{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MGF4QAAQGFKHAV7KN4JMH2NMA7","short_pith_number":"pith:MGF4QAAQ","canonical_record":{"source":{"id":"2401.11601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T21:21:51Z","cross_cats_sorted":[],"title_canon_sha256":"8ea7a5edc47e8b9bd7bff8cfc0439f161a372b1591b5b9006eeb8bd7c0e6c1c1","abstract_canon_sha256":"41b17d35bac04127d6e7543a5d5912b9fbfac5a4d7dacfe7f43ff93d7a9f2d96"},"schema_version":"1.0"},"canonical_sha256":"618bc8001031547057ea6f12c3e9ac07c7388137723dbd0ec228d65c6d7a56b1","source":{"kind":"arxiv","id":"2401.11601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11601","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11601v1","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11601","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"pith_short_12","alias_value":"MGF4QAAQGFKH","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"pith_short_16","alias_value":"MGF4QAAQGFKHAV7K","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"pith_short_8","alias_value":"MGF4QAAQ","created_at":"2026-07-05T07:36:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MGF4QAAQGFKHAV7KN4JMH2NMA7","target":"record","payload":{"canonical_record":{"source":{"id":"2401.11601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T21:21:51Z","cross_cats_sorted":[],"title_canon_sha256":"8ea7a5edc47e8b9bd7bff8cfc0439f161a372b1591b5b9006eeb8bd7c0e6c1c1","abstract_canon_sha256":"41b17d35bac04127d6e7543a5d5912b9fbfac5a4d7dacfe7f43ff93d7a9f2d96"},"schema_version":"1.0"},"canonical_sha256":"618bc8001031547057ea6f12c3e9ac07c7388137723dbd0ec228d65c6d7a56b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:06.863875Z","signature_b64":"SwEdRy6quEeI+3PUeBcVugZw2hViN81kGWpt1YjT3t8glrH74H9ekO3Ri31eXhHEx8BWlvpilfXQM5eSFGm7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"618bc8001031547057ea6f12c3e9ac07c7388137723dbd0ec228d65c6d7a56b1","last_reissued_at":"2026-07-05T07:36:06.863486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:06.863486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.11601","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"97OBlHQafpIC7dkVNMSztk45e+g4UiZ903ZUHcxRgYfGNIG/0OHqxpHwaMu/LRjet/tGGo9ALjslJ/OuoE45Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:30.712955Z"},"content_sha256":"5847f7906b3e248143e0d1b77883cea549048ae0e61f64d89da501f5d78dc4a2","schema_version":"1.0","event_id":"sha256:5847f7906b3e248143e0d1b77883cea549048ae0e61f64d89da501f5d78dc4a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MGF4QAAQGFKHAV7KN4JMH2NMA7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Evaluation Measures for Evaluating Social Biases in Masked Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yang Liu","submitted_at":"2024-01-21T21:21:51Z","abstract_excerpt":"Many evaluation measures are used to evaluate social biases in masked language models (MLMs). However, we find that these previously proposed evaluation measures are lacking robustness in scenarios with limited datasets. This is because these measures are obtained by comparing the pseudo-log-likelihood (PLL) scores of the stereotypical and anti-stereotypical samples using an indicator function. The disadvantage is the limited mining of the PLL score sets without capturing its distributional information. In this paper, we represent a PLL score set as a Gaussian distribution and use Kullback Lei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11601","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/2401.11601/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SBcnWOopHskYxkUZ/tdRIOLrey8dpS9Ymjiiq7K9lTwv/D8+5yddBDmAaqVDd5NF2uFlbd92Din4F3oBbjVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:30.713501Z"},"content_sha256":"f57f63a6f0ba45066b79c6a6519941c3d4ff6ba2ef946cd2f58151cab5896491","schema_version":"1.0","event_id":"sha256:f57f63a6f0ba45066b79c6a6519941c3d4ff6ba2ef946cd2f58151cab5896491"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGF4QAAQGFKHAV7KN4JMH2NMA7/bundle.json","state_url":"https://pith.science/pith/MGF4QAAQGFKHAV7KN4JMH2NMA7