{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SWLWFMRMDXLT76I6FFP5MN5OQ6","short_pith_number":"pith:SWLWFMRM","canonical_record":{"source":{"id":"2501.06826","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-01-12T14:39:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7d8075d9217d4c0af996f2d4711262d6ae89fee8acdc5023b437001f0c865c0d","abstract_canon_sha256":"1e54427b6bccdc27e4c958b3bdc3388f88d054d0ca78203ee1c310a9d230ce74"},"schema_version":"1.0"},"canonical_sha256":"959762b22c1dd73ff91e295fd637ae879cefa5a0be8c7fec11b821474aa0b21c","source":{"kind":"arxiv","id":"2501.06826","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06826","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06826v3","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06826","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"SWLWFMRMDXLT","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"SWLWFMRMDXLT76I6","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"SWLWFMRM","created_at":"2026-07-05T11:59:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SWLWFMRMDXLT76I6FFP5MN5OQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06826","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-01-12T14:39:26Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7d8075d9217d4c0af996f2d4711262d6ae89fee8acdc5023b437001f0c865c0d","abstract_canon_sha256":"1e54427b6bccdc27e4c958b3bdc3388f88d054d0ca78203ee1c310a9d230ce74"},"schema_version":"1.0"},"canonical_sha256":"959762b22c1dd73ff91e295fd637ae879cefa5a0be8c7fec11b821474aa0b21c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:10.144123Z","signature_b64":"hGJ7hM6BBTi19Yk2cO3x9RRcQbilgVdglDkTBZRXTIQYB0/3ctVE3r/zy0OwuC80GeuiAOqWfJGoOmeC6EqtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"959762b22c1dd73ff91e295fd637ae879cefa5a0be8c7fec11b821474aa0b21c","last_reissued_at":"2026-07-05T11:59:10.143661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:10.143661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06826","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B4TOUU5ZfrRk5s97YgrM7nc3a0b2vrXstesWRWdrROlbVq0X7hz7nHR/+wAoobUQZ+Qv37HVJHkahdMn7KiIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:26:58.706882Z"},"content_sha256":"34835e13326e9acaa86c9368132bbf27e1c85e8ed80c39c67dcdcce8a549641e","schema_version":"1.0","event_id":"sha256:34835e13326e9acaa86c9368132bbf27e1c85e8ed80c39c67dcdcce8a549641e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SWLWFMRMDXLT76I6FFP5MN5OQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"stat.ME","authors_text":"Barbara Plank, Bolei Ma, Christoph Kern, Frauke Kreuter, Rob Chew, Stephanie Eckman","submitted_at":"2025-01-12T14:39:26Z","abstract_excerpt":"Models trained on crowdsourced annotations may not reflect population views, if those who work as annotators do not represent the broader population. In this paper, we propose PAIR: Population-Aligned Instance Replication, a post-processing method that adjusts training data to better reflect target population characteristics without collecting additional annotations. Using simulation studies on offensive language and hate speech detection with varying annotator compositions, we show that non-representative pools degrade model calibration while leaving accuracy largely unchanged. PAIR corrects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06826","kind":"arxiv","version":3},"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/2501.06826/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":"2026-07-05T11:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"49vFZE6DPL8fmQdrNAI2j8s65Qlq5FanTXRvW7I6/N32ir5DsEUzuxe+IBZShkcQ9jjRyiwMUTUCpEB0SfLSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:26:58.707447Z"},"content_sha256":"24bb150c466de6d363da305d6cf505ee0feb1282de23a8a9911e40ebf39d7aa4","schema_version":"1.0","event_id":"sha256:24bb150c466de6d363da305d6cf505ee0feb1282de23a8a9911e40ebf39d7aa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWLWFMRMDXLT76I6FFP5MN5OQ6/bundle.json","state_url":"https://pith.science/pith/SWLWFMRMDXLT76I6FFP5MN5OQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWLWFMRMDXLT76I6FFP5MN5OQ6/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":"2026-08-18T10:26:58Z","links":{"resolver":"https://pith.science/pith/SWLWFMRMDXLT76I6FFP5MN5OQ6","bundle":"https://pith.science/pith/SWLWFMRMDXLT76I6FFP5MN5OQ6/bundle.json","state":"https://pith.science/pith/SWLWFMRMDXLT76I6FFP5MN5OQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWLWFMRMDXLT76I6FFP5MN5OQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SWLWFMRMDXLT76I6FFP5MN5OQ6","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":"1e54427b6bccdc27e4c958b3bdc3388f88d054d0ca78203ee1c310a9d230ce74","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-01-12T14:39:26Z","title_canon_sha256":"7d8075d9217d4c0af996f2d4711262d6ae89fee8acdc5023b437001f0c865c0d"},"schema_version":"1.0","source":{"id":"2501.06826","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06826","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06826v3","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06826","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"SWLWFMRMDXLT","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"SWLWFMRMDXLT76I6","created_at":"2026-07-05T11:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"SWLWFMRM","created_at":"2026-07-05T11:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:24bb150c466de6d363da305d6cf505ee0feb1282de23a8a9911e40ebf39d7aa4","target":"graph","created_at":"2026-07-05T11:59:10Z","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/2501.06826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Models trained on crowdsourced annotations may not reflect population views, if those who work as annotators do not represent the broader population. In this paper, we propose PAIR: Population-Aligned Instance Replication, a post-processing method that adjusts training data to better reflect target population characteristics without collecting additional annotations. Using simulation studies on offensive language and hate speech detection with varying annotator compositions, we show that non-representative pools degrade model calibration while leaving accuracy largely unchanged. PAIR corrects ","authors_text":"Barbara Plank, Bolei Ma, Christoph Kern, Frauke Kreuter, Rob Chew, Stephanie Eckman","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-01-12T14:39:26Z","title":"Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06826","kind":"arxiv","version":3},"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":"sha256:34835e13326e9acaa86c9368132bbf27e1c85e8ed80c39c67dcdcce8a549641e","target":"record","created_at":"2026-07-05T11:59:10Z","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":"1e54427b6bccdc27e4c958b3bdc3388f88d054d0ca78203ee1c310a9d230ce74","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-01-12T14:39:26Z","title_canon_sha256":"7d8075d9217d4c0af996f2d4711262d6ae89fee8acdc5023b437001f0c865c0d"},"schema_version":"1.0","source":{"id":"2501.06826","kind":"arxiv","version":3}},"canonical_sha256":"959762b22c1dd73ff91e295fd637ae879cefa5a0be8c7fec11b821474aa0b21c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"959762b22c1dd73ff91e295fd637ae879cefa5a0be8c7fec11b821474aa0b21c","first_computed_at":"2026-07-05T11:59:10.143661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:10.143661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hGJ7hM6BBTi19Yk2cO3x9RRcQbilgVdglDkTBZRXTIQYB0/3ctVE3r/zy0OwuC80GeuiAOqWfJGoOmeC6EqtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:10.144123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06826","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34835e13326e9acaa86c9368132bbf27e1c85e8ed80c39c67dcdcce8a549641e","sha256:24bb150c466de6d363da305d6cf505ee0feb1282de23a8a9911e40ebf39d7aa4"],"state_sha256":"9506843c8d90b4a0c97d8d6a130b14e570673e9f852b955aac7e19315e3456c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHQK1mPdS3g/toU0oAVTaLilbp5pqOrNPi3vNQiquGsD1EeyIkcQzCHYpMcpTJ7QfIIDYcup0erySO3J98fkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:26:58.713077Z","bundle_sha256":"870fdfa53d58296484db5d98efe187ceaba34d143318ab19ca53fff840cb8235"}}