{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OXKBG7BC7A2SLXYQ243JM7C4SU","short_pith_number":"pith:OXKBG7BC","canonical_record":{"source":{"id":"2408.16423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-29T10:31:52Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c49c52df6df3d24480952b2aec0dbd5da30153c0b98ce0c7882fd229d8c0182d","abstract_canon_sha256":"234a6422b9f8c217996b83197f1d518a02b61ce456efa1999f5912a90d0420c8"},"schema_version":"1.0"},"canonical_sha256":"75d4137c22f83525df10d736967c5c95353142f45b20a0281672ce019dfd1524","source":{"kind":"arxiv","id":"2408.16423","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16423","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16423v1","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16423","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"pith_short_12","alias_value":"OXKBG7BC7A2S","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"pith_short_16","alias_value":"OXKBG7BC7A2SLXYQ","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"pith_short_8","alias_value":"OXKBG7BC","created_at":"2026-07-05T09:00:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OXKBG7BC7A2SLXYQ243JM7C4SU","target":"record","payload":{"canonical_record":{"source":{"id":"2408.16423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-29T10:31:52Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c49c52df6df3d24480952b2aec0dbd5da30153c0b98ce0c7882fd229d8c0182d","abstract_canon_sha256":"234a6422b9f8c217996b83197f1d518a02b61ce456efa1999f5912a90d0420c8"},"schema_version":"1.0"},"canonical_sha256":"75d4137c22f83525df10d736967c5c95353142f45b20a0281672ce019dfd1524","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:41.152783Z","signature_b64":"CHwzh/Mf/Pzwz+vnJrud89LTmGwFsuxtzXM0Ryrx9TwP9HvYDtlPJ98V/0bBeT5DfF6syqao3HwRnKohEOinCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75d4137c22f83525df10d736967c5c95353142f45b20a0281672ce019dfd1524","last_reissued_at":"2026-07-05T09:00:41.152345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:41.152345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.16423","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":"2026-07-05T09:00:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVz+MFkVYFBKBPbnuD3RkGEpeFPwQUUDKoL1MCiwSGaUTqO0MYwK+yc2vQHoGl6m4BHXTv0gCU2dd0n8WLIVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:59:07.625666Z"},"content_sha256":"3fd545a3b55660701e2bee6c3f9b7858d5076c15f9b62c034d4077a8401527a9","schema_version":"1.0","event_id":"sha256:3fd545a3b55660701e2bee6c3f9b7858d5076c15f9b62c034d4077a8401527a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OXKBG7BC7A2SLXYQ243JM7C4SU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WHISMA: A Speech-LLM to Perform Zero-shot Spoken Language Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong-Thanh Do, Mohan Li, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev, Youmna Farag","submitted_at":"2024-08-29T10:31:52Z","abstract_excerpt":"Speech large language models (speech-LLMs) integrate speech and text-based foundation models to provide a unified framework for handling a wide range of downstream tasks. In this paper, we introduce WHISMA, a speech-LLM tailored for spoken language understanding (SLU) that demonstrates robust performance in various zero-shot settings. WHISMA combines the speech encoder from Whisper with the Llama-3 LLM, and is fine-tuned in a parameter-efficient manner on a comprehensive collection of SLU-related datasets. Our experiments show that WHISMA significantly improves the zero-shot slot filling perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16423","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/2408.16423/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":"2026-07-05T09:00:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r9Ty9WJpPV1+sqSqSZQ+O4FbvlcmUIpYQVTPDE0iYa77XNyJCJDEYtydJh8ddaYrI2J0C40WbkqaEXMcZVEQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:59:07.626148Z"},"content_sha256":"b8695614392a135d745849428bbbb02e078e08a6f31a70f3e3dcb45d44f40213","schema_version":"1.0","event_id":"sha256:b8695614392a135d745849428bbbb02e078e08a6f31a70f3e3dcb45d44f40213"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXKBG7BC7A2SLXYQ243JM7C4SU/bundle.json","state_url":"https://pith.science/pith/OXKBG7BC7A2SLXYQ243JM7C4SU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXKBG7BC7A2SLXYQ243JM7C4SU/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":"2026-08-11T07:59:07Z","links":{"resolver":"https://pith.science/pith/OXKBG7BC7A2SLXYQ243JM7C4SU","bundle":"https://pith.science/pith/OXKBG7BC7A2SLXYQ243JM7C4SU/bundle.json","state":"https://pith.science/pith/OXKBG7BC7A2SLXYQ243JM7C4SU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXKBG7BC7A2SLXYQ243JM7C4SU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OXKBG7BC7A2SLXYQ243JM7C4SU","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":"234a6422b9f8c217996b83197f1d518a02b61ce456efa1999f5912a90d0420c8","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-29T10:31:52Z","title_canon_sha256":"c49c52df6df3d24480952b2aec0dbd5da30153c0b98ce0c7882fd229d8c0182d"},"schema_version":"1.0","source":{"id":"2408.16423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16423","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16423v1","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16423","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"pith_short_12","alias_value":"OXKBG7BC7A2S","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"pith_short_16","alias_value":"OXKBG7BC7A2SLXYQ","created_at":"2026-07-05T09:00:41Z"},{"alias_kind":"pith_short_8","alias_value":"OXKBG7BC","created_at":"2026-07-05T09:00:41Z"}],"graph_snapshots":[{"event_id":"sha256:b8695614392a135d745849428bbbb02e078e08a6f31a70f3e3dcb45d44f40213","target":"graph","created_at":"2026-07-05T09:00:41Z","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/2408.16423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech large language models (speech-LLMs) integrate speech and text-based foundation models to provide a unified framework for handling a wide range of downstream tasks. In this paper, we introduce WHISMA, a speech-LLM tailored for spoken language understanding (SLU) that demonstrates robust performance in various zero-shot settings. WHISMA combines the speech encoder from Whisper with the Llama-3 LLM, and is fine-tuned in a parameter-efficient manner on a comprehensive collection of SLU-related datasets. Our experiments show that WHISMA significantly improves the zero-shot slot filling perfo","authors_text":"Cong-Thanh Do, Mohan Li, Rama Doddipatla, Simon Keizer, Svetlana Stoyanchev, Youmna Farag","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-29T10:31:52Z","title":"WHISMA: A Speech-LLM to Perform Zero-shot Spoken Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16423","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":"sha256:3fd545a3b55660701e2bee6c3f9b7858d5076c15f9b62c034d4077a8401527a9","target":"record","created_at":"2026-07-05T09:00:41Z","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":"234a6422b9f8c217996b83197f1d518a02b61ce456efa1999f5912a90d0420c8","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-08-29T10:31:52Z","title_canon_sha256":"c49c52df6df3d24480952b2aec0dbd5da30153c0b98ce0c7882fd229d8c0182d"},"schema_version":"1.0","source":{"id":"2408.16423","kind":"arxiv","version":1}},"canonical_sha256":"75d4137c22f83525df10d736967c5c95353142f45b20a0281672ce019dfd1524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75d4137c22f83525df10d736967c5c95353142f45b20a0281672ce019dfd1524","first_computed_at":"2026-07-05T09:00:41.152345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:41.152345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CHwzh/Mf/Pzwz+vnJrud89LTmGwFsuxtzXM0Ryrx9TwP9HvYDtlPJ98V/0bBeT5DfF6syqao3HwRnKohEOinCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:41.152783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fd545a3b55660701e2bee6c3f9b7858d5076c15f9b62c034d4077a8401527a9","sha256:b8695614392a135d745849428bbbb02e078e08a6f31a70f3e3dcb45d44f40213"],"state_sha256":"50c8800e07476e4287ee306cd2e3e29d9c5076c7592510688c2de7d74da170e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KTbDrwVf61zlkBuGBJbauP+X2BvF+K6zS9AO47VAN3PaH2QRS/lFTn1mj/JiW72hS6P2RWt438CLG4LDlDv3Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T07:59:07.630537Z","bundle_sha256":"1f1f73f07e66a897a4b3499ef6c4ac31bde553c40dab97925ec0c94485e8ff77"}}