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGF4QAAQGFKHAV7KN4JMH2NMA7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T13:16:30Z","links":{"resolver":"https://pith.science/pith/MGF4QAAQGFKHAV7KN4JMH2NMA7","bundle":"https://pith.science/pith/MGF4QAAQGFKHAV7KN4JMH2NMA7/bundle.json","state":"https://pith.science/pith/MGF4QAAQGFKHAV7KN4JMH2NMA7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGF4QAAQGFKHAV7KN4JMH2NMA7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MGF4QAAQGFKHAV7KN4JMH2NMA7","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":"41b17d35bac04127d6e7543a5d5912b9fbfac5a4d7dacfe7f43ff93d7a9f2d96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T21:21:51Z","title_canon_sha256":"8ea7a5edc47e8b9bd7bff8cfc0439f161a372b1591b5b9006eeb8bd7c0e6c1c1"},"schema_version":"1.0","source":{"id":"2401.11601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11601","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11601v1","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11601","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"pith_short_12","alias_value":"MGF4QAAQGFKH","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"pith_short_16","alias_value":"MGF4QAAQGFKHAV7K","created_at":"2026-07-05T07:36:06Z"},{"alias_kind":"pith_short_8","alias_value":"MGF4QAAQ","created_at":"2026-07-05T07:36:06Z"}],"graph_snapshots":[{"event_id":"sha256:f57f63a6f0ba45066b79c6a6519941c3d4ff6ba2ef946cd2f58151cab5896491","target":"graph","created_at":"2026-07-05T07:36:06Z","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/2401.11601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many evaluation measures are used to evaluate social biases in masked language models (MLMs). However, we find that these previously proposed evaluation measures are lacking robustness in scenarios with limited datasets. This is because these measures are obtained by comparing the pseudo-log-likelihood (PLL) scores of the stereotypical and anti-stereotypical samples using an indicator function. The disadvantage is the limited mining of the PLL score sets without capturing its distributional information. In this paper, we represent a PLL score set as a Gaussian distribution and use Kullback Lei","authors_text":"Yang Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T21:21:51Z","title":"Robust Evaluation Measures for Evaluating Social Biases in Masked Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11601","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":"sha256:5847f7906b3e248143e0d1b77883cea549048ae0e61f64d89da501f5d78dc4a2","target":"record","created_at":"2026-07-05T07:36:06Z","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":"41b17d35bac04127d6e7543a5d5912b9fbfac5a4d7dacfe7f43ff93d7a9f2d96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T21:21:51Z","title_canon_sha256":"8ea7a5edc47e8b9bd7bff8cfc0439f161a372b1591b5b9006eeb8bd7c0e6c1c1"},"schema_version":"1.0","source":{"id":"2401.11601","kind":"arxiv","version":1}},"canonical_sha256":"618bc8001031547057ea6f12c3e9ac07c7388137723dbd0ec228d65c6d7a56b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"618bc8001031547057ea6f12c3e9ac07c7388137723dbd0ec228d65c6d7a56b1","first_computed_at":"2026-07-05T07:36:06.863486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:06.863486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SwEdRy6quEeI+3PUeBcVugZw2hViN81kGWpt1YjT3t8glrH74H9ekO3Ri31eXhHEx8BWlvpilfXQM5eSFGm7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:06.863875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5847f7906b3e248143e0d1b77883cea549048ae0e61f64d89da501f5d78dc4a2","sha256:f57f63a6f0ba45066b79c6a6519941c3d4ff6ba2ef946cd2f58151cab5896491"],"state_sha256":"4583d43a3a0aaf60ae1c87de25ad6322f8f1d7ce697ca1e7a2b43b69fd20730b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udKa6BRGZUW6EGwgROEc6OCnfSCZVnitOgPM5G6DDMN/FEMRZwkGcFVUViS7r0j+P0YKFtJPPiNQD4hSq7GbBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:16:30.716907Z","bundle_sha256":"2a611813582ccfd6808e659c3238a095be5b379dd3b98ec2361810ac314522b9"}}