{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TWBG5UEUD3UTPGNQZMRXXXOQHR","short_pith_number":"pith:TWBG5UEU","canonical_record":{"source":{"id":"2410.03798","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T04:34:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b23ade8f90e03815391739f650c97f5e9a80d167273b49b3a0f6e31941229d10","abstract_canon_sha256":"b8e46894eef133e8ff9e5f3b88e1a0e8657e89c0502caa10f158df8971fde72f"},"schema_version":"1.0"},"canonical_sha256":"9d826ed0941ee93799b0cb237bddd03c5adf2b17cfb55d12ecb79d50ed743909","source":{"kind":"arxiv","id":"2410.03798","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03798","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03798v2","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03798","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"TWBG5UEUD3UT","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"TWBG5UEUD3UTPGNQ","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"TWBG5UEU","created_at":"2026-07-05T09:20:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TWBG5UEUD3UTPGNQZMRXXXOQHR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03798","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T04:34:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b23ade8f90e03815391739f650c97f5e9a80d167273b49b3a0f6e31941229d10","abstract_canon_sha256":"b8e46894eef133e8ff9e5f3b88e1a0e8657e89c0502caa10f158df8971fde72f"},"schema_version":"1.0"},"canonical_sha256":"9d826ed0941ee93799b0cb237bddd03c5adf2b17cfb55d12ecb79d50ed743909","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:04.065037Z","signature_b64":"vfwzEXZI6eYl1FcFc14J0KWiG4o9jWxKIpk/KkTLH7q9KumAxvzD6HlDRS75s60xnCljM5C/t+CdLOAl3ebEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d826ed0941ee93799b0cb237bddd03c5adf2b17cfb55d12ecb79d50ed743909","last_reissued_at":"2026-07-05T09:20:04.064507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:04.064507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03798","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":"2026-07-05T09:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KrY728CN519Bc2jKulyHRf3wkKvRlEMFHcqODRiX2MmAaYBgLpeedwsm76byErKyhtARx4BThJxy6DBVYSBCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:22:59.123958Z"},"content_sha256":"31f29ee7370fcc855faf472a6e15ff0f3b9bd111c23867be96921e2a99ca602d","schema_version":"1.0","event_id":"sha256:31f29ee7370fcc855faf472a6e15ff0f3b9bd111c23867be96921e2a99ca602d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TWBG5UEUD3UTPGNQZMRXXXOQHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Liang Ding, Min Zhang, Tengfei Yu, Xuebo Liu, Zhiyi Hou","submitted_at":"2024-10-04T04:34:24Z","abstract_excerpt":"Large language models (LLMs) exhibit remarkable performance across diverse tasks, indicating their potential for expansion into large speech-text models (LSMs) by integrating speech capabilities. Although unified speech-text pre-training and multimodal data instruction-tuning offer considerable benefits, these methods generally entail significant resource demands and tend to overfit specific tasks. This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning. We explore the instruction-following dynamics within LSMs, identify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03798","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/2410.03798/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":"2026-07-05T09:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bCwqWuyKOUWCjU0jnqRD0BGEznH4Lw8NCXrkfpEHPnjHZokSxJWZw08N6Sb64+GahxHci5QxfXRrP9AOR2F5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T05:22:59.124544Z"},"content_sha256":"b2ea396a0001fa0de51c553005cc5c64255c763dc7d65acf9d6310139786d33d","schema_version":"1.0","event_id":"sha256:b2ea396a0001fa0de51c553005cc5c64255c763dc7d65acf9d6310139786d33d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TWBG5UEUD3UTPGNQZMRXXXOQHR/bundle.json","state_url":"https://pith.science/pith/TWBG5UEUD3UTPGNQZMRXXXOQHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TWBG5UEUD3UTPGNQZMRXXXOQHR/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":"2026-08-22T05:22:59Z","links":{"resolver":"https://pith.science/pith/TWBG5UEUD3UTPGNQZMRXXXOQHR","bundle":"https://pith.science/pith/TWBG5UEUD3UTPGNQZMRXXXOQHR/bundle.json","state":"https://pith.science/pith/TWBG5UEUD3UTPGNQZMRXXXOQHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TWBG5UEUD3UTPGNQZMRXXXOQHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TWBG5UEUD3UTPGNQZMRXXXOQHR","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":"b8e46894eef133e8ff9e5f3b88e1a0e8657e89c0502caa10f158df8971fde72f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T04:34:24Z","title_canon_sha256":"b23ade8f90e03815391739f650c97f5e9a80d167273b49b3a0f6e31941229d10"},"schema_version":"1.0","source":{"id":"2410.03798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03798","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03798v2","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03798","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"TWBG5UEUD3UT","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"TWBG5UEUD3UTPGNQ","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"TWBG5UEU","created_at":"2026-07-05T09:20:04Z"}],"graph_snapshots":[{"event_id":"sha256:b2ea396a0001fa0de51c553005cc5c64255c763dc7d65acf9d6310139786d33d","target":"graph","created_at":"2026-07-05T09:20:04Z","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/2410.03798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) exhibit remarkable performance across diverse tasks, indicating their potential for expansion into large speech-text models (LSMs) by integrating speech capabilities. Although unified speech-text pre-training and multimodal data instruction-tuning offer considerable benefits, these methods generally entail significant resource demands and tend to overfit specific tasks. This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning. We explore the instruction-following dynamics within LSMs, identify","authors_text":"Dacheng Tao, Liang Ding, Min Zhang, Tengfei Yu, Xuebo Liu, Zhiyi Hou","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T04:34:24Z","title":"Self-Powered LLM Modality Expansion for Large Speech-Text Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03798","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":"sha256:31f29ee7370fcc855faf472a6e15ff0f3b9bd111c23867be96921e2a99ca602d","target":"record","created_at":"2026-07-05T09:20:04Z","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":"b8e46894eef133e8ff9e5f3b88e1a0e8657e89c0502caa10f158df8971fde72f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T04:34:24Z","title_canon_sha256":"b23ade8f90e03815391739f650c97f5e9a80d167273b49b3a0f6e31941229d10"},"schema_version":"1.0","source":{"id":"2410.03798","kind":"arxiv","version":2}},"canonical_sha256":"9d826ed0941ee93799b0cb237bddd03c5adf2b17cfb55d12ecb79d50ed743909","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d826ed0941ee93799b0cb237bddd03c5adf2b17cfb55d12ecb79d50ed743909","first_computed_at":"2026-07-05T09:20:04.064507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:04.064507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vfwzEXZI6eYl1FcFc14J0KWiG4o9jWxKIpk/KkTLH7q9KumAxvzD6HlDRS75s60xnCljM5C/t+CdLOAl3ebEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:04.065037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31f29ee7370fcc855faf472a6e15ff0f3b9bd111c23867be96921e2a99ca602d","sha256:b2ea396a0001fa0de51c553005cc5c64255c763dc7d65acf9d6310139786d33d"],"state_sha256":"c2ef19f7fd64ea092e64d4e9b998ed80b334329d5b8b51d5df8faeb48bf6546f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAv9Pk5pn8wpF4fsuogMuvNqao4aHm88RNbpJ+mGHTS6CC7HgPJt5NGOr3ZNcPZvAzcZktjaz/JlOWSLFeIADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T05:22:59.129857Z","bundle_sha256":"a890258428cb1ef0289a3ef72a5bcc0ad415b92a2f5409289216ea40016184c8"}}