{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6U74O6SBC6ADS2UNLUSCNCL3VW","short_pith_number":"pith:6U74O6SB","canonical_record":{"source":{"id":"2505.12349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T10:29:24Z","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"title_canon_sha256":"3997d09ff112bb96e911be7c50efb0990b0b3622b13f581ed2cae31fa699141a","abstract_canon_sha256":"4bed7148f6e63cc72f5d5dcc2f19dfbffe5ae0cf843199fdddf3e5f172e4aea1"},"schema_version":"1.0"},"canonical_sha256":"f53fc77a411780396a8d5d2426897badbd029b2230b7ef56c835cbbd71e63491","source":{"kind":"arxiv","id":"2505.12349","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12349","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12349v1","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12349","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"6U74O6SBC6AD","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"6U74O6SBC6ADS2UN","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"6U74O6SB","created_at":"2026-07-05T11:05:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6U74O6SBC6ADS2UNLUSCNCL3VW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12349","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T10:29:24Z","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"title_canon_sha256":"3997d09ff112bb96e911be7c50efb0990b0b3622b13f581ed2cae31fa699141a","abstract_canon_sha256":"4bed7148f6e63cc72f5d5dcc2f19dfbffe5ae0cf843199fdddf3e5f172e4aea1"},"schema_version":"1.0"},"canonical_sha256":"f53fc77a411780396a8d5d2426897badbd029b2230b7ef56c835cbbd71e63491","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:02.799968Z","signature_b64":"gbnW956Q67/gmqMUgNk+727wdnKha73tbgdEJk4qWL/+DjODoSlmSV/+y7PbFMe21WSa5m6XDXRhze3vFawdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f53fc77a411780396a8d5d2426897badbd029b2230b7ef56c835cbbd71e63491","last_reissued_at":"2026-07-05T11:05:02.799435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:02.799435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12349","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":"2026-07-05T11:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sCZQJzqhkjzsGQ02qX7/7X91oJHMebFSeim2nyVea36shWtfqpNfuT6f5Qj8zy/QrAIUFrRNixJPyD9IzKDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:34:55.848307Z"},"content_sha256":"2d71ff218c0d151a04903fbcd5ff75568008ab8c29d3809bc5c5783cdf493352","schema_version":"1.0","event_id":"sha256:2d71ff218c0d151a04903fbcd5ff75568008ab8c29d3809bc5c5783cdf493352"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6U74O6SBC6ADS2UNLUSCNCL3VW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Axel Abels, Tom Lenaerts","submitted_at":"2025-05-18T10:29:24Z","abstract_excerpt":"Despite their performance, large language models (LLMs) can inadvertently perpetuate biases found in the data they are trained on. By analyzing LLM responses to bias-eliciting headlines, we find that these models often mirror human biases. To address this, we explore crowd-based strategies for mitigating bias through response aggregation. We first demonstrate that simply averaging responses from multiple LLMs, intended to leverage the \"wisdom of the crowd\", can exacerbate existing biases due to the limited diversity within LLM crowds. In contrast, we show that locally weighted aggregation meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12349","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/2505.12349/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":"2026-07-05T11:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PHpF8yjLwsFRaqv9ObLqO6uHdHra0bgt8e6623IQZU43GW+SksnX6bKD2lcYQRQUbcAuOmzgins+k551V+RXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:34:55.848909Z"},"content_sha256":"44bd81ab9de8be3f3b8e1037f86f98f6c701220bc143f3ae75924932dd0916f2","schema_version":"1.0","event_id":"sha256:44bd81ab9de8be3f3b8e1037f86f98f6c701220bc143f3ae75924932dd0916f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6U74O6SBC6ADS2UNLUSCNCL3VW/bundle.json","state_url":"https://pith.science/pith/6U74O6SBC6ADS2UNLUSCNCL3VW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6U74O6SBC6ADS2UNLUSCNCL3VW/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":"2026-08-06T19:34:55Z","links":{"resolver":"https://pith.science/pith/6U74O6SBC6ADS2UNLUSCNCL3VW","bundle":"https://pith.science/pith/6U74O6SBC6ADS2UNLUSCNCL3VW/bundle.json","state":"https://pith.science/pith/6U74O6SBC6ADS2UNLUSCNCL3VW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6U74O6SBC6ADS2UNLUSCNCL3VW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6U74O6SBC6ADS2UNLUSCNCL3VW","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":"4bed7148f6e63cc72f5d5dcc2f19dfbffe5ae0cf843199fdddf3e5f172e4aea1","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T10:29:24Z","title_canon_sha256":"3997d09ff112bb96e911be7c50efb0990b0b3622b13f581ed2cae31fa699141a"},"schema_version":"1.0","source":{"id":"2505.12349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12349","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12349v1","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12349","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"6U74O6SBC6AD","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"6U74O6SBC6ADS2UN","created_at":"2026-07-05T11:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"6U74O6SB","created_at":"2026-07-05T11:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:44bd81ab9de8be3f3b8e1037f86f98f6c701220bc143f3ae75924932dd0916f2","target":"graph","created_at":"2026-07-05T11:05:02Z","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/2505.12349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their performance, large language models (LLMs) can inadvertently perpetuate biases found in the data they are trained on. By analyzing LLM responses to bias-eliciting headlines, we find that these models often mirror human biases. To address this, we explore crowd-based strategies for mitigating bias through response aggregation. We first demonstrate that simply averaging responses from multiple LLMs, intended to leverage the \"wisdom of the crowd\", can exacerbate existing biases due to the limited diversity within LLM crowds. In contrast, we show that locally weighted aggregation meth","authors_text":"Axel Abels, Tom Lenaerts","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T10:29:24Z","title":"Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12349","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":"sha256:2d71ff218c0d151a04903fbcd5ff75568008ab8c29d3809bc5c5783cdf493352","target":"record","created_at":"2026-07-05T11:05:02Z","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":"4bed7148f6e63cc72f5d5dcc2f19dfbffe5ae0cf843199fdddf3e5f172e4aea1","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T10:29:24Z","title_canon_sha256":"3997d09ff112bb96e911be7c50efb0990b0b3622b13f581ed2cae31fa699141a"},"schema_version":"1.0","source":{"id":"2505.12349","kind":"arxiv","version":1}},"canonical_sha256":"f53fc77a411780396a8d5d2426897badbd029b2230b7ef56c835cbbd71e63491","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f53fc77a411780396a8d5d2426897badbd029b2230b7ef56c835cbbd71e63491","first_computed_at":"2026-07-05T11:05:02.799435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:02.799435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gbnW956Q67/gmqMUgNk+727wdnKha73tbgdEJk4qWL/+DjODoSlmSV/+y7PbFMe21WSa5m6XDXRhze3vFawdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:02.799968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d71ff218c0d151a04903fbcd5ff75568008ab8c29d3809bc5c5783cdf493352","sha256:44bd81ab9de8be3f3b8e1037f86f98f6c701220bc143f3ae75924932dd0916f2"],"state_sha256":"3304419a26708d5076c5c04913aa5e5321a1e7a43ecd0816cf09ebf5ee89aaea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nk8o6pCXTFt+csstkQuhmhyCGvMI08yTXVpu9a0iPHqq+UcKbM8ieg+4CAw8QA69EjowGD+QiSfLOYQ6jtGjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:34:55.853443Z","bundle_sha256":"b5a475163586e497e0a7c0b27c5ce9539fe3d33caa84f7242800d5bdca7e1732"}}