{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SSF73N6N2IUAWSUWXNOPMK6AW5","short_pith_number":"pith:SSF73N6N","schema_version":"1.0","canonical_sha256":"948bfdb7cdd2280b4a96bb5cf62bc0b762173a4bd61580d9e692367856b69daf","source":{"kind":"arxiv","id":"2607.27209","version":1},"attestation_state":"computed","paper":{"title":"Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DL","authors_text":"Binyan Xu, Fan Yang, Kehuan Zhang, Xilin Dai","submitted_at":"2026-04-30T10:54:54Z","abstract_excerpt":"Peer review at ML conferences increasingly relies on reviewer scores as the primary decision instrument. As submissions have scaled from thousands to tens of thousands per year, no systematic audit has examined whether this instrument functions uniformly across research areas, or whether acceptance outcomes are in practice shaped by forces that reviewer scores neither capture nor control. This position paper argues that acceptance outcomes are shaped by forces beyond reviewer scores, and that the underlying cause is a measurement design failure, not individual bias. When a fixed numerical scal"},"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":"2607.27209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-04-30T10:54:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d889769b414cc4399eb5368638e909bdb7cc3d80c90b6dddf29fbe22b57fd24c","abstract_canon_sha256":"058eae864f17f27c9cddacefad9a8dbf5af51b368264d28a8ab484bd3688f6d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"948bfdb7cdd2280b4a96bb5cf62bc0b762173a4bd61580d9e692367856b69daf","last_reissued_at":"2026-07-31T00:10:19.791888Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:19.791888Z"},"graph_snapshot":{"paper":{"title":"Reviewer Scores Are Not Comparable Across Research Areas in ML Peer Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DL","authors_text":"Binyan Xu, Fan Yang, Kehuan Zhang, Xilin Dai","submitted_at":"2026-04-30T10:54:54Z","abstract_excerpt":"Peer review at ML conferences increasingly relies on reviewer scores as the primary decision instrument. As submissions have scaled from thousands to tens of thousands per year, no systematic audit has examined whether this instrument functions uniformly across research areas, or whether acceptance outcomes are in practice shaped by forces that reviewer scores neither capture nor control. This position paper argues that acceptance outcomes are shaped by forces beyond reviewer scores, and that the underlying cause is a measurement design failure, not individual bias. When a fixed numerical scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27209","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/2607.27209/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":"2607.27209","created_at":"2026-07-31T00:10:19.794228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27209v1","created_at":"2026-07-31T00:10:19.794228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27209","created_at":"2026-07-31T00:10:19.794228+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSF73N6N2IUA","created_at":"2026-07-31T00:10:19.794228+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSF73N6N2IUAWSUW","created_at":"2026-07-31T00:10:19.794228+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSF73N6N","created_at":"2026-07-31T00:10:19.794228+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/SSF73N6N2IUAWSUWXNOPMK6AW5","json":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5.json","graph_json":"https://pith.science/api/pith-number/SSF73N6N2IUAWSUWXNOPMK6AW5/graph.json","events_json":"https://pith.science/api/pith-number/SSF73N6N2IUAWSUWXNOPMK6AW5/events.json","paper":"https://pith.science/paper/SSF73N6N"},"agent_actions":{"view_html":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5","download_json":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5.json","view_paper":"https://pith.science/paper/SSF73N6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27209&json=true","fetch_graph":"https://pith.science/api/pith-number/SSF73N6N2IUAWSUWXNOPMK6AW5/graph.json","fetch_events":"https://pith.science/api/pith-number/SSF73N6N2IUAWSUWXNOPMK6AW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5/action/storage_attestation","attest_author":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5/action/author_attestation","sign_citation":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5/action/citation_signature","submit_replication":"https://pith.science/pith/SSF73N6N2IUAWSUWXNOPMK6AW5/action/replication_record"}},"created_at":"2026-07-31T00:10:19.794228+00:00","updated_at":"2026-07-31T00:10:19.794228+00:00"}