{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VD6Y2IRDDY426HWEX2I6PD4QAO","short_pith_number":"pith:VD6Y2IRD","canonical_record":{"source":{"id":"2410.11005","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T18:44:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4af49b1ad258d19f51798a5d3004693429063a350f7c5265ecc458255545d7eb","abstract_canon_sha256":"b293ad81a4a2d6cbe51f44b25508ab9a6ca2aa5ec239bb10c9762011474ee4f5"},"schema_version":"1.0"},"canonical_sha256":"a8fd8d22231e39af1ec4be91e78f9003b5dfec34cc88db158e9d91a375b709d8","source":{"kind":"arxiv","id":"2410.11005","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11005","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11005v3","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11005","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"VD6Y2IRDDY42","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"VD6Y2IRDDY426HWE","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"VD6Y2IRD","created_at":"2026-07-05T11:18:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VD6Y2IRDDY426HWEX2I6PD4QAO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11005","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T18:44:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4af49b1ad258d19f51798a5d3004693429063a350f7c5265ecc458255545d7eb","abstract_canon_sha256":"b293ad81a4a2d6cbe51f44b25508ab9a6ca2aa5ec239bb10c9762011474ee4f5"},"schema_version":"1.0"},"canonical_sha256":"a8fd8d22231e39af1ec4be91e78f9003b5dfec34cc88db158e9d91a375b709d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:14.858766Z","signature_b64":"yNieZ6aHtt9f0wbbxmPuSFmmh2H06LLHJrS90otZCTOBIGM0vu9ekyCJNiL9/KpLIHaW4MRoYzqLCDCwEdihBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8fd8d22231e39af1ec4be91e78f9003b5dfec34cc88db158e9d91a375b709d8","last_reissued_at":"2026-07-05T11:18:14.858241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:14.858241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11005","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":"2026-07-05T11:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyNooaHqm0HYoIhTTb9a33+Vml53LWHzsoEu01N93woJtnSAxRVp0DRArW8TkH0JhRKxC0CxXbFAx0aia1nSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:30:45.786988Z"},"content_sha256":"f4ac5430545f7970a1b94c6024cbf9ca80a06908d375c2dcc7422cd98609714f","schema_version":"1.0","event_id":"sha256:f4ac5430545f7970a1b94c6024cbf9ca80a06908d375c2dcc7422cd98609714f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VD6Y2IRDDY426HWEX2I6PD4QAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adrian de Wynter, Emanuele La Malfa, Fangru Lin, Furu Wei, Janet B. Pierrehumbert, Michael Wooldridge, Shaoguang Mao, Si-Qing Chen, Valentin Hofmann, Xun Wang","submitted_at":"2024-10-14T18:44:23Z","abstract_excerpt":"Language is not monolithic. While benchmarks, including those designed for multiple languages, are often used as proxies to evaluate the performance of Large Language Models (LLMs), they tend to overlook the nuances of within-language variation and thus fail to model the experience of speakers of non-standard dialects. Focusing on African American Vernacular English (AAVE), we present the first study aimed at objectively assessing the fairness and robustness of LLMs in handling dialects across canonical reasoning tasks, including algorithm, math, logic, and integrated reasoning. We introduce R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11005","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/2410.11005/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":"2026-07-05T11:18:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jyG+ePYNuUGhraihtvOeLNOEtc2aF8Sos0hlan8mF6c6/MB9TtxbGqIKOQeoFx7T9cG7BiNx1EODsr3kNlSlAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:30:45.787472Z"},"content_sha256":"5a212b5981bbd1b100ffc1d4bed8d66703014f2b6ca9651c9f9322120ac8b745","schema_version":"1.0","event_id":"sha256:5a212b5981bbd1b100ffc1d4bed8d66703014f2b6ca9651c9f9322120ac8b745"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VD6Y2IRDDY426HWEX2I6PD4QAO/bundle.json","state_url":"https://pith.science/pith/VD6Y2IRDDY426HWEX2I6PD4QAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VD6Y2IRDDY426HWEX2I6PD4QAO/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":"2026-07-07T05:30:45Z","links":{"resolver":"https://pith.science/pith/VD6Y2IRDDY426HWEX2I6PD4QAO","bundle":"https://pith.science/pith/VD6Y2IRDDY426HWEX2I6PD4QAO/bundle.json","state":"https://pith.science/pith/VD6Y2IRDDY426HWEX2I6PD4QAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VD6Y2IRDDY426HWEX2I6PD4QAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VD6Y2IRDDY426HWEX2I6PD4QAO","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":"b293ad81a4a2d6cbe51f44b25508ab9a6ca2aa5ec239bb10c9762011474ee4f5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T18:44:23Z","title_canon_sha256":"4af49b1ad258d19f51798a5d3004693429063a350f7c5265ecc458255545d7eb"},"schema_version":"1.0","source":{"id":"2410.11005","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11005","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11005v3","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11005","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"VD6Y2IRDDY42","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"VD6Y2IRDDY426HWE","created_at":"2026-07-05T11:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"VD6Y2IRD","created_at":"2026-07-05T11:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:5a212b5981bbd1b100ffc1d4bed8d66703014f2b6ca9651c9f9322120ac8b745","target":"graph","created_at":"2026-07-05T11:18:14Z","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/2410.11005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language is not monolithic. While benchmarks, including those designed for multiple languages, are often used as proxies to evaluate the performance of Large Language Models (LLMs), they tend to overlook the nuances of within-language variation and thus fail to model the experience of speakers of non-standard dialects. Focusing on African American Vernacular English (AAVE), we present the first study aimed at objectively assessing the fairness and robustness of LLMs in handling dialects across canonical reasoning tasks, including algorithm, math, logic, and integrated reasoning. We introduce R","authors_text":"Adrian de Wynter, Emanuele La Malfa, Fangru Lin, Furu Wei, Janet B. Pierrehumbert, Michael Wooldridge, Shaoguang Mao, Si-Qing Chen, Valentin Hofmann, Xun Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T18:44:23Z","title":"Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11005","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:f4ac5430545f7970a1b94c6024cbf9ca80a06908d375c2dcc7422cd98609714f","target":"record","created_at":"2026-07-05T11:18:14Z","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":"b293ad81a4a2d6cbe51f44b25508ab9a6ca2aa5ec239bb10c9762011474ee4f5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-14T18:44:23Z","title_canon_sha256":"4af49b1ad258d19f51798a5d3004693429063a350f7c5265ecc458255545d7eb"},"schema_version":"1.0","source":{"id":"2410.11005","kind":"arxiv","version":3}},"canonical_sha256":"a8fd8d22231e39af1ec4be91e78f9003b5dfec34cc88db158e9d91a375b709d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8fd8d22231e39af1ec4be91e78f9003b5dfec34cc88db158e9d91a375b709d8","first_computed_at":"2026-07-05T11:18:14.858241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:14.858241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yNieZ6aHtt9f0wbbxmPuSFmmh2H06LLHJrS90otZCTOBIGM0vu9ekyCJNiL9/KpLIHaW4MRoYzqLCDCwEdihBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:14.858766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11005","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4ac5430545f7970a1b94c6024cbf9ca80a06908d375c2dcc7422cd98609714f","sha256:5a212b5981bbd1b100ffc1d4bed8d66703014f2b6ca9651c9f9322120ac8b745"],"state_sha256":"50995df509901f6ab9b2dea3b93fd741a58d35083735291e57094062e827d7a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdbzN2yRy9oYHeVj7WFjoAGjlClhuSAcsvu329lFXuCJ6qfASCkvonAYAATF/H22VOhYdm4nQz/gScBKRfZ5CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:30:45.792054Z","bundle_sha256":"560b5d4bb340007ce87cf17562aea06e5e4aa38aaba280dad72d6bae3b2ec76c"}}