{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4SJL6QAU4CMCM6NKHRZHK37AGY","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":"31f1653130d17ec831b38f6eb18cb39662c02d7a8371f1476d66a349ad38b5e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T02:48:58Z","title_canon_sha256":"eb4821fe7ddd9957b82b7f62bf80f1de22f305ee8f6924e8b9936e797d798a91"},"schema_version":"1.0","source":{"id":"2606.24080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24080","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24080v1","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24080","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_12","alias_value":"4SJL6QAU4CMC","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_16","alias_value":"4SJL6QAU4CMCM6NK","created_at":"2026-06-24T01:14:39Z"},{"alias_kind":"pith_short_8","alias_value":"4SJL6QAU","created_at":"2026-06-24T01:14:39Z"}],"graph_snapshots":[{"event_id":"sha256:499189f317b5efc6271ac8c11de5937d5d4ea293b63c41f470b54480c23ba325","target":"graph","created_at":"2026-06-24T01:14:39Z","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/2606.24080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thousands of languages are spoken worldwide, yet many remain under-resourced for Automatic Speech Recognition (ASR) due to the limited availability of high-quality transcribed speech data. Collecting accurate transcriptions is often costly and labor-intensive, particularly for low-resource languages. In this work, we investigate the use of aligned audio-image pairs to adapt pretrained audio encoders without requiring transcription data before supervised fine-tuning. Our proposed representation alignment stage is introduced between large-scale pretraining and supervised ASR fine-tuning. Specifi","authors_text":"Nihar Desai, Prasanta Kumar Ghosh, Sujith Pulikodan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T02:48:58Z","title":"Audio--Image Alignment as a Continued-Pretraining Stage Improves Low-Resource ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24080","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":"sha256:894c4257a0b40350be8fe8eb498a4c12864dec297206f4a3b860cabce23f520e","target":"record","created_at":"2026-06-24T01:14:39Z","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":"31f1653130d17ec831b38f6eb18cb39662c02d7a8371f1476d66a349ad38b5e9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-23T02:48:58Z","title_canon_sha256":"eb4821fe7ddd9957b82b7f62bf80f1de22f305ee8f6924e8b9936e797d798a91"},"schema_version":"1.0","source":{"id":"2606.24080","kind":"arxiv","version":1}},"canonical_sha256":"e492bf4014e0982679aa3c72756fe03611e5c35567c3ea9ee0d01d06c03bb7d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e492bf4014e0982679aa3c72756fe03611e5c35567c3ea9ee0d01d06c03bb7d4","first_computed_at":"2026-06-24T01:14:39.779447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:39.779447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0/Jw5tAfvxaP06uZgExlRmbIt0ZqjUJLxp+/0VGp5gRurvBt5RYPOaE75TUX2O1Y2iD8pDNXUclT9aNLMbObDQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:39.779830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:894c4257a0b40350be8fe8eb498a4c12864dec297206f4a3b860cabce23f520e","sha256:499189f317b5efc6271ac8c11de5937d5d4ea293b63c41f470b54480c23ba325"],"state_sha256":"d344259a365634c7b7b66bfa56557d68d8aedef0ab53ba1ba6a475f7996fd821"}