{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EAI2RZYGSRE2UBW42WV2USNMQY","short_pith_number":"pith:EAI2RZYG","canonical_record":{"source":{"id":"2408.03900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T16:55:28Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"44d2f00ac38f0e28d432f4973f8df48bfd256400cf34971639e4d54eb5546b03","abstract_canon_sha256":"f75248ef6cb5da08f6781d33bb07c2bb64e70f065a22169f2827e2b525b30641"},"schema_version":"1.0"},"canonical_sha256":"2011a8e7069449aa06dcd5abaa49ac860ec3d11239de08e19bc6345b4b06b1b0","source":{"kind":"arxiv","id":"2408.03900","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03900","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03900v1","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03900","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"pith_short_12","alias_value":"EAI2RZYGSRE2","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"pith_short_16","alias_value":"EAI2RZYGSRE2UBW4","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"pith_short_8","alias_value":"EAI2RZYG","created_at":"2026-07-05T08:53:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EAI2RZYGSRE2UBW42WV2USNMQY","target":"record","payload":{"canonical_record":{"source":{"id":"2408.03900","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T16:55:28Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"44d2f00ac38f0e28d432f4973f8df48bfd256400cf34971639e4d54eb5546b03","abstract_canon_sha256":"f75248ef6cb5da08f6781d33bb07c2bb64e70f065a22169f2827e2b525b30641"},"schema_version":"1.0"},"canonical_sha256":"2011a8e7069449aa06dcd5abaa49ac860ec3d11239de08e19bc6345b4b06b1b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:12.563456Z","signature_b64":"l42pw/CYlwqkCwujO+KwjGFjfaq0Fh1Qm2h7P0RfkR3PkW9jS6Hv3JqnqwS8DtFcTy27B85Jv2KADT7J6rCQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2011a8e7069449aa06dcd5abaa49ac860ec3d11239de08e19bc6345b4b06b1b0","last_reissued_at":"2026-07-05T08:53:12.563086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:12.563086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.03900","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":"2026-07-05T08:53:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g787B8sFJ4ny8NR5UBmcccYSirEEXwwbpU0uPfjp5dzRIBBpU5yXAMsKV+6ma5ZZPShij6xZYjND985RstSTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:46:14.915830Z"},"content_sha256":"e01c65395904c678c05998c83e9add86e5d720705afbc90d4bf141a3f513f688","schema_version":"1.0","event_id":"sha256:e01c65395904c678c05998c83e9add86e5d720705afbc90d4bf141a3f513f688"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EAI2RZYGSRE2UBW42WV2USNMQY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Beomseok Lee, Ioan Calapodescu, Laurent Besacier, Marco Gaido, Matteo Negri","submitted_at":"2024-08-07T16:55:28Z","abstract_excerpt":"We present Speech-MASSIVE, a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus. Speech-MASSIVE covers 12 languages from different families and inherits from MASSIVE the annotations for the intent prediction and slot-filling tasks. Our extension is prompted by the scarcity of massively multilingual SLU datasets and the growing need for versatile speech datasets to assess foundation models (LLMs, speech encoders) across languages and tasks. We provide a multimodal, multitask, multilingual dataset and report SLU "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03900","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/2408.03900/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":"2026-07-05T08:53:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nsiofOzPvW+AuiIW0o3trpNeH6Seye7F/99WQGcmgp64XT9dfDdMkGdhHpEgcfaOd9TvagUJbSdyf0T2b6/rAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:46:14.916331Z"},"content_sha256":"697dd9086864e3800d8c987c638a4b1f000a3855d99d3f3407493d57d79fd57b","schema_version":"1.0","event_id":"sha256:697dd9086864e3800d8c987c638a4b1f000a3855d99d3f3407493d57d79fd57b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EAI2RZYGSRE2UBW42WV2USNMQY/bundle.json","state_