{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZEV5662LEFUZP6CJLI555G2PLD","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":"d0b5e3868064c0893c6ca3c40a4e211fe9b7095ea6e72f3399ad884e1d88e137","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-11T15:48:03Z","title_canon_sha256":"048bb8f52c622b0ae68e5e57c14a2938d2da46e6704187d67a915e23e8ee7bad"},"schema_version":"1.0","source":{"id":"2607.10371","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10371","created_at":"2026-07-14T01:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10371v1","created_at":"2026-07-14T01:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10371","created_at":"2026-07-14T01:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZEV5662LEFUZ","created_at":"2026-07-14T01:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZEV5662LEFUZP6CJ","created_at":"2026-07-14T01:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZEV5662L","created_at":"2026-07-14T01:21:12Z"}],"graph_snapshots":[{"event_id":"sha256:0895bb6e68fcc7dc679d86ebabcca8fcf6ff01d003bd114afb46761baedc5ff2","target":"graph","created_at":"2026-07-14T01:21:12Z","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/2607.10371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent scaling successes, multilingual ASR performance remains highly uneven, with long-tail languages suffering from severe data scarcity. This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages (Kazakh, Kyrgyz, Uzbek). We present GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective. Crucially, we introduce a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-language dominance. In controlled compa","authors_text":"Aleksandr Kutsakov, Alexandr Maximenko, Andrei Kuzmenko, Dmitrii Bolotov, Fyodor Minkin, Georgii Gospodinov, Oleg Kutuzov, Pavel Bogomolov","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-11T15:48:03Z","title":"GigaAM Multilingual: Foundation Model for Underrepresented Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10371","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":"sha256:61642b551f7e837ad2a039cfbb4e2718a472bcbc7655ac94f7ba218a98115367","target":"record","created_at":"2026-07-14T01:21:12Z","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":"d0b5e3868064c0893c6ca3c40a4e211fe9b7095ea6e72f3399ad884e1d88e137","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-11T15:48:03Z","title_canon_sha256":"048bb8f52c622b0ae68e5e57c14a2938d2da46e6704187d67a915e23e8ee7bad"},"schema_version":"1.0","source":{"id":"2607.10371","kind":"arxiv","version":1}},"canonical_sha256":"c92bdf7b4b216997f8495a3bde9b4f58f3c911bd475b716812e7c70ac44614a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c92bdf7b4b216997f8495a3bde9b4f58f3c911bd475b716812e7c70ac44614a8","first_computed_at":"2026-07-14T01:21:12.518901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:12.518901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ey2mjs5MLzXW1LgoBp2RVVybbUMa8gR7cl5Q9Gq3SxMT2n+eeCg3AfO3pnRDFMamLfrBKSV1WgqmPYkgxRbpDQ==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:12.519783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10371","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61642b551f7e837ad2a039cfbb4e2718a472bcbc7655ac94f7ba218a98115367","sha256:0895bb6e68fcc7dc679d86ebabcca8fcf6ff01d003bd114afb46761baedc5ff2"],"state_sha256":"bfd859e48592747eace076c1974c0249380f3a8aad5f36fa29945c2932265103"}