"alias_kind":"pith_short_16","alias_value":"BPRIN4VQJF2HZJFL","created_at":"2026-07-05T09:51:38Z"},{"alias_kind":"pith_short_8","alias_value":"BPRIN4VQ","created_at":"2026-07-05T09:51:38Z"}],"graph_snapshots":[{"event_id":"sha256:9db32578330eb4a5b646acd861c103955b321af3ad7ec6c59b53df1a1767b0b6","target":"graph","created_at":"2026-07-05T09:51:38Z","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/2410.23432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientists across disciplines often use data from the internet to conduct research, generating valuable insights about human behavior. However, as generative AI relying on massive text corpora becomes increasingly valuable, platforms have greatly restricted access to data through official channels. As a result, researchers will likely engage in more web scraping to collect data, introducing new challenges and concerns for researchers. This paper proposes a comprehensive framework for web scraping in social science research for U.S.-based researchers, examining the legal, ethical, institutional","authors_text":"Andrew Gruen, Gabe Maldoff, Megan A. Brown, Michael Zimmer, Solomon Messing, Zeve Sanderson","cross_cats":["cs.SI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-10-30T20:20:44Z","title":"Web Scraping for Research: Legal, Ethical, Institutional, and Scientific Considerations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23432","kind":"arxiv","version":2},"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:ae823d8d3d265c3ef050449bc2484ff6c8f89d0a1bb193d083f7fdd8924d6976","target":"record","created_at":"2026-07-05T09:51:38Z","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":"d87714adb2f55bbd4301cc68b52e01a5c0c105770b39bad5900eea1bc92b4ab9","cross_cats_sorted":["cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-10-30T20:20:44Z","title_canon_sha256":"b8e7a66ace1f9afaf9a44b403a8e618ed1a93372bbd9c5fda0028c88a5c0ff80"},"schema_version":"1.0","source":{"id":"2410.23432","kind":"arxiv","version":2}},"canonical_sha256":"0be286f2b049747ca4ab1be1d247209dcd74542a315f45810385f782fb6f66aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0be286f2b049747ca4ab1be1d247209dcd74542a315f45810385f782fb6f66aa","first_computed_at":"2026-07-05T09:51:38.125413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:38.125413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xJt0E9HO62Pz+NzV/mGV3BmyDZ/IzV+yA6vIpKwLwwDffdfdtO5TG3JCZNFT1tvmgrsyrctFImXyF2C762VdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:38.125905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23432","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae823d8d3d265c3ef050449bc2484ff6c8f89d0a1bb193d083f7fdd8924d6976","sha256:9db32578330eb4a5b646acd861c103955b321af3ad7ec6c59b53df1a1767b0b6"],"state_sha256":"2fdff9a32c3250e8e63f89b9a129dee59e6398d7e30a85f1417342d268eb6878"}