{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TR2X4UW7B7LJ56LA5AZ6F7DNKF","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":"b8a44da477cd634c14ac235a16d397f665b910316092ebb11d0d366ccf528032","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T15:23:07Z","title_canon_sha256":"828fe36912983203f7b5df8b6e97ea03c73748f8831defd086483f1d8cab4362"},"schema_version":"1.0","source":{"id":"2506.13596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13596","created_at":"2026-07-05T11:32:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13596v2","created_at":"2026-07-05T11:32:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13596","created_at":"2026-07-05T11:32:31Z"},{"alias_kind":"pith_short_12","alias_value":"TR2X4UW7B7LJ","created_at":"2026-07-05T11:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"TR2X4UW7B7LJ56LA","created_at":"2026-07-05T11:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"TR2X4UW7","created_at":"2026-07-05T11:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:777f29ba5efe5af616ea3ae3d127053ecbea946419c224347be373dc9b84d063","target":"graph","created_at":"2026-07-05T11:32:31Z","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/2506.13596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents our system for the MLC-SLM Challenge 2025, focusing on multilingual speech recognition and language modeling with large language models (LLMs). Our approach combines a fine-tuned Whisper-large-v3 encoder with efficient projector architectures and various decoder configurations. We employ a three-stage training methodology that progressively optimizes the encoder, projector, and LLM components. Our system achieves competitive performance with a private test average WER/CER result of 16.63% using the Gemma3-12B and 18.6% using the Qwen2.5-7B as decoder-only language model.","authors_text":"Huy-Dat Tran, Long-Vu Hoang, Tuan Nguyen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T15:23:07Z","title":"Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13596","kind":"arxiv","version":2},"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:eb6cb3be795a1c69d2dd2de2320096b51de9aa62292a7745af272616328b54b2","target":"record","created_at":"2026-07-05T11:32:31Z","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":"b8a44da477cd634c14ac235a16d397f665b910316092ebb11d0d366ccf528032","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T15:23:07Z","title_canon_sha256":"828fe36912983203f7b5df8b6e97ea03c73748f8831defd086483f1d8cab4362"},"schema_version":"1.0","source":{"id":"2506.13596","kind":"arxiv","version":2}},"canonical_sha256":"9c757e52df0fd69ef960e833e2fc6d5164f311d5ccd4ee7724801bce77115e38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c757e52df0fd69ef960e833e2fc6d5164f311d5ccd4ee7724801bce77115e38","first_computed_at":"2026-07-05T11:32:31.113095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:31.113095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q/TqvfzcgP2v4A/Nv2Z8xnMcZql3bik9dPOxSNzSZWJYJPGuOQKZ8LsxrgWYzn8K6SYiqk4MO49M55ttdfqsBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:31.113604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb6cb3be795a1c69d2dd2de2320096b51de9aa62292a7745af272616328b54b2","sha256:777f29ba5efe5af616ea3ae3d127053ecbea946419c224347be373dc9b84d063"],"state_sha256":"de0bf8de87d03a0c70378c31f6678193c9851a76c84b69e6d2f41b2a15b37e45"}