{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N3ENU2IHEMXUSD7LFBUR2W3V2J","short_pith_number":"pith:N3ENU2IH","canonical_record":{"source":{"id":"2409.20007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"18724d28dbf2ed9717292b49a51e1cff161ed42455afe140d256eba4ccf66c5d","abstract_canon_sha256":"59e1eacf790c2a30d7f523c081898c06b6995bfc82f13ae216972e6d9028236d"},"schema_version":"1.0"},"canonical_sha256":"6ec8da6907232f490feb28691d5b75d254bec7d1a52b94f3e9ebaefa9a756b2b","source":{"kind":"arxiv","id":"2409.20007","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20007","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20007v2","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20007","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"N3ENU2IHEMXU","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"N3ENU2IHEMXUSD7L","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"N3ENU2IH","created_at":"2026-07-05T11:44:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N3ENU2IHEMXUSD7LFBUR2W3V2J","target":"record","payload":{"canonical_record":{"source":{"id":"2409.20007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"18724d28dbf2ed9717292b49a51e1cff161ed42455afe140d256eba4ccf66c5d","abstract_canon_sha256":"59e1eacf790c2a30d7f523c081898c06b6995bfc82f13ae216972e6d9028236d"},"schema_version":"1.0"},"canonical_sha256":"6ec8da6907232f490feb28691d5b75d254bec7d1a52b94f3e9ebaefa9a756b2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:41.594706Z","signature_b64":"2oeuLu3JMFkCWiRwvHc54CyA10GpXeyrmR00h3T1I1B+N7BE/a1Gni+8phgqEX8XW74smL1dGuPdgQo7OheYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec8da6907232f490feb28691d5b75d254bec7d1a52b94f3e9ebaefa9a756b2b","last_reissued_at":"2026-07-05T11:44:41.594212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:41.594212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.20007","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kagdz5vSHv3lloqBo2UTG++R0jfpGPDUdMcFbI4m5pnN43Qq1Tlw+wL/zkOAGuG6WbSLIy7MYW8gqUjO1PhoAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:59:13.692198Z"},"content_sha256":"602c5dd55cd47b0c17926ea139f91b951332ca964f0d8c4fa4a34d550eb65476","schema_version":"1.0","event_id":"sha256:602c5dd55cd47b0c17926ea139f91b951332ca964f0d8c4fa4a34d550eb65476"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N3ENU2IHEMXUSD7LFBUR2W3V2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Chao-Han Huck Yang, Hung-yi Lee, Jagadeesh Balam, Ke-Han Lu, Szu-Wei Fu, Yu-Chiang Frank Wang, Zhehuai Chen","submitted_at":"2024-09-30T07:01:21Z","abstract_excerpt":"Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs) by incorporating pre-trained speech models. However, these SLMs often undergo extensive speech instruction-tuning to bridge the gap between speech and text modalities. This requires significant annotation efforts and risks catastrophic forgetting of the original language capabilities. In this work, we present a simple yet effective automatic process for creating speech-text pair data that carefully injects speech paralinguistic understanding abilities into SLMs while preserving t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20007","kind":"arxiv","version":2},"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/2409.20007/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":"2026-07-05T11:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pR9AHKk7vfnVkF8RyqsXPNOhvVti0YtYHaG0IZxTrDrfV0oKA5GuPaouH1gHXzqtQUbhXfNWpymt6mlwaB71Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:59:13.693187Z"},"content_sha256":"813b5184093796b6ae2d91b2d8f88ccddace4afa014ad65cd082fc193c006ca2","schema_version":"1.0","event_id":"sha256:813b5184093796b6ae2d91b2d8f88ccddace4afa014ad65cd082fc193c006ca2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3ENU2IHEMXUSD7LFBUR2W3V2J/bundle.json","state_url":"https://pith.science/pith/N3ENU2IHEMXUSD7LFBUR2W3V2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3ENU2IHEMXUSD7LFBUR2W3V2J/