{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4RH6VKKNWUKIS7F6O5I52DE77O","short_pith_number":"pith:4RH6VKKN","canonical_record":{"source":{"id":"2606.29031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T17:57:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55431eb1a0aa2e1e98c379a1b9ec1617a4180b7ac71c908342aefca067b00c59","abstract_canon_sha256":"3a6031580bdcb4527ec035377ba6a5d200473eefd98cc5e1e0f6be3f9c47469b"},"schema_version":"1.0"},"canonical_sha256":"e44feaa94db514897cbe7751dd0c9ffbb8ffaca3de1c05a4bf3823ef2c63e0b2","source":{"kind":"arxiv","id":"2606.29031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29031","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29031v1","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29031","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"4RH6VKKNWUKI","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"4RH6VKKNWUKIS7F6","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"4RH6VKKN","created_at":"2026-06-30T01:17:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4RH6VKKNWUKIS7F6O5I52DE77O","target":"record","payload":{"canonical_record":{"source":{"id":"2606.29031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T17:57:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55431eb1a0aa2e1e98c379a1b9ec1617a4180b7ac71c908342aefca067b00c59","abstract_canon_sha256":"3a6031580bdcb4527ec035377ba6a5d200473eefd98cc5e1e0f6be3f9c47469b"},"schema_version":"1.0"},"canonical_sha256":"e44feaa94db514897cbe7751dd0c9ffbb8ffaca3de1c05a4bf3823ef2c63e0b2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:50.091969Z","signature_b64":"0Tb0wGBCQpZr4khzAQgOpQvW7sAMPn2etde32C2psoU2glBBtCdu86C88ZKzae+yQGFTwo5w8iosWwkBBjzpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e44feaa94db514897cbe7751dd0c9ffbb8ffaca3de1c05a4bf3823ef2c63e0b2","last_reissued_at":"2026-06-30T01:17:50.091294Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:50.091294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.29031","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLhFcXd/kHCp+YjI+/XwSY/2kug1hTJasSIogCFQqVVJGEgOl86xD2eXGRXG8laCKC5i2tXUZFO0s49lIs3WCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:56:46.217350Z"},"content_sha256":"9adb079a73f86ba6bb91f3fc4e9254478dede271df49eeac146fe4ee078b7c83","schema_version":"1.0","event_id":"sha256:9adb079a73f86ba6bb91f3fc4e9254478dede271df49eeac146fe4ee078b7c83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4RH6VKKNWUKIS7F6O5I52DE77O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Leverage Synthetic Speech for LLM-Based ASR Systems?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andreas Stolcke, Dairazalia Sanchez-Cortes, Esa\\'u Villatoro-Tello, Kadri Hacio\\u{g}lu, Manjunath K E, Old\\v{r}ich Plchot, Petr Motlicek, Sergio Burdisso, S\\'everin Baroudi, Shashi Kumar, Srikanth Madikeri, Yanis Labrak","submitted_at":"2026-06-27T17:57:27Z","abstract_excerpt":"In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from modern text-to-speech (TTS) is an appealing alternative for training automatic speech recognition (ASR) without exposing sensitive customer recordings. Yet a persistent distributional gap between synthetic and real data limits how far it can replace genuine recordings. Prior work largely treats this gap as a black box to be engineered around, but in our work, we instead examine its origin directly by probing a SLAM-ASR architecture. Then, we locali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29031","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.29031/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFxP5Nc+fbOC3zM/fDX2FDD5J1GCg5Q2C21JaB6I5VtOA0uvRAeHQzhBbCukcYV9TNmeJfzrt3VTwnzHSxnCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:56:46.217752Z"},"content_sha256":"2018a106eea96486d295428807efae66d57b592261efea9dd41235ad41f21e6a","schema_version":"1.0","event_id":"sha256:2018a106eea96486d295428807efae66d57b592261efea9dd41235ad41f21e6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RH6VKKNWUKIS7F6O5I52DE77O/bundle.json","state_url":"https://pith.science/pith/4RH6VKKNWUKIS7F6O5I52DE77O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RH6VKKNWUKIS7F6O5I52DE77O/