{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7N4BBHOTOFDRZZ33TH2JNZETO6","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":"13243897dcd64089bf4a68047357218e113c265fc280f33dc27326a3336e06ab","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-09T10:36:42Z","title_canon_sha256":"051ab7a43fc1402aca076bd50ce67c7d57bdf4a60effb2c5f4a30cd65cb1c2c6"},"schema_version":"1.0","source":{"id":"2409.16295","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16295","created_at":"2026-07-05T10:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16295v2","created_at":"2026-07-05T10:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16295","created_at":"2026-07-05T10:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"7N4BBHOTOFDR","created_at":"2026-07-05T10:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"7N4BBHOTOFDRZZ33","created_at":"2026-07-05T10:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"7N4BBHOT","created_at":"2026-07-05T10:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:823967d7a2cbd0e715ac924e69eed5c9d71dd13b69f06bc0a7d9724aef3390a6","target":"graph","created_at":"2026-07-05T10:09:48Z","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/2409.16295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their impressive success, training foundation models remains computationally costly. This paper investigates how to efficiently train speech foundation models with self-supervised learning (SSL) under a limited compute budget. We examine critical factors in SSL that impact the budget, including model architecture, model size, and data size. Our goal is to make analytical steps toward understanding the training dynamics of speech foundation models. We benchmark SSL objectives in an entirely comparable setting and find that other factors contribute more significantly to the success of SS","authors_text":"Andy T. Liu, Haibin Wu, Hung-yi Lee, Stefan Winkler, Yi-Cheng Lin","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-09T10:36:42Z","title":"Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16295","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:dede668857529bc9aa09850407e62d0ebcc33c277fa737e773bd4685d7421f81","target":"record","created_at":"2026-07-05T10:09:48Z","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":"13243897dcd64089bf4a68047357218e113c265fc280f33dc27326a3336e06ab","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-09T10:36:42Z","title_canon_sha256":"051ab7a43fc1402aca076bd50ce67c7d57bdf4a60effb2c5f4a30cd65cb1c2c6"},"schema_version":"1.0","source":{"id":"2409.16295","kind":"arxiv","version":2}},"canonical_sha256":"fb78109dd371471ce77b99f496e493779d5a2d4bcb92a21bab1a1eb43349aae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb78109dd371471ce77b99f496e493779d5a2d4bcb92a21bab1a1eb43349aae4","first_computed_at":"2026-07-05T10:09:48.018466Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:48.018466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8vXu5oyXDOr9dqUD2ddODFvtePcRojb1BelhYcoVRF5Ha2KzA7p8WfPhym2LlUa8fkhyZnEKOsr5zKzOm1LnCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:48.018928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16295","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dede668857529bc9aa09850407e62d0ebcc33c277fa737e773bd4685d7421f81","sha256:823967d7a2cbd0e715ac924e69eed5c9d71dd13b69f06bc0a7d9724aef3390a6"],"state_sha256":"7f70ca199b388dd37850c8df808cd638287dd64792edd9952648472e9d9fd7bd"}