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":"2026-08-06T05:59:13Z","links":{"resolver":"https://pith.science/pith/N3ENU2IHEMXUSD7LFBUR2W3V2J","bundle":"https://pith.science/pith/N3ENU2IHEMXUSD7LFBUR2W3V2J/bundle.json","state":"https://pith.science/pith/N3ENU2IHEMXUSD7LFBUR2W3V2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3ENU2IHEMXUSD7LFBUR2W3V2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3ENU2IHEMXUSD7LFBUR2W3V2J","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":"59e1eacf790c2a30d7f523c081898c06b6995bfc82f13ae216972e6d9028236d","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","title_canon_sha256":"18724d28dbf2ed9717292b49a51e1cff161ed42455afe140d256eba4ccf66c5d"},"schema_version":"1.0","source":{"id":"2409.20007","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.20007","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2409.20007v2","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20007","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"N3ENU2IHEMXU","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"N3ENU2IHEMXUSD7L","created_at":"2026-07-05T11:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"N3ENU2IH","created_at":"2026-07-05T11:44:41Z"}],"graph_snapshots":[{"event_id":"sha256:813b5184093796b6ae2d91b2d8f88ccddace4afa014ad65cd082fc193c006ca2","target":"graph","created_at":"2026-07-05T11:44:41Z","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/2409.20007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent end-to-end speech language models (SLMs) have expanded upon the capabilities of large language models (LLMs) by incorporating pre-trained speech models. However, these SLMs often undergo extensive speech instruction-tuning to bridge the gap between speech and text modalities. This requires significant annotation efforts and risks catastrophic forgetting of the original language capabilities. In this work, we present a simple yet effective automatic process for creating speech-text pair data that carefully injects speech paralinguistic understanding abilities into SLMs while preserving t","authors_text":"Boris Ginsburg, Chao-Han Huck Yang, Hung-yi Lee, Jagadeesh Balam, Ke-Han Lu, Szu-Wei Fu, Yu-Chiang Frank Wang, Zhehuai Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20007","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":"sha256:602c5dd55cd47b0c17926ea139f91b951332ca964f0d8c4fa4a34d550eb65476","target":"record","created_at":"2026-07-05T11:44:41Z","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":"59e1eacf790c2a30d7f523c081898c06b6995bfc82f13ae216972e6d9028236d","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-30T07:01:21Z","title_canon_sha256":"18724d28dbf2ed9717292b49a51e1cff161ed42455afe140d256eba4ccf66c5d"},"schema_version":"1.0","source":{"id":"2409.20007","kind":"arxiv","version":2}},"canonical_sha256":"6ec8da6907232f490feb28691d5b75d254bec7d1a52b94f3e9ebaefa9a756b2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ec8da6907232f490feb28691d5b75d254bec7d1a52b94f3e9ebaefa9a756b2b","first_computed_at":"2026-07-05T11:44:41.594212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:41.594212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2oeuLu3JMFkCWiRwvHc54CyA10GpXeyrmR00h3T1I1B+N7BE/a1Gni+8phgqEX8XW74smL1dGuPdgQo7OheYBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:41.594706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.20007","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:602c5dd55cd47b0c17926ea139f91b951332ca964f0d8c4fa4a34d550eb65476","sha256:813b5184093796b6ae2d91b2d8f88ccddace4afa014ad65cd082fc193c006ca2"],"state_sha256":"cb3c619d524149b239b2d579de9706d5fd781220d2d6fb11831efe940e3fcf05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Gjtd1f3+egyTWYiKMPgmDxnZQFHsp+W/0kqozO3ezk5NOLVH3blERiikjtYZDfWm/iicYTsGwK0o/RFBJKcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:59:13.699087Z","bundle_sha256":"71f3a07713080464287065c40e9f2b5c243c9598abd5d6c315a153cd87e5769c"}}