{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GTAIBYWH7B2FVP43VQ4YSPICTK","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":"5e0faa65ea52a02ae645c326d44992757595f3ea8fbab66b71bec070bc31cf69","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T17:59:09Z","title_canon_sha256":"7ca5a86b2c84d20aa0f8561252a79210eff87797d222910909b360f59154ccf7"},"schema_version":"1.0","source":{"id":"2509.10452","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10452","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10452v2","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10452","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_12","alias_value":"GTAIBYWH7B2F","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_16","alias_value":"GTAIBYWH7B2FVP43","created_at":"2026-05-26T02:05:01Z"},{"alias_kind":"pith_short_8","alias_value":"GTAIBYWH","created_at":"2026-05-26T02:05:01Z"}],"graph_snapshots":[{"event_id":"sha256:b251797ffa5a6eca918e9e0f874e17cdd80b2c631045605690af52165018c1c1","target":"graph","created_at":"2026-05-26T02:05:01Z","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/2509.10452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In many real-world settings, collecting speech data is impractical, necessitating text-only adaptation. We propose WhisTLE, a deeply supervised, text-only adaptation method for pretrained encoder-decoder ASR models. WhisTLE trains a variational autoencoder (VAE) to model encoder outputs from text and fine-tunes the decoder using the learned text-to-latent encoder, optionally combined with text-to-speech (TTS) adaptation. At inference, the original encode","authors_text":"Akshat Pandey, Karun Kumar, Raphael Tang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T17:59:09Z","title":"WhisTLE: Deeply Supervised, Text-Only Domain Adaptation for Pretrained Speech Recognition Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10452","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":"sha256:4dcc9da07b52695bfa29fd26e9e0b45358f5738ea94205c8629e9a7b3b950e36","target":"record","created_at":"2026-05-26T02:05:01Z","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":"5e0faa65ea52a02ae645c326d44992757595f3ea8fbab66b71bec070bc31cf69","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T17:59:09Z","title_canon_sha256":"7ca5a86b2c84d20aa0f8561252a79210eff87797d222910909b360f59154ccf7"},"schema_version":"1.0","source":{"id":"2509.10452","kind":"arxiv","version":2}},"canonical_sha256":"34c080e2c7f8745abf9bac39893d029ab1af9fdb7a229fb9a704a98c03a327d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34c080e2c7f8745abf9bac39893d029ab1af9fdb7a229fb9a704a98c03a327d0","first_computed_at":"2026-05-26T02:05:01.978542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:01.978542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MFvU9G1ti/UITPPXAwYkyrRcjvftcquqCv94fI4JEaz2P6EM80f/CLV7aOsNbuBH8NBj81cwoSbq4AoAb7lbBw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:01.979325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.10452","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dcc9da07b52695bfa29fd26e9e0b45358f5738ea94205c8629e9a7b3b950e36","sha256:b251797ffa5a6eca918e9e0f874e17cdd80b2c631045605690af52165018c1c1"],"state_sha256":"cfaf703cd9a3e75e46f8bcb7bb174b173c1dc2b29d8e810bebf0dcbf1630719e"}