{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:27P3IBH5PVHACZUSYJYSYEWBSA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0f76956486d485ae9d6f92aefde0314250e63ce34e1528cb7f8cfbea7880d9ea","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T08:24:11Z","title_canon_sha256":"a3f0b10e2b867e209aa7ffafb8e88312d7fab24c84f8eb4f916ad795e8cda529"},"schema_version":"1.0","source":{"id":"2210.07626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07626","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07626v1","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07626","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"27P3IBH5PVHA","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"27P3IBH5PVHACZUS","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"27P3IBH5","created_at":"2026-07-05T05:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:cc2a97e7cb2cfd290b26c0cc8cc7854246927c79a9a8ece40a8fadbb9f7d5060","target":"graph","created_at":"2026-07-05T05:06:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.07626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic evaluation metrics are crucial to the development of generative systems. In recent years, pre-trained language model (PLM) based metrics, such as BERTScore, have been commonly adopted in various generation tasks. However, it has been demonstrated that PLMs encode a range of stereotypical societal biases, leading to a concern on the fairness of PLMs as metrics. To that end, this work presents the first systematic study on the social bias in PLM-based metrics. We demonstrate that popular PLM-based metrics exhibit significantly higher social bias than traditional metrics on 6 sensitive ","authors_text":"Junliang He, Tianxiang Sun, Xipeng Qiu, Xuanjing Huang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T08:24:11Z","title":"BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07626","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f06fb8cb1998902d925730f60a0e5610490947ed9ab4550d3b3eab453d7f37fc","target":"record","created_at":"2026-07-05T05:06:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0f76956486d485ae9d6f92aefde0314250e63ce34e1528cb7f8cfbea7880d9ea","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T08:24:11Z","title_canon_sha256":"a3f0b10e2b867e209aa7ffafb8e88312d7fab24c84f8eb4f916ad795e8cda529"},"schema_version":"1.0","source":{"id":"2210.07626","kind":"arxiv","version":1}},"canonical_sha256":"d7dfb404fd7d4e016692c2712c12c19030adb75031fe7d65a0ca10604acd428b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7dfb404fd7d4e016692c2712c12c19030adb75031fe7d65a0ca10604acd428b","first_computed_at":"2026-07-05T05:06:39.438998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:39.438998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bb71txcwefSE3e6vMgJy2UzsdbCtifr8AzQGbMoLYzLiBxHCHcNgSJPOpt/epnL0/phtZHG5o8yZOBBca8w1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:39.439387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f06fb8cb1998902d925730f60a0e5610490947ed9ab4550d3b3eab453d7f37fc","sha256:cc2a97e7cb2cfd290b26c0cc8cc7854246927c79a9a8ece40a8fadbb9f7d5060"],"state_sha256":"4a6b584cd44346352e2387f4b8e3b9c0d838448fd4bf89171605f923565d0e77"}