{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AVJHU64QPCEW3SKZ3B7757EKQB","short_pith_number":"pith:AVJHU64Q","schema_version":"1.0","canonical_sha256":"05527a7b9078896dc959d87ffefc8a8055f10bdf6e2a3ad7dcee9041b7dc5662","source":{"kind":"arxiv","id":"2606.04924","version":1},"attestation_state":"computed","paper":{"title":"Can Crowdsourcing Survive the LLM Era? A Community Survey on Human Data Collection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amelie Wuehrl, Aswathy Velutharambath, Neele Falk, Sofie Labat, Tarun Tater","submitted_at":"2026-06-03T14:18:27Z","abstract_excerpt":"The widespread use of Large Language Models (LLMs) as writing tools challenges the validity of crowdsourced data, as crowdworkers may outsource tasks to models. To better understand how this is addressed, we surveyed 155 researchers in NLP and related disciplines about their experiences and opinions on collecting free-text responses via crowdsourcing. This paper provides an overview of practitioners' challenges, mitigation strategies, and the foreseen implications on data quality. 44% of respondents reported observing LLM usage in their crowdsourced data. While 93% of them had anticipated this"},"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":"2606.04924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T14:18:27Z","cross_cats_sorted":[],"title_canon_sha256":"d0c41533108ffe697739b03824efe2f247d93523048b31d24a76bd1c944054ed","abstract_canon_sha256":"a62b22a78953734bba534eda0a85519f208401b9583827487d9444932aa2a30c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:55.952607Z","signature_b64":"CfmR1v+EUOcH78ZLlnAj6BjjsNg411ESQB/cYWUFGyLSubcZ4Am1ODraaRNnxucppihnbxh9J9R0fbCbyPUeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05527a7b9078896dc959d87ffefc8a8055f10bdf6e2a3ad7dcee9041b7dc5662","last_reissued_at":"2026-06-04T01:09:55.951647Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:55.951647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Crowdsourcing Survive the LLM Era? A Community Survey on Human Data Collection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amelie Wuehrl, Aswathy Velutharambath, Neele Falk, Sofie Labat, Tarun Tater","submitted_at":"2026-06-03T14:18:27Z","abstract_excerpt":"The widespread use of Large Language Models (LLMs) as writing tools challenges the validity of crowdsourced data, as crowdworkers may outsource tasks to models. To better understand how this is addressed, we surveyed 155 researchers in NLP and related disciplines about their experiences and opinions on collecting free-text responses via crowdsourcing. This paper provides an overview of practitioners' challenges, mitigation strategies, and the foreseen implications on data quality. 44% of respondents reported observing LLM usage in their crowdsourced data. While 93% of them had anticipated this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04924","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/2606.04924/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":"2606.04924","created_at":"2026-06-04T01:09:55.951806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04924v1","created_at":"2026-06-04T01:09:55.951806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04924","created_at":"2026-06-04T01:09:55.951806+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVJHU64QPCEW","created_at":"2026-06-04T01:09:55.951806+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVJHU64QPCEW3SKZ","created_at":"2026-06-04T01:09:55.951806+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVJHU64Q","created_at":"2026-06-04T01:09:55.951806+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/AVJHU64QPCEW3SKZ3B7757EKQB","json":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB.json","graph_json":"https://pith.science/api/pith-number/AVJHU64QPCEW3SKZ3B7757EKQB/graph.json","events_json":"https://pith.science/api/pith-number/AVJHU64QPCEW3SKZ3B7757EKQB/events.json","paper":"https://pith.science/paper/AVJHU64Q"},"agent_actions":{"view_html":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB","download_json":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB.json","view_paper":"https://pith.science/paper/AVJHU64Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04924&json=true","fetch_graph":"https://pith.science/api/pith-number/AVJHU64QPCEW3SKZ3B7757EKQB/graph.json","fetch_events":"https://pith.science/api/pith-number/AVJHU64QPCEW3SKZ3B7757EKQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB/action/storage_attestation","attest_author":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB/action/author_attestation","sign_citation":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB/action/citation_signature","submit_replication":"https://pith.science/pith/AVJHU64QPCEW3SKZ3B7757EKQB/action/replication_record"}},"created_at":"2026-06-04T01:09:55.951806+00:00","updated_at":"2026-06-04T01:09:55.951806+00:00"}