{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SVCSTTVCUZKI5SY6LHDI2NZPHK","short_pith_number":"pith:SVCSTTVC","schema_version":"1.0","canonical_sha256":"954529cea2a6548ecb1e59c68d372f3a885556cf103d4315c055b10643b59f53","source":{"kind":"arxiv","id":"2608.05510","version":1},"attestation_state":"computed","paper":{"title":"Different Perturbations, Different Mechanisms: Understanding Continued Pre-training for Zero-Shot Dialect Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aarohi Srivastava, David Chiang","submitted_at":"2026-08-06T01:23:51Z","abstract_excerpt":"Dialectal variation remains a major challenge for multilingual language models. Perturbation-based continued pre-training (CPT) has emerged as a promising approach to improving robustness, yet existing work largely evaluates individual perturbation strategies in isolation and provides limited insight into why they work. We present a systematic study of perturbation-based CPT for multilingual dialect robustness in LLMs, comparing six training conditions across nine German, Italian, and Arabic dialect tasks. Perturbation-based CPT, especially character-noised CPT, consistently improves zero-shot"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.05510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T01:23:51Z","cross_cats_sorted":[],"title_canon_sha256":"0dde08cc84a375489c1f874b6896d9e2f438391953006a4c54604f37a2752a61","abstract_canon_sha256":"36be0ad90b63294f85891613052b6529267414e24a026710e0db506aca46651a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:48:00.098247Z","signature_b64":"lGK4vxEz3izF2Le0jM7X0Sduz6/9pZmd64nY7MJo0ztwzx0LE8MGIU4Fw0vFahXKt48JD6ihj2bYQgYTWMySDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"954529cea2a6548ecb1e59c68d372f3a885556cf103d4315c055b10643b59f53","last_reissued_at":"2026-08-07T00:48:00.096756Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:48:00.096756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Different Perturbations, Different Mechanisms: Understanding Continued Pre-training for Zero-Shot Dialect Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aarohi Srivastava, David Chiang","submitted_at":"2026-08-06T01:23:51Z","abstract_excerpt":"Dialectal variation remains a major challenge for multilingual language models. Perturbation-based continued pre-training (CPT) has emerged as a promising approach to improving robustness, yet existing work largely evaluates individual perturbation strategies in isolation and provides limited insight into why they work. We present a systematic study of perturbation-based CPT for multilingual dialect robustness in LLMs, comparing six training conditions across nine German, Italian, and Arabic dialect tasks. Perturbation-based CPT, especially character-noised CPT, consistently improves zero-shot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05510","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/2608.05510/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.05510","created_at":"2026-08-07T00:48:00.098160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05510v1","created_at":"2026-08-07T00:48:00.098160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05510","created_at":"2026-08-07T00:48:00.098160+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVCSTTVCUZKI","created_at":"2026-08-07T00:48:00.098160+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVCSTTVCUZKI5SY6","created_at":"2026-08-07T00:48:00.098160+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVCSTTVC","created_at":"2026-08-07T00:48:00.098160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK","json":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK.json","graph_json":"https://pith.science/api/pith-number/SVCSTTVCUZKI5SY6LHDI2NZPHK/graph.json","events_json":"https://pith.science/api/pith-number/SVCSTTVCUZKI5SY6LHDI2NZPHK/events.json","paper":"https://pith.science/paper/SVCSTTVC"},"agent_actions":{"view_html":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK","download_json":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK.json","view_paper":"https://pith.science/paper/SVCSTTVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05510&json=true","fetch_graph":"https://pith.science/api/pith-number/SVCSTTVCUZKI5SY6LHDI2NZPHK/graph.json","fetch_events":"https://pith.science/api/pith-number/SVCSTTVCUZKI5SY6LHDI2NZPHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK/action/storage_attestation","attest_author":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK/action/author_attestation","sign_citation":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK/action/citation_signature","submit_replication":"https://pith.science/pith/SVCSTTVCUZKI5SY6LHDI2NZPHK/action/replication_record"}},"created_at":"2026-08-07T00:48:00.098160+00:00","updated_at":"2026-08-07T00:48:00.098160+00:00"}