{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I6JANFPE3XAYV2Q6O5WC4A6JNK","short_pith_number":"pith:I6JANFPE","schema_version":"1.0","canonical_sha256":"47920695e4ddc18aea1e776c2e03c96a974ff7a3a81a0bd9276ce35078dd63b0","source":{"kind":"arxiv","id":"2208.06161","version":2},"attestation_state":"computed","paper":{"title":"Sparse Probability of Agreement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jeppe N{\\o}rregaard, Leon Derczynski","submitted_at":"2022-08-12T08:15:34Z","abstract_excerpt":"Measuring inter-annotator agreement is important for annotation tasks, but many metrics require a fully-annotated set of data, where all annotators annotate all samples. We define Sparse Probability of Agreement, SPA, which estimates the probability of agreement when not all annotator-item-pairs are available. We show that under certain conditions, SPA is an unbiased estimator, and we provide multiple weighing schemes for handling data with various degrees of annotation."},"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":"2208.06161","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-12T08:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"3b5519eebbd5546840b5f8cac87659e74bba30d7b93625e78dea295cca748c3f","abstract_canon_sha256":"430f7ec985208c4f9ab67d02ce784f265de2a384d6e55e6547ff962c88a4138d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:32.010084Z","signature_b64":"N1TPeA5QP7yqNxnztWju0ZtK5WCpnXDD3KqHB10ZKQq0Pd99PzkS9hK/43NDu6o5p/R39y4K119joq4WQI1PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47920695e4ddc18aea1e776c2e03c96a974ff7a3a81a0bd9276ce35078dd63b0","last_reissued_at":"2026-07-05T05:45:32.009580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:32.009580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Probability of Agreement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jeppe N{\\o}rregaard, Leon Derczynski","submitted_at":"2022-08-12T08:15:34Z","abstract_excerpt":"Measuring inter-annotator agreement is important for annotation tasks, but many metrics require a fully-annotated set of data, where all annotators annotate all samples. We define Sparse Probability of Agreement, SPA, which estimates the probability of agreement when not all annotator-item-pairs are available. We show that under certain conditions, SPA is an unbiased estimator, and we provide multiple weighing schemes for handling data with various degrees of annotation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06161","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/2208.06161/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":"2208.06161","created_at":"2026-07-05T05:45:32.009647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.06161v2","created_at":"2026-07-05T05:45:32.009647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06161","created_at":"2026-07-05T05:45:32.009647+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6JANFPE3XAY","created_at":"2026-07-05T05:45:32.009647+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6JANFPE3XAYV2Q6","created_at":"2026-07-05T05:45:32.009647+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6JANFPE","created_at":"2026-07-05T05:45:32.009647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17653","citing_title":"QuMAB: Query-based Multi-Annotator Behavior Modeling with Reliability under Sparse Labels","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK","json":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK.json","graph_json":"https://pith.science/api/pith-number/I6JANFPE3XAYV2Q6O5WC4A6JNK/graph.json","events_json":"https://pith.science/api/pith-number/I6JANFPE3XAYV2Q6O5WC4A6JNK/events.json","paper":"https://pith.science/paper/I6JANFPE"},"agent_actions":{"view_html":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK","download_json":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK.json","view_paper":"https://pith.science/paper/I6JANFPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.06161&json=true","fetch_graph":"https://pith.science/api/pith-number/I6JANFPE3XAYV2Q6O5WC4A6JNK/graph.json","fetch_events":"https://pith.science/api/pith-number/I6JANFPE3XAYV2Q6O5WC4A6JNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK/action/storage_attestation","attest_author":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK/action/author_attestation","sign_citation":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK/action/citation_signature","submit_replication":"https://pith.science/pith/I6JANFPE3XAYV2Q6O5WC4A6JNK/action/replication_record"}},"created_at":"2026-07-05T05:45:32.009647+00:00","updated_at":"2026-07-05T05:45:32.009647+00:00"}