url":"https://pith.science/pith/EAI2RZYGSRE2UBW42WV2USNMQY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EAI2RZYGSRE2UBW42WV2USNMQY/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":"2026-08-12T12:46:14Z","links":{"resolver":"https://pith.science/pith/EAI2RZYGSRE2UBW42WV2USNMQY","bundle":"https://pith.science/pith/EAI2RZYGSRE2UBW42WV2USNMQY/bundle.json","state":"https://pith.science/pith/EAI2RZYGSRE2UBW42WV2USNMQY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EAI2RZYGSRE2UBW42WV2USNMQY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EAI2RZYGSRE2UBW42WV2USNMQY","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":"f75248ef6cb5da08f6781d33bb07c2bb64e70f065a22169f2827e2b525b30641","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T16:55:28Z","title_canon_sha256":"44d2f00ac38f0e28d432f4973f8df48bfd256400cf34971639e4d54eb5546b03"},"schema_version":"1.0","source":{"id":"2408.03900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03900","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03900v1","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03900","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"pith_short_12","alias_value":"EAI2RZYGSRE2","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"pith_short_16","alias_value":"EAI2RZYGSRE2UBW4","created_at":"2026-07-05T08:53:12Z"},{"alias_kind":"pith_short_8","alias_value":"EAI2RZYG","created_at":"2026-07-05T08:53:12Z"}],"graph_snapshots":[{"event_id":"sha256:697dd9086864e3800d8c987c638a4b1f000a3855d99d3f3407493d57d79fd57b","target":"graph","created_at":"2026-07-05T08:53:12Z","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/2408.03900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Speech-MASSIVE, a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus. Speech-MASSIVE covers 12 languages from different families and inherits from MASSIVE the annotations for the intent prediction and slot-filling tasks. Our extension is prompted by the scarcity of massively multilingual SLU datasets and the growing need for versatile speech datasets to assess foundation models (LLMs, speech encoders) across languages and tasks. We provide a multimodal, multitask, multilingual dataset and report SLU ","authors_text":"Beomseok Lee, Ioan Calapodescu, Laurent Besacier, Marco Gaido, Matteo Negri","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T16:55:28Z","title":"Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03900","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:e01c65395904c678c05998c83e9add86e5d720705afbc90d4bf141a3f513f688","target":"record","created_at":"2026-07-05T08:53:12Z","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":"f75248ef6cb5da08f6781d33bb07c2bb64e70f065a22169f2827e2b525b30641","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-07T16:55:28Z","title_canon_sha256":"44d2f00ac38f0e28d432f4973f8df48bfd256400cf34971639e4d54eb5546b03"},"schema_version":"1.0","source":{"id":"2408.03900","kind":"arxiv","version":1}},"canonical_sha256":"2011a8e7069449aa06dcd5abaa49ac860ec3d11239de08e19bc6345b4b06b1b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2011a8e7069449aa06dcd5abaa49ac860ec3d11239de08e19bc6345b4b06b1b0","first_computed_at":"2026-07-05T08:53:12.563086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:12.563086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l42pw/CYlwqkCwujO+KwjGFjfaq0Fh1Qm2h7P0RfkR3PkW9jS6Hv3JqnqwS8DtFcTy27B85Jv2KADT7J6rCQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:12.563456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e01c65395904c678c05998c83e9add86e5d720705afbc90d4bf141a3f513f688","sha256:697dd9086864e3800d8c987c638a4b1f000a3855d99d3f3407493d57d79fd57b"],"state_sha256":"75047f5082f3406657b0eade039c12f7b76fb150035b98b38f951f7abf9498dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJ17lhDHZEwYQohi+Grx35S5ilsvvHI1u5jvqpj5DcQzTLahfYtgMb8f9Q5PrOFOWyuRGLp9Zh9iZ1rb8LV7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:46:14.920985Z","bundle_sha256":"6b6277371e58ced179a6f7c6116e1c96930ea5dcfd73b7b4ee460d22ee8a7563"}}