{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A44CEUU2FB6JGV7TZGNVXRRMXP","short_pith_number":"pith:A44CEUU2","canonical_record":{"source":{"id":"2406.18871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T03:52:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"707e4bb66bdb3cf700ed30715b79e819c842f2023f134bff02f0e6339b17e659","abstract_canon_sha256":"56f86f7d806cab2da25108fc22cf9b029969d3e2aa75560d52a6ff139b38663a"},"schema_version":"1.0"},"canonical_sha256":"073822529a287c9357f3c99b5bc62cbbd4d3ec73b5b151383701bd2ab2e8d0d1","source":{"kind":"arxiv","id":"2406.18871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18871","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18871v1","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18871","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_12","alias_value":"A44CEUU2FB6J","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_16","alias_value":"A44CEUU2FB6JGV7T","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_8","alias_value":"A44CEUU2","created_at":"2026-07-05T08:37:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A44CEUU2FB6JGV7TZGNVXRRMXP","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T03:52:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"707e4bb66bdb3cf700ed30715b79e819c842f2023f134bff02f0e6339b17e659","abstract_canon_sha256":"56f86f7d806cab2da25108fc22cf9b029969d3e2aa75560d52a6ff139b38663a"},"schema_version":"1.0"},"canonical_sha256":"073822529a287c9357f3c99b5bc62cbbd4d3ec73b5b151383701bd2ab2e8d0d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:26.938031Z","signature_b64":"Vqm6NTBrDlK7ay9CY61tQqXdyrreaIQP1a6LqBvnvDpejF3ntSDpNp3t3B8rPMVfan3Y89puLgGpDN2DJbZ/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"073822529a287c9357f3c99b5bc62cbbd4d3ec73b5b151383701bd2ab2e8d0d1","last_reissued_at":"2026-07-05T08:37:26.937689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:26.937689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18871","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":"2026-07-05T08:37:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wJ+Gcy16RaSwWCtDEZ/JooPycrKf65MManwNk5frcME/JEa/b3K38rAP9imwX9UiLhL9WgBJXHiZFnBzSLnkAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:01:20.128661Z"},"content_sha256":"3990d858b192a03c799d8e42faae9a154718689cf356190aa9f2dd3ba4ec35b0","schema_version":"1.0","event_id":"sha256:3990d858b192a03c799d8e42faae9a154718689cf356190aa9f2dd3ba4ec35b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A44CEUU2FB6JGV7TZGNVXRRMXP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, He Huang, Hung-yi Lee, Ke-Han Lu, Szu-Wei Fu, Yu-Chiang Frank Wang, Zhehuai Chen","submitted_at":"2024-06-27T03:52:35Z","abstract_excerpt":"Recent speech language models (SLMs) typically incorporate pre-trained speech models to extend the capabilities from large language models (LLMs). In this paper, we propose a Descriptive Speech-Text Alignment approach that leverages speech captioning to bridge the gap between speech and text modalities, enabling SLMs to interpret and generate comprehensive natural language descriptions, thereby facilitating the capability to understand both linguistic and non-linguistic features in speech. Enhanced with the proposed approach, our model demonstrates superior performance on the Dynamic-SUPERB be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18871","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/2406.18871/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":"2026-07-05T08:37:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NWxLFuv8uuS0mftCkfKATc0YI1t9saiQ8GyJwPlrq8nQoaYLAvEjGDRYRhW5jo3c4okHIU5TiqpTu66TlGthDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:01:20.129592Z"},"content_sha256":"44638651a7381ec7f8dc5bf0a6881e017b8d722f8b3f9cc5a33c0159132e3f0c","schema_version":"1.0","event_id":"sha256:44638651a7381ec7f8dc5bf0a6881e017b8d722f8b3f9cc5a33c0159132e3f0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A44CEUU2FB6JGV7TZGNVXRRMXP/bundle.json","state_url":"https://pith.science/pith/A44CEUU2FB6JGV7TZGNVXRRMXP