{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNGXQLR2SCKIEG4FDGVUH3OZWK","short_pith_number":"pith:FNGXQLR2","schema_version":"1.0","canonical_sha256":"2b4d782e3a9094821b8519ab43edd9b290edc6bc683a806ba0c137a2a0491efd","source":{"kind":"arxiv","id":"2402.13567","version":1},"attestation_state":"computed","paper":{"title":"Spot Check Equivalence: an Interpretable Metric for Information Elicitation Mechanisms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Grant Schoenebeck, Paul Resnick, Shengwei Xu, Yichi Zhang","submitted_at":"2024-02-21T06:57:07Z","abstract_excerpt":"Because high-quality data is like oxygen for AI systems, effectively eliciting information from crowdsourcing workers has become a first-order problem for developing high-performance machine learning algorithms. Two prevalent paradigms, spot-checking and peer prediction, enable the design of mechanisms to evaluate and incentivize high-quality data from human labelers. So far, at least three metrics have been proposed to compare the performances of these techniques [33, 8, 3]. However, different metrics lead to divergent and even contradictory results in various contexts. In this paper, we harm"},"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":"2402.13567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T06:57:07Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"17aaaae8de1355d4734500c5e43204e15534fdcf87ca0d99a38a3dce5b2d435c","abstract_canon_sha256":"bd65137130780e82518f9d1bbdd9c9b6563f900e2a0a536a567b522c5f75efd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:34.272965Z","signature_b64":"NBopXxBWdJx72J3R1nVxGLMMl4sYUZtrhXBCYXVPoJlsNuJb2B8upJfDGZC2OJlGgXdTAe9l0AfF+6ex5fj9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b4d782e3a9094821b8519ab43edd9b290edc6bc683a806ba0c137a2a0491efd","last_reissued_at":"2026-07-05T07:47:34.272450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:34.272450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spot Check Equivalence: an Interpretable Metric for Information Elicitation Mechanisms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Grant Schoenebeck, Paul Resnick, Shengwei Xu, Yichi Zhang","submitted_at":"2024-02-21T06:57:07Z","abstract_excerpt":"Because high-quality data is like oxygen for AI systems, effectively eliciting information from crowdsourcing workers has become a first-order problem for developing high-performance machine learning algorithms. Two prevalent paradigms, spot-checking and peer prediction, enable the design of mechanisms to evaluate and incentivize high-quality data from human labelers. So far, at least three metrics have been proposed to compare the performances of these techniques [33, 8, 3]. However, different metrics lead to divergent and even contradictory results in various contexts. In this paper, we harm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13567","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/2402.13567/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":"2402.13567","created_at":"2026-07-05T07:47:34.272507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13567v1","created_at":"2026-07-05T07:47:34.272507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13567","created_at":"2026-07-05T07:47:34.272507+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNGXQLR2SCKI","created_at":"2026-07-05T07:47:34.272507+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNGXQLR2SCKIEG4F","created_at":"2026-07-05T07:47:34.272507+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNGXQLR2","created_at":"2026-07-05T07:47:34.272507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01423","citing_title":"Scoring Rules! Statistical and Strategic Alignment for Text Evaluation Metrics","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK","json":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK.json","graph_json":"https://pith.science/api/pith-number/FNGXQLR2SCKIEG4FDGVUH3OZWK/graph.json","events_json":"https://pith.science/api/pith-number/FNGXQLR2SCKIEG4FDGVUH3OZWK/events.json","paper":"https://pith.science/paper/FNGXQLR2"},"agent_actions":{"view_html":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK","download_json":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK.json","view_paper":"https://pith.science/paper/FNGXQLR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13567&json=true","fetch_graph":"https://pith.science/api/pith-number/FNGXQLR2SCKIEG4FDGVUH3OZWK/graph.json","fetch_events":"https://pith.science/api/pith-number/FNGXQLR2SCKIEG4FDGVUH3OZWK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK/action/storage_attestation","attest_author":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK/action/author_attestation","sign_citation":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK/action/citation_signature","submit_replication":"https://pith.science/pith/FNGXQLR2SCKIEG4FDGVUH3OZWK/action/replication_record"}},"created_at":"2026-07-05T07:47:34.272507+00:00","updated_at":"2026-07-05T07:47:34.272507+00:00"}