{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3P32UXCSFIA2MQCDNJ4LU3VTE","short_pith_number":"pith:H3P32UXC","schema_version":"1.0","canonical_sha256":"3edfbd52e291500d32021b53c5d37599009ee4ae986e07f61c1504820376595d","source":{"kind":"arxiv","id":"2502.07732","version":2},"attestation_state":"computed","paper":{"title":"When Incentives Backfire, Data Stops Being Human","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.CY","authors_text":"Kelsey Allen, Manoel Horta Ribeiro, Prasanta Bhattacharya, Sebastin Santy, Sewoong Oh","submitted_at":"2025-02-11T17:51:52Z","abstract_excerpt":"Progress in AI has relied on human-generated data, from annotator marketplaces to the wider Internet. However, the widespread use of large language models now threatens the quality and integrity of human-generated data on these very platforms. We argue that this issue goes beyond the immediate challenge of filtering AI-generated content -- it reveals deeper flaws in how data collection systems are designed. Existing systems often prioritize speed, scale, and efficiency at the cost of intrinsic human motivation, leading to declining engagement and data quality. We propose that rethinking data c"},"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":"2502.07732","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-02-11T17:51:52Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.HC","cs.LG"],"title_canon_sha256":"4547ba8625509d482a6aa34afdcb0295d08f956b4922af60255e181a766aee6e","abstract_canon_sha256":"8537d7fc09734c9b38b6eef8221cb33bdb45d5ed428338607d94c605e72b1c1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:41.130758Z","signature_b64":"/drk/2ApC6NBC4TkIvvnK7Hbt9FxhK9R0xzuHnaM7Yd65mBiRHp+K+tPszI0d08cLjbKZsS/H3VsJYqkOe2mAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3edfbd52e291500d32021b53c5d37599009ee4ae986e07f61c1504820376595d","last_reissued_at":"2026-07-05T11:17:41.130243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:41.130243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Incentives Backfire, Data Stops Being Human","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.HC","cs.LG"],"primary_cat":"cs.CY","authors_text":"Kelsey Allen, Manoel Horta Ribeiro, Prasanta Bhattacharya, Sebastin Santy, Sewoong Oh","submitted_at":"2025-02-11T17:51:52Z","abstract_excerpt":"Progress in AI has relied on human-generated data, from annotator marketplaces to the wider Internet. However, the widespread use of large language models now threatens the quality and integrity of human-generated data on these very platforms. We argue that this issue goes beyond the immediate challenge of filtering AI-generated content -- it reveals deeper flaws in how data collection systems are designed. Existing systems often prioritize speed, scale, and efficiency at the cost of intrinsic human motivation, leading to declining engagement and data quality. We propose that rethinking data c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07732","kind":"arxiv","version":2},"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/2502.07732/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":"2502.07732","created_at":"2026-07-05T11:17:41.130301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07732v2","created_at":"2026-07-05T11:17:41.130301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07732","created_at":"2026-07-05T11:17:41.130301+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3P32UXCSFIA","created_at":"2026-07-05T11:17:41.130301+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3P32UXCSFIA2MQC","created_at":"2026-07-05T11:17:41.130301+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3P32UXC","created_at":"2026-07-05T11:17:41.130301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26965","citing_title":"The Impact of AI-Generated Text on the Internet","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE","json":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE.json","graph_json":"https://pith.science/api/pith-number/H3P32UXCSFIA2MQCDNJ4LU3VTE/graph.json","events_json":"https://pith.science/api/pith-number/H3P32UXCSFIA2MQCDNJ4LU3VTE/events.json","paper":"https://pith.science/paper/H3P32UXC"},"agent_actions":{"view_html":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE","download_json":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE.json","view_paper":"https://pith.science/paper/H3P32UXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07732&json=true","fetch_graph":"https://pith.science/api/pith-number/H3P32UXCSFIA2MQCDNJ4LU3VTE/graph.json","fetch_events":"https://pith.science/api/pith-number/H3P32UXCSFIA2MQCDNJ4LU3VTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE/action/storage_attestation","attest_author":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE/action/author_attestation","sign_citation":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE/action/citation_signature","submit_replication":"https://pith.science/pith/H3P32UXCSFIA2MQCDNJ4LU3VTE/action/replication_record"}},"created_at":"2026-07-05T11:17:41.130301+00:00","updated_at":"2026-07-05T11:17:41.130301+00:00"}