{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:P3ZKMQR36M6DEYDELXYZGD5OFW","short_pith_number":"pith:P3ZKMQR3","canonical_record":{"source":{"id":"2605.13084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:54:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"819ec47c8b639955dab995be59e4b81aa6f67ca948b7ebe86dd4f99e050cbe68","abstract_canon_sha256":"ae20b59064df3d7aaf7e96c58e01c79853d6e44341b05df94792f8eb3e9c6693"},"schema_version":"1.0"},"canonical_sha256":"7ef2a6423bf33c3260645df1930fae2da1fa51c3e868975ed9e188745bfac7fc","source":{"kind":"arxiv","id":"2605.13084","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13084","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13084v2","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13084","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"P3ZKMQR36M6D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"P3ZKMQR36M6DEYDE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"P3ZKMQR3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:P3ZKMQR36M6DEYDELXYZGD5OFW","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:54:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"819ec47c8b639955dab995be59e4b81aa6f67ca948b7ebe86dd4f99e050cbe68","abstract_canon_sha256":"ae20b59064df3d7aaf7e96c58e01c79853d6e44341b05df94792f8eb3e9c6693"},"schema_version":"1.0"},"canonical_sha256":"7ef2a6423bf33c3260645df1930fae2da1fa51c3e868975ed9e188745bfac7fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:58.585270Z","signature_b64":"IW57wRdMAUYoK8ZA8/4EJn/Utg5w0A+qm3qYoR9jJCRUWiqQfrDMwlKn4my/dejU3H2+6myAJRXA8JJRIEo3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ef2a6423bf33c3260645df1930fae2da1fa51c3e868975ed9e188745bfac7fc","last_reissued_at":"2026-05-18T03:08:58.584523Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:58.584523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13084","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":"2026-05-18T03:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfzq8jdZWDHtXMRj+r4dv2jUO3Q/iBmfBE/w+MyFpOYwq52+17O+GiN5fpjcThHpRmJAXcpZBJ+ePioUCLNQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:53:39.599424Z"},"content_sha256":"e203a01012b62e4820359d8e18daf61e665417e1d5c809515e5f0a2d61381236","schema_version":"1.0","event_id":"sha256:e203a01012b62e4820359d8e18daf61e665417e1d5c809515e5f0a2d61381236"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:P3ZKMQR36M6DEYDELXYZGD5OFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does language matter for spoken word classification? A multilingual generative meta-learning approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multilingual spoken word classification shows only small gains over monolingual models, with training data volume outweighing language count.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Batsirayi Mupamhi Ziki, Louise Beyers, Ruan van der Merwe","submitted_at":"2026-05-13T06:54:51Z","abstract_excerpt":"Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the meta-learning approach remains under-explored in multilingual spoken word classification. In this paper, we apply the Generative Meta-Continual Learning algorithm to spoken word classification. The generative nature of this algorithm makes it viable for use in application, and the meta-learning aspect promotes generalisation, which is crucial in a multilingual setting. We train monolingual models on English, German, French, and Catalan, a bilingual "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We find that although the multilingual model performs best, the differences between model performance is unexpectedly low. We also find that the hours of unique data seen during training seems to be a stronger performance indicator than the number of languages included in the training data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Generative Meta-Continual Learning algorithm transfers effectively to multilingual spoken word classification without requiring language-specific modifications or additional regularization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Multilingual generative meta-learning for spoken word classification shows small gains over monolingual models, with unique data volume mattering more than the number of languages.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multilingual spoken word classification shows only small gains over monolingual models, with training data volume outweighing language count.