{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M5W3C4ZBXXQIQQ32QBV2OYTLKD","short_pith_number":"pith:M5W3C4ZB","canonical_record":{"source":{"id":"2402.13723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-21T11:35:19Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"8b35a73408868b2ac64e554ded64f58e3087afb4596f523e6318216fe84dd774","abstract_canon_sha256":"0946c1fb7eb2c6b2c21f91fc7fee20d158495e8dd1d59bd3c744f0f2d4b69b18"},"schema_version":"1.0"},"canonical_sha256":"676db17321bde088437a806ba7626b50c6ca1467b61033c08476765c66ea42ac","source":{"kind":"arxiv","id":"2402.13723","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13723","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13723v1","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13723","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"pith_short_12","alias_value":"M5W3C4ZBXXQI","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"pith_short_16","alias_value":"M5W3C4ZBXXQIQQ32","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"pith_short_8","alias_value":"M5W3C4ZB","created_at":"2026-07-05T07:47:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M5W3C4ZBXXQIQQ32QBV2OYTLKD","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-21T11:35:19Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"8b35a73408868b2ac64e554ded64f58e3087afb4596f523e6318216fe84dd774","abstract_canon_sha256":"0946c1fb7eb2c6b2c21f91fc7fee20d158495e8dd1d59bd3c744f0f2d4b69b18"},"schema_version":"1.0"},"canonical_sha256":"676db17321bde088437a806ba7626b50c6ca1467b61033c08476765c66ea42ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:48.065387Z","signature_b64":"qnElGGi6Tx1TztKvmSJnFUEV8+U/x54m2FzvEQez9NZfzfsn8x5UB1p+kxt7LlgF242sWeMuMp8hfTN/Qdb7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"676db17321bde088437a806ba7626b50c6ca1467b61033c08476765c66ea42ac","last_reissued_at":"2026-07-05T07:47:48.064945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:48.064945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13723","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":"2026-07-05T07:47:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GipEHhdBQ8nzVyRg83dSyEVvGaPO9Yn0qBXwoyM0DMEF9r9sb3kQ6435UbfwAFvXZSCjh/0fEsYhmj60j4RoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:26:23.788835Z"},"content_sha256":"6d3b5eed47adbc5ebda8d9ae44aafea223cc10de944a17b59acc974f06be3b3d","schema_version":"1.0","event_id":"sha256:6d3b5eed47adbc5ebda8d9ae44aafea223cc10de944a17b59acc974f06be3b3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M5W3C4ZBXXQIQQ32QBV2OYTLKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"David A. van Leeuwen, Nik Vaessen","submitted_at":"2024-02-21T11:35:19Z","abstract_excerpt":"Foundation models in speech are often trained using many GPUs, which implicitly leads to large effective batch sizes. In this paper we study the effect of batch size on pre-training, both in terms of statistics that can be monitored during training, and in the effect on the performance of a downstream fine-tuning task. By using batch sizes varying from 87.5 seconds to 80 minutes of speech we show that, for a fixed amount of iterations, larger batch sizes result in better pre-trained models. However, there is lower limit for stability, and an upper limit for effectiveness. We then show that the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13723","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/2402.13723/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":"2026-07-05T07:47:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wW50ylDypo0bUpqox9oxdMkau3bWP10r7+RH6sxnUxQOvhPRUL2uJoyHcMxqZMiQT9C1b7GpHWolkiVPQEs0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:26:23.789835Z"},"content_sha256":"95437fbb9512bcab6ca6beb1e81c572e45ff11e7f4977cc3ccc9c24840f39a35","schema_version":"1.0","event_id":"sha256:95437fbb9512bcab6ca6beb1e81c572e45ff11e7f4977cc3ccc9c24840f39a35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5W3C4ZBXXQIQQ32QBV2OYTLKD/bundle.json","state_url":"https://pith.science/pith/M5W3C4ZBXXQIQQ32QBV2OYTLKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5W3C4ZBXXQIQQ32QBV2OYTLKD/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":"2026-08-13T03:26:23Z","links":{"resolver":"https://pith.science/pith/M5W3C4ZBXXQIQQ32QBV2OYTLKD","bundle":"https://pith.science/pith/M5W3C4ZBXXQIQQ32QBV2OYTLKD/bundle.json","state":"https://pith.science/pith/M5W3C4ZBXXQIQQ32QBV2OYTLKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5W3C4ZBXXQIQQ32QBV2OYTLKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M5W3C4ZBXXQIQQ32QBV2OYTLKD","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":"0946c1fb7eb2c6b2c21f91fc7fee20d158495e8dd1d59bd3c744f0f2d4b69b18","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-21T11:35:19Z","title_canon_sha256":"8b35a73408868b2ac64e554ded64f58e3087afb4596f523e6318216fe84dd774"},"schema_version":"1.0","source":{"id":"2402.13723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13723","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13723v1","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13723","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"pith_short_12","alias_value":"M5W3C4ZBXXQI","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"pith_short_16","alias_value":"M5W3C4ZBXXQIQQ32","created_at":"2026-07-05T07:47:48Z"},{"alias_kind":"pith_short_8","alias_value":"M5W3C4ZB","created_at":"2026-07-05T07:47:48Z"}],"graph_snapshots":[{"event_id":"sha256:95437fbb9512bcab6ca6beb1e81c572e45ff11e7f4977cc3ccc9c24840f39a35","target":"graph","created_at":"2026-07-05T07:47:48Z","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/2402.13723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models in speech are often trained using many GPUs, which implicitly leads to large effective batch sizes. In this paper we study the effect of batch size on pre-training, both in terms of statistics that can be monitored during training, and in the effect on the performance of a downstream fine-tuning task. By using batch sizes varying from 87.5 seconds to 80 minutes of speech we show that, for a fixed amount of iterations, larger batch sizes result in better pre-trained models. However, there is lower limit for stability, and an upper limit for effectiveness. We then show that the","authors_text":"David A. van Leeuwen, Nik Vaessen","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-21T11:35:19Z","title":"The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13723","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":"sha256:6d3b5eed47adbc5ebda8d9ae44aafea223cc10de944a17b59acc974f06be3b3d","target":"record","created_at":"2026-07-05T07:47:48Z","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":"0946c1fb7eb2c6b2c21f91fc7fee20d158495e8dd1d59bd3c744f0f2d4b69b18","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-21T11:35:19Z","title_canon_sha256":"8b35a73408868b2ac64e554ded64f58e3087afb4596f523e6318216fe84dd774"},"schema_version":"1.0","source":{"id":"2402.13723","kind":"arxiv","version":1}},"canonical_sha256":"676db17321bde088437a806ba7626b50c6ca1467b61033c08476765c66ea42ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"676db17321bde088437a806ba7626b50c6ca1467b61033c08476765c66ea42ac","first_computed_at":"2026-07-05T07:47:48.064945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:48.064945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qnElGGi6Tx1TztKvmSJnFUEV8+U/x54m2FzvEQez9NZfzfsn8x5UB1p+kxt7LlgF242sWeMuMp8hfTN/Qdb7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:48.065387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d3b5eed47adbc5ebda8d9ae44aafea223cc10de944a17b59acc974f06be3b3d","sha256:95437fbb9512bcab6ca6beb1e81c572e45ff11e7f4977cc3ccc9c24840f39a35"],"state_sha256":"e1fd9af46882258dc6d70aee821db2b9900e8410926e1ce5e7d56544e43a68ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MH9OArNJP+sweDfBLESBn4xOWzohSpyW9xPDqo0krjc+kuAYFL4enPpO+FQuohDgpweqnyailSYu4Gr6BQqJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T03:26:23.794944Z","bundle_sha256":"b8ba879cb3397c40e5910bb90d26c7a186cc2be10771beb959e01c221fac1a7c"}}