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A44CEUU2FB6JGV7TZGNVXRRMXP/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":"2026-08-06T00:01:20Z","links":{"resolver":"https://pith.science/pith/A44CEUU2FB6JGV7TZGNVXRRMXP","bundle":"https://pith.science/pith/A44CEUU2FB6JGV7TZGNVXRRMXP/bundle.json","state":"https://pith.science/pith/A44CEUU2FB6JGV7TZGNVXRRMXP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A44CEUU2FB6JGV7TZGNVXRRMXP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A44CEUU2FB6JGV7TZGNVXRRMXP","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":"56f86f7d806cab2da25108fc22cf9b029969d3e2aa75560d52a6ff139b38663a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T03:52:35Z","title_canon_sha256":"707e4bb66bdb3cf700ed30715b79e819c842f2023f134bff02f0e6339b17e659"},"schema_version":"1.0","source":{"id":"2406.18871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18871","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18871v1","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18871","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_12","alias_value":"A44CEUU2FB6J","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_16","alias_value":"A44CEUU2FB6JGV7T","created_at":"2026-07-05T08:37:26Z"},{"alias_kind":"pith_short_8","alias_value":"A44CEUU2","created_at":"2026-07-05T08:37:26Z"}],"graph_snapshots":[{"event_id":"sha256:44638651a7381ec7f8dc5bf0a6881e017b8d722f8b3f9cc5a33c0159132e3f0c","target":"graph","created_at":"2026-07-05T08:37:26Z","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/2406.18871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent speech language models (SLMs) typically incorporate pre-trained speech models to extend the capabilities from large language models (LLMs). In this paper, we propose a Descriptive Speech-Text Alignment approach that leverages speech captioning to bridge the gap between speech and text modalities, enabling SLMs to interpret and generate comprehensive natural language descriptions, thereby facilitating the capability to understand both linguistic and non-linguistic features in speech. Enhanced with the proposed approach, our model demonstrates superior performance on the Dynamic-SUPERB be","authors_text":"Boris Ginsburg, He Huang, Hung-yi Lee, Ke-Han Lu, Szu-Wei Fu, Yu-Chiang Frank Wang, Zhehuai Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T03:52:35Z","title":"DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18871","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":"sha256:3990d858b192a03c799d8e42faae9a154718689cf356190aa9f2dd3ba4ec35b0","target":"record","created_at":"2026-07-05T08:37:26Z","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":"56f86f7d806cab2da25108fc22cf9b029969d3e2aa75560d52a6ff139b38663a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-27T03:52:35Z","title_canon_sha256":"707e4bb66bdb3cf700ed30715b79e819c842f2023f134bff02f0e6339b17e659"},"schema_version":"1.0","source":{"id":"2406.18871","kind":"arxiv","version":1}},"canonical_sha256":"073822529a287c9357f3c99b5bc62cbbd4d3ec73b5b151383701bd2ab2e8d0d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"073822529a287c9357f3c99b5bc62cbbd4d3ec73b5b151383701bd2ab2e8d0d1","first_computed_at":"2026-07-05T08:37:26.937689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:26.937689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vqm6NTBrDlK7ay9CY61tQqXdyrreaIQP1a6LqBvnvDpejF3ntSDpNp3t3B8rPMVfan3Y89puLgGpDN2DJbZ/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:26.938031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3990d858b192a03c799d8e42faae9a154718689cf356190aa9f2dd3ba4ec35b0","sha256:44638651a7381ec7f8dc5bf0a6881e017b8d722f8b3f9cc5a33c0159132e3f0c"],"state_sha256":"4243098b29df4a18515c38480f8022e1ec191b337fd31dc373d1e4672bc1f8ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WvSC3t3UOuHSFIOjH3FwShGoUv2kHpe2cSblZSoTu/XtYQHP/rkARIm8n1SJ2R5wpVx3vTJhN0GwzH3EktpkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:01:20.135440Z","bundle_sha256":"a233e88531a688af49e3ca0a8274005fa98df2cffd2068578de3bd9fb3449c66"}}