{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YRTVKMRPQ5BRNASUFO6HUDJPIJ","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":"49609323773799ff264f47980d2f9727e84d15a4be70175d90f84afd9a58be3b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:47:57Z","title_canon_sha256":"44cbf462fbadec377a16ff436dc7ea50a00f39f82ae324857a2621d7a9506804"},"schema_version":"1.0","source":{"id":"2605.13075","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13075","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13075v2","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13075","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"YRTVKMRPQ5BR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YRTVKMRPQ5BRNASU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YRTVKMRP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:72c60bb603eb4b2f7dc8fdd52665bc302991715f27fd4427cc64b4233e377c7c","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":"GeMCL produces exceptionally stable performance, and although it does not always outperform a repeatedly fully-finetuned HuBERT model nor a frozen HuBERT model with a repeatedly trained classifier head, it produces comparable performance to the latter while adapting 2000 times faster, having been trained less than half of the data for two orders of magnitude less time."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the generative component of GeMCL sufficiently prevents catastrophic forgetting when the number of sequential classes reaches 1000, without the need for task-specific hyperparameter retuning or additional regularization beyond what is described."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GeMCL scales few-shot spoken word classification to 1000 classes with 5 shots each, matching frozen-HuBERT baseline performance while adapting 2000 times faster on less than half the data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Generative meta-continual learning scales few-shot spoken word classification to 1000 classes while matching strong baselines at far lower adaptation cost."}],"snapshot_sha256":"366dd0a1b9b3ee4f5cfa66f7b74c3c839042c0e88928e942a2d2793024d6a785"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Few-shot spoken word classification has largely been developed for applications where a small number of classes is considered, and so the potential of larger-scale few-shot spoken word classification remains untapped. This paper investigates the potential of a spoken word classifier to sequentially learn to distinguish between 1000 classes when it is given only five shots per class. We demonstrate that this scaling capability exists by training a model using the Generative Meta-Continual Learning (GeMCL) algorithm and comparing it to repeatedly trained or finetuned baselines. We find that GeMC","authors_text":"Batsirayi Mupamhi Ziki, Louise Beyers, Ruan van der Merwe","cross_cats":["cs.AI"],"headline":"Generative meta-continual learning scales few-shot spoken word classification to 1000 classes while matching strong baselines at far lower adaptation cost.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:47:57Z","title":"Scaling few-shot spoken word classification with generative meta-continual learning"},"references":{"count":27,"internal_anchors":0,"resolved_work":27,"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":"333a1544bc137041e981d670469685e1e21572d080117666ea43cf4d17b7a2af"},"source":{"id":"2605.13075","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T05:59:08.722142Z","id":"0be2f0cc-e57e-49ff-8786-0ba4b1e0d7b9","model_set":{"reader":"grok-4.3"},"one_line_summary":"GeMCL scales few-shot spoken word classification to 1000 classes with 5 shots each, matching frozen-HuBERT baseline performance while adapting 2000 times faster on less than half the data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Generative meta-continual learning scales few-shot spoken word classification to 1000 classes while matching strong baselines at far lower adaptation cost.","strongest_claim":"GeMCL produces exceptionally stable performance, and although it does not always outperform a repeatedly fully-finetuned HuBERT model nor a frozen HuBERT model with a repeatedly trained classifier head, it produces comparable performance to the latter while adapting 2000 times faster, having been trained less than half of the data for two orders of magnitude less time.","weakest_assumption":"That the generative component of GeMCL sufficiently prevents catastrophic forgetting when the number of sequential classes reaches 1000, without the need for task-specific hyperparameter retuning or additional regularization beyond what is described."}},"verdict_id":"0be2f0cc-e57e-49ff-8786-0ba4b1e0d7b9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c8359c08c55050c940451c0977f359fbbcdb2fc63a2c786e42b27e60489e7fb9","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":"49609323773799ff264f47980d2f9727e84d15a4be70175d90f84afd9a58be3b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T06:47:57Z","title_canon_sha256":"44cbf462fbadec377a16ff436dc7ea50a00f39f82ae324857a2621d7a9506804"},"schema_version":"1.0","source":{"id":"2605.13075","kind":"arxiv","version":2}},"canonical_sha256":"c46755322f87431682542bbc7a0d2f424e6546ccc54c0b2fa778e00d00aaa448","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c46755322f87431682542bbc7a0d2f424e6546ccc54c0b2fa778e00d00aaa448","first_computed_at":"2026-05-18T03:08:58.789616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:58.789616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5sdoFaZL6tjIfq01jz0uHxfKEtH5p0iuJ1Xh7UVl4KjyqWRR5+DCXBCGDuQDkvjwznUN2EZFbTUaPQ4fuKpCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:58.790211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13075","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8359c08c55050c940451c0977f359fbbcdb2fc63a2c786e42b27e60489e7fb9","sha256:72c60bb603eb4b2f7dc8fdd52665bc302991715f27fd4427cc64b4233e377c7c"],"state_sha256":"b8f967c6b5998957b2c99779b400dc3af44f1f8c7434acb4097c8b4a5e1cf6d1"}