{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KRX662XDVC7Y7TE7Q4IDKQJK6V","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":"7b973eec6a966459691f837557068620f16b07d9a8f9822a9fa96269edf2253b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T15:55:23Z","title_canon_sha256":"b462dd2589e4aeaa70487db88e21445f92e4f8521777c2c2852771e9de6cc659"},"schema_version":"1.0","source":{"id":"2606.13507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13507","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13507v1","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13507","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"pith_short_12","alias_value":"KRX662XDVC7Y","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"pith_short_16","alias_value":"KRX662XDVC7Y7TE7","created_at":"2026-06-12T01:10:07Z"},{"alias_kind":"pith_short_8","alias_value":"KRX662XD","created_at":"2026-06-12T01:10:07Z"}],"graph_snapshots":[{"event_id":"sha256:3951effd0b79e8c5f1c3758780bfc3768319e736bb8e44c8298b9e43293b62cc","target":"graph","created_at":"2026-06-12T01:10:07Z","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/2606.13507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale mined corpora provide abundant training data for end-to-end speech-to-speech translation (S2ST) but may contain noise, misalignment, and semantic errors. Filtering noisy data is crucial to maintain robust speech translation performance. We study how to train an audio-language model to make keep/drop decisions on paired speech directly from audio. To obtain reliable supervision without manual labels, we adopt a scalable two-stage Rank-to-Distill strategy. A lightweight ranker generates keep/drop pseudo-labels from noisy speech pairs, then trains an audio large language model to pred","authors_text":"Qixu Chen, Satoshi Nakamura","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T15:55:23Z","title":"Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13507","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":"sha256:4f1b2555df0dc311368018e49f8b9bd2e2f6e0a941ff240c1db5370652572d95","target":"record","created_at":"2026-06-12T01:10:07Z","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":"7b973eec6a966459691f837557068620f16b07d9a8f9822a9fa96269edf2253b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-11T15:55:23Z","title_canon_sha256":"b462dd2589e4aeaa70487db88e21445f92e4f8521777c2c2852771e9de6cc659"},"schema_version":"1.0","source":{"id":"2606.13507","kind":"arxiv","version":1}},"canonical_sha256":"546fef6ae3a8bf8fcc9f871035412af55d522aacddd417ff6bcd8ac7fcc55f85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"546fef6ae3a8bf8fcc9f871035412af55d522aacddd417ff6bcd8ac7fcc55f85","first_computed_at":"2026-06-12T01:10:07.381866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:07.381866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wZOPQmiA7RKlysVJyipCO9uItuXkVYobrY+J69wcFyxDX7+1aKut2CIXLGoCEvH4T/9mSN9LxIGUOkkcuOaoAA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:07.382762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f1b2555df0dc311368018e49f8b9bd2e2f6e0a941ff240c1db5370652572d95","sha256:3951effd0b79e8c5f1c3758780bfc3768319e736bb8e44c8298b9e43293b62cc"],"state_sha256":"f46b533f7026660a7b3c964da042238b1a075d2af96b9aeba760f444532682f1"}