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T07:56:46Z","links":{"resolver":"https://pith.science/pith/4RH6VKKNWUKIS7F6O5I52DE77O","bundle":"https://pith.science/pith/4RH6VKKNWUKIS7F6O5I52DE77O/bundle.json","state":"https://pith.science/pith/4RH6VKKNWUKIS7F6O5I52DE77O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RH6VKKNWUKIS7F6O5I52DE77O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4RH6VKKNWUKIS7F6O5I52DE77O","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":"3a6031580bdcb4527ec035377ba6a5d200473eefd98cc5e1e0f6be3f9c47469b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T17:57:27Z","title_canon_sha256":"55431eb1a0aa2e1e98c379a1b9ec1617a4180b7ac71c908342aefca067b00c59"},"schema_version":"1.0","source":{"id":"2606.29031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29031","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29031v1","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29031","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"pith_short_12","alias_value":"4RH6VKKNWUKI","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"pith_short_16","alias_value":"4RH6VKKNWUKIS7F6","created_at":"2026-06-30T01:17:50Z"},{"alias_kind":"pith_short_8","alias_value":"4RH6VKKN","created_at":"2026-06-30T01:17:50Z"}],"graph_snapshots":[{"event_id":"sha256:2018a106eea96486d295428807efae66d57b592261efea9dd41235ad41f21e6a","target":"graph","created_at":"2026-06-30T01:17:50Z","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/2606.29031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In regulated domains such as banking and healthcare, where privacy constraints make real speech costly to collect and retain, synthetic speech from modern text-to-speech (TTS) is an appealing alternative for training automatic speech recognition (ASR) without exposing sensitive customer recordings. Yet a persistent distributional gap between synthetic and real data limits how far it can replace genuine recordings. Prior work largely treats this gap as a black box to be engineered around, but in our work, we instead examine its origin directly by probing a SLAM-ASR architecture. Then, we locali","authors_text":"Andreas Stolcke, Dairazalia Sanchez-Cortes, Esa\\'u Villatoro-Tello, Kadri Hacio\\u{g}lu, Manjunath K E, Old\\v{r}ich Plchot, Petr Motlicek, Sergio Burdisso, S\\'everin Baroudi, Shashi Kumar, Srikanth Madikeri, Yanis Labrak","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T17:57:27Z","title":"How to Leverage Synthetic Speech for LLM-Based ASR Systems?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29031","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":"sha256:9adb079a73f86ba6bb91f3fc4e9254478dede271df49eeac146fe4ee078b7c83","target":"record","created_at":"2026-06-30T01:17:50Z","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":"3a6031580bdcb4527ec035377ba6a5d200473eefd98cc5e1e0f6be3f9c47469b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T17:57:27Z","title_canon_sha256":"55431eb1a0aa2e1e98c379a1b9ec1617a4180b7ac71c908342aefca067b00c59"},"schema_version":"1.0","source":{"id":"2606.29031","kind":"arxiv","version":1}},"canonical_sha256":"e44feaa94db514897cbe7751dd0c9ffbb8ffaca3de1c05a4bf3823ef2c63e0b2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e44feaa94db514897cbe7751dd0c9ffbb8ffaca3de1c05a4bf3823ef2c63e0b2","first_computed_at":"2026-06-30T01:17:50.091294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:50.091294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Tb0wGBCQpZr4khzAQgOpQvW7sAMPn2etde32C2psoU2glBBtCdu86C88ZKzae+yQGFTwo5w8iosWwkBBjzpCw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:50.091969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9adb079a73f86ba6bb91f3fc4e9254478dede271df49eeac146fe4ee078b7c83","sha256:2018a106eea96486d295428807efae66d57b592261efea9dd41235ad41f21e6a"],"state_sha256":"1bf2bf2c2cbb411f93d602be084cd9032c03f69fdac8e845d81de0d54ede7a3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j19ytmXtkUODtseUAiGyqgIm12ZADnPRE4Nl8JExlzgfVHg+F/nZ8Qzw+6I+58Bh19s98G+LgZaiq8XVZffVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T07:56:46.220341Z","bundle_sha256":"6d770d6a1cf55fef784714c8b498ced6a46ff6e852f09a4c0652801463d67f19"}}