{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SVCSTTVCUZKI5SY6LHDI2NZPHK","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":"36be0ad90b63294f85891613052b6529267414e24a026710e0db506aca46651a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T01:23:51Z","title_canon_sha256":"0dde08cc84a375489c1f874b6896d9e2f438391953006a4c54604f37a2752a61"},"schema_version":"1.0","source":{"id":"2608.05510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05510","created_at":"2026-08-07T00:48:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05510v1","created_at":"2026-08-07T00:48:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05510","created_at":"2026-08-07T00:48:00Z"},{"alias_kind":"pith_short_12","alias_value":"SVCSTTVCUZKI","created_at":"2026-08-07T00:48:00Z"},{"alias_kind":"pith_short_16","alias_value":"SVCSTTVCUZKI5SY6","created_at":"2026-08-07T00:48:00Z"},{"alias_kind":"pith_short_8","alias_value":"SVCSTTVC","created_at":"2026-08-07T00:48:00Z"}],"graph_snapshots":[{"event_id":"sha256:f36cbbeea1794501e4e54b3db6cb6fcc9bdcc1131d7d0e521d4c9c64d20ddccd","target":"graph","created_at":"2026-08-07T00:48:00Z","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/2608.05510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aarohi Srivastava, David Chiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T01:23:51Z","title":"Different Perturbations, Different Mechanisms: Understanding Continued Pre-training for Zero-Shot Dialect Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05510","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":"sha256:6f590dede19d1d50286569d2e3352315678eb54f9e77e13ff38d3a079c130d50","target":"record","created_at":"2026-08-07T00:48:00Z","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":"36be0ad90b63294f85891613052b6529267414e24a026710e0db506aca46651a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T01:23:51Z","title_canon_sha256":"0dde08cc84a375489c1f874b6896d9e2f438391953006a4c54604f37a2752a61"},"schema_version":"1.0","source":{"id":"2608.05510","kind":"arxiv","version":1}},"canonical_sha256":"954529cea2a6548ecb1e59c68d372f3a885556cf103d4315c055b10643b59f53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"954529cea2a6548ecb1e59c68d372f3a885556cf103d4315c055b10643b59f53","first_computed_at":"2026-08-07T00:48:00.096756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:48:00.096756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lGK4vxEz3izF2Le0jM7X0Sduz6/9pZmd64nY7MJo0ztwzx0LE8MGIU4Fw0vFahXKt48JD6ihj2bYQgYTWMySDQ==","signature_status":"signed_v1","signed_at":"2026-08-07T00:48:00.098247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f590dede19d1d50286569d2e3352315678eb54f9e77e13ff38d3a079c130d50","sha256:f36cbbeea1794501e4e54b3db6cb6fcc9bdcc1131d7d0e521d4c9c64d20ddccd"],"state_sha256":"49724fb06536c11f17079924c165452e3397dae8ccffc8b01ef90f415a34c607"}