{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DSULOVOKBVYAHJH2OWR3E47RRX","short_pith_number":"pith:DSULOVOK","canonical_record":{"source":{"id":"2406.12946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T08:27:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"39a1d4644e85290888e7c255efa2c6a3de023e898fa5e733ac91f3a73204536e","abstract_canon_sha256":"f5d7f85b23e7d89af815628a371efb5fbf6ae9de729018543765bb9c41b498c2"},"schema_version":"1.0"},"canonical_sha256":"1ca8b755ca0d7003a4fa75a3b273f18de9e7ce77e0da5fad60c2fb5c87cf60dc","source":{"kind":"arxiv","id":"2406.12946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12946","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12946v1","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12946","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"pith_short_12","alias_value":"DSULOVOKBVYA","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"pith_short_16","alias_value":"DSULOVOKBVYAHJH2","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"pith_short_8","alias_value":"DSULOVOK","created_at":"2026-07-05T08:34:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DSULOVOKBVYAHJH2OWR3E47RRX","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T08:27:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"39a1d4644e85290888e7c255efa2c6a3de023e898fa5e733ac91f3a73204536e","abstract_canon_sha256":"f5d7f85b23e7d89af815628a371efb5fbf6ae9de729018543765bb9c41b498c2"},"schema_version":"1.0"},"canonical_sha256":"1ca8b755ca0d7003a4fa75a3b273f18de9e7ce77e0da5fad60c2fb5c87cf60dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:22.734105Z","signature_b64":"BPRqrWzbk77g3Bxi2t2lIhTVzOMFHpS/fq/SRhevYqugIOUO2V5PUz0w0KKmjihqK2+gLWMy33y+YlMol1tqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca8b755ca0d7003a4fa75a3b273f18de9e7ce77e0da5fad60c2fb5c87cf60dc","last_reissued_at":"2026-07-05T08:34:22.733644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:22.733644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12946","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":"2026-07-05T08:34:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"opidGXTT2mW1G3FVGB+RTa4Vlj/AiYWPJpeBDZ4lXq+XbO6Edej6EuPaHDhJC2Uk8kXrUpLWuFziHKuYkf1hCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:49:41.417803Z"},"content_sha256":"b555d49b72cec098061032ec42d5a65062a9aaebbfe05497713b8a4f7bc5072b","schema_version":"1.0","event_id":"sha256:b555d49b72cec098061032ec42d5a65062a9aaebbfe05497713b8a4f7bc5072b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DSULOVOKBVYAHJH2OWR3E47RRX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Instruction Data Generation and Unsupervised Adaptation for Speech Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Jagadeesh Balam, Somshubra Majumdar, Steve Huang, Vahid Noroozi, Zhehuai Chen","submitted_at":"2024-06-18T08:27:00Z","abstract_excerpt":"In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both modalities, synthetic data generation emerges as a crucial strategy to enhance the performance of such systems and facilitate the modeling of cross-modal relationships between the speech and text domains. Our process employs large language models to generate textual components and text-to-speech systems to generate speech components. The proposed methods offer a pract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12946","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/2406.12946/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":"2026-07-05T08:34:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qo88X8e9y4k1EBmvSfaEMkOKsU0QeWquPTm0gvi69l6esILQJ8Jk+2d7iZAf9aJreTB0+0IAF4UI1hrPjDNGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:49:41.418169Z"},"content_sha256":"d6cd90bf12db7c982f2188303501729801fad3eede1af0ea16ce172aa4a81d1b","schema_version":"1.0","event_id":"sha256:d6cd90bf12db7c982f2188303501729801fad3eede1af0ea16ce172aa4a81d1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSULOVOKBVYAHJH2OWR3E47RRX/bundle.json","state_url":"https://pith.science/pith/DSULOVOKBVYAHJH2OWR3E47RRX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSULOVOKBVYAHJH2OWR3E47RRX/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":"2026-07-07T14:49:41Z","links":{"resolver":"https://pith.science/pith/DSULOVOKBVYAHJH2OWR3E47RRX","bundle":"https://pith.science/pith/DSULOVOKBVYAHJH2OWR3E47RRX/bundle.json","state":"https://pith.science/pith/DSULOVOKBVYAHJH2OWR3E47RRX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSULOVOKBVYAHJH2OWR3E47RRX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DSULOVOKBVYAHJH2OWR3E47RRX","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":"f5d7f85b23e7d89af815628a371efb5fbf6ae9de729018543765bb9c41b498c2","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T08:27:00Z","title_canon_sha256":"39a1d4644e85290888e7c255efa2c6a3de023e898fa5e733ac91f3a73204536e"},"schema_version":"1.0","source":{"id":"2406.12946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12946","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12946v1","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12946","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"pith_short_12","alias_value":"DSULOVOKBVYA","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"pith_short_16","alias_value":"DSULOVOKBVYAHJH2","created_at":"2026-07-05T08:34:22Z"},{"alias_kind":"pith_short_8","alias_value":"DSULOVOK","created_at":"2026-07-05T08:34:22Z"}],"graph_snapshots":[{"event_id":"sha256:d6cd90bf12db7c982f2188303501729801fad3eede1af0ea16ce172aa4a81d1b","target":"graph","created_at":"2026-07-05T08:34:22Z","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/2406.12946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both modalities, synthetic data generation emerges as a crucial strategy to enhance the performance of such systems and facilitate the modeling of cross-modal relationships between the speech and text domains. Our process employs large language models to generate textual components and text-to-speech systems to generate speech components. The proposed methods offer a pract","authors_text":"Boris Ginsburg, Jagadeesh Balam, Somshubra Majumdar, Steve Huang, Vahid Noroozi, Zhehuai Chen","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T08:27:00Z","title":"Instruction Data Generation and Unsupervised Adaptation for Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12946","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:b555d49b72cec098061032ec42d5a65062a9aaebbfe05497713b8a4f7bc5072b","target":"record","created_at":"2026-07-05T08:34:22Z","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":"f5d7f85b23e7d89af815628a371efb5fbf6ae9de729018543765bb9c41b498c2","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-18T08:27:00Z","title_canon_sha256":"39a1d4644e85290888e7c255efa2c6a3de023e898fa5e733ac91f3a73204536e"},"schema_version":"1.0","source":{"id":"2406.12946","kind":"arxiv","version":1}},"canonical_sha256":"1ca8b755ca0d7003a4fa75a3b273f18de9e7ce77e0da5fad60c2fb5c87cf60dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ca8b755ca0d7003a4fa75a3b273f18de9e7ce77e0da5fad60c2fb5c87cf60dc","first_computed_at":"2026-07-05T08:34:22.733644Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:22.733644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BPRqrWzbk77g3Bxi2t2lIhTVzOMFHpS/fq/SRhevYqugIOUO2V5PUz0w0KKmjihqK2+gLWMy33y+YlMol1tqDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:22.734105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b555d49b72cec098061032ec42d5a65062a9aaebbfe05497713b8a4f7bc5072b","sha256:d6cd90bf12db7c982f2188303501729801fad3eede1af0ea16ce172aa4a81d1b"],"state_sha256":"65eedc6a67df86e77e8450db704dd23801e104e0502c1dfe5ae151bf226dc40b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWH73jAYsgeatWdM1vYWgruRCj+iAhSeb6MkypRA1sLOWB8o+wGtFVYmesInHI7MKD77Lya3otKft+T2VnBKCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:49:41.419987Z","bundle_sha256":"75de3eb420a604e3d4c0900555efca5261513d552d931bad73c5e2772443cf74"}}