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"dab6a85a302be302746d0062288fdc7460f2d62c6ba4355e965a8d0061c81af8"},"source":{"id":"2605.13084","kind":"arxiv","version":2},"verdict":{"id":"f910f401-2bfe-4939-b80f-c1d3fd9d0582","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:54:36.066802Z","strongest_claim":"We find that although the multilingual model performs best, the differences between model performance is unexpectedly low. We also find that the hours of unique data seen during training seems to be a stronger performance indicator than the number of languages included in the training data.","one_line_summary":"Multilingual generative meta-learning for spoken word classification shows small gains over monolingual models, with unique data volume mattering more than the number of languages.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Generative Meta-Continual Learning algorithm transfers effectively to multilingual spoken word classification without requiring language-specific modifications or additional regularization.","pith_extraction_headline":"Multilingual spoken word classification shows only small gains over monolingual models, with training data volume outweighing language count."},"references":{"count":41,"sample":[{"doi":"","year":2021,"title":"Proceedings of the 35th International Conference on Neural Information Processing Systems , articleno =","work_id":"ba172f7f-115d-4529-a696-2c624e30eec3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Three types of incremental learning , volume =","work_id":"ed810d98-e4c9-4071-915f-9b9f23e35e11","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) , year=","work_id":"4bb07d75-2642-47b6-b043-5da3121b3043","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units , year=","work_id":"60e12a71-d941-4bc4-a38e-c79e672fb181","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Proceedings of the 34th International Conference on Neural Information Processing Systems , articleno =","work_id":"b5321801-7023-4fb8-adfd-73aaca01f9cc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"3f78750290661403f614a66cdaab6d04b4e82864dfcce1b78932547a89bac9ce","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":"f910f401-2bfe-4939-b80f-c1d3fd9d0582"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GP2AW+JxgHQ+xg9V8i4m1Dv1Zvp5bne8cmPhAap64kKeRwvx9sLNTaWSR0pIWd98lybPhuIdl5PYBQ9nFnNbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:53:39.600494Z"},"content_sha256":"49d7da50fb7b1bc3a6ecf005b78d097e32e6c94f249723441db25fa474ac2e17","schema_version":"1.0","event_id":"sha256:49d7da50fb7b1bc3a6ecf005b78d097e32e6c94f249723441db25fa474ac2e17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3ZKMQR36M6DEYDELXYZGD5OFW/bundle.json","state_url":"https://pith.science/pith/P3ZKMQR36M6DEYDELXYZGD5OFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3ZKMQR36M6DEYDELXYZGD5OFW/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":"2026-05-29T19:53:39Z","links":{"resolver":"https://pith.science/pith/P3ZKMQR36M6DEYDELXYZGD5OFW","bundle":"https://pith.science/pith/P3ZKMQR36M6DEYDELXYZGD5OFW/bundle.json","state":"https://pith.science/pith/P3ZKMQR36M6DEYDELXYZGD5OFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3ZKMQR36M6DEYDELXYZGD5OFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P3ZKMQR36M6DEYDELXYZGD5OFW","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":"ae20b59064df3d7aaf7e96c58e01c79853d6e44341b05df94792f8eb3e9c6693","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:54:51Z","title_canon_sha256":"819ec47c8b639955dab995be59e4b81aa6f67ca948b7ebe86dd4f99e050cbe68"},"schema_version":"1.0","source":{"id":"2605.13084","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13084","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13084v2","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13084","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"P3ZKMQR36M6D","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"P3ZKMQR36M6DEYDE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"P3ZKMQR3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:49d7da50fb7b1bc3a6ecf005b78d097e32e6c94f249723441db25fa474ac2e17","target":"graph","created_at":"2026-05-18T03:08:58Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We find that although the multilingual model performs best, the differences between model performance is unexpectedly low. We also find that the hours of unique data seen during training seems to be a stronger performance indicator than the number of languages included in the training data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the Generative Meta-Continual Learning algorithm transfers effectively to multilingual spoken word classification without requiring language-specific modifications or additional regularization."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Multilingual generative meta-learning for spoken word classification shows small gains over monolingual models, with unique data volume mattering more than the number of languages."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multilingual spoken word classification shows only small gains over monolingual models, with training data volume outweighing language count."}],"snapshot_sha256":"dab6a85a302be302746d0062288fdc7460f2d62c6ba4355e965a8d0061c81af8"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the meta-learning approach remains under-explored in multilingual spoken word classification. In this paper, we apply the Generative Meta-Continual Learning algorithm to spoken word classification. The generative nature of this algorithm makes it viable for use in application, and the meta-learning aspect promotes generalisation, which is crucial in a multilingual setting. We train monolingual models on English, German, French, and Catalan, a bilingual ","authors_text":"Batsirayi Mupamhi Ziki, Louise Beyers, Ruan van der Merwe","cross_cats":["cs.AI"],"headline":"Multilingual spoken word classification shows only small gains over monolingual models, with training data volume outweighing language count.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:54:51Z","title":"Does language matter for spoken word classification? A multilingual generative meta-learning approach"},"references":{"count":41,"internal_anchors":0,"resolved_work":41,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Proceedings of the 35th International Conference on Neural Information Processing Systems , articleno =","work_id":"ba172f7f-115d-4529-a696-2c624e30eec3","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Three types of incremental learning , volume =","work_id":"ed810d98-e4c9-4071-915f-9b9f23e35e11","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) , year=","work_id":"4bb07d75-2642-47b6-b043-5da3121b3043","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units , year=","work_id":"60e12a71-d941-4bc4-a38e-c79e672fb181","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Proceedings of the 34th International Conference on Neural Information Processing Systems , articleno =","work_id":"b5321801-7023-4fb8-adfd-73aaca01f9cc","year":2020}],"snapshot_sha256":"3f78750290661403f614a66cdaab6d04b4e82864dfcce1b78932547a89bac9ce"},"source":{"id":"2605.13084","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T05:54:36.066802Z","id":"f910f401-2bfe-4939-b80f-c1d3fd9d0582","model_set":{"reader":"grok-4.3"},"one_line_summary":"Multilingual generative meta-learning for spoken word classification shows small gains over monolingual models, with unique data volume mattering more than the number of languages.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multilingual spoken word classification shows only small gains over monolingual models, with training data volume outweighing language count.","strongest_claim":"We find that although the multilingual model performs best, the differences between model performance is unexpectedly low. We also find that the hours of unique data seen during training seems to be a stronger performance indicator than the number of languages included in the training data.","weakest_assumption":"That the Generative Meta-Continual Learning algorithm transfers effectively to multilingual spoken word classification without requiring language-specific modifications or additional regularization."}},"verdict_id":"f910f401-2bfe-4939-b80f-c1d3fd9d0582"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e203a01012b62e4820359d8e18daf61e665417e1d5c809515e5f0a2d61381236","target":"record","created_at":"2026-05-18T03:08:58Z","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":"ae20b59064df3d7aaf7e96c58e01c79853d6e44341b05df94792f8eb3e9c6693","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:54:51Z","title_canon_sha256":"819ec47c8b639955dab995be59e4b81aa6f67ca948b7ebe86dd4f99e050cbe68"},"schema_version":"1.0","source":{"id":"2605.13084","kind":"arxiv","version":2}},"canonical_sha256":"7ef2a6423bf33c3260645df1930fae2da1fa51c3e868975ed9e188745bfac7fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ef2a6423bf33c3260645df1930fae2da1fa51c3e868975ed9e188745bfac7fc","first_computed_at":"2026-05-18T03:08:58.584523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:58.584523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IW57wRdMAUYoK8ZA8/4EJn/Utg5w0A+qm3qYoR9jJCRUWiqQfrDMwlKn4my/dejU3H2+6myAJRXA8JJRIEo3Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:58.585270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13084","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e203a01012b62e4820359d8e18daf61e665417e1d5c809515e5f0a2d61381236","sha256:49d7da50fb7b1bc3a6ecf005b78d097e32e6c94f249723441db25fa474ac2e17"],"state_sha256":"3595b58f0d9930aacef57a2c17dac91dac4fdcd43ed42407253c2096c07b8080"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2oyboLYETlJRFgkLe0cM3kcXpMu+Il/6tjQSpLeed0f1IDRHTKPHD3jHswF7Nl1eEUgSwLbdYpMcfIThQoR6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:53:39.604429Z","bundle_sha256":"b85743354ebb8ea2fb421c5b9709297e923cc85a602fdf4034f6bb193e014b73"}}