{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CRRF5QNMVU34KDTNCEMI4KGMST","short_pith_number":"pith:CRRF5QNM","canonical_record":{"source":{"id":"2402.11215","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-17T07:49:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"2f8681f3206479b7ebdef4d85113197e1b077b523cf65e00af8eeea3dbf345e2","abstract_canon_sha256":"1019988c3e37a1fdeac0c3e4f731b7347e182883675569b952f140ace9d56213"},"schema_version":"1.0"},"canonical_sha256":"14625ec1acad37c50e6d11188e28cc94eeda781237811cee8402c0a99fe1325b","source":{"kind":"arxiv","id":"2402.11215","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11215","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11215v3","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11215","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"CRRF5QNMVU34","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"CRRF5QNMVU34KDTN","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"CRRF5QNM","created_at":"2026-07-05T08:24:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CRRF5QNMVU34KDTNCEMI4KGMST","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11215","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-17T07:49:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"2f8681f3206479b7ebdef4d85113197e1b077b523cf65e00af8eeea3dbf345e2","abstract_canon_sha256":"1019988c3e37a1fdeac0c3e4f731b7347e182883675569b952f140ace9d56213"},"schema_version":"1.0"},"canonical_sha256":"14625ec1acad37c50e6d11188e28cc94eeda781237811cee8402c0a99fe1325b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:02.076542Z","signature_b64":"muxXADYa8u4NlygVSKkuauYnWmX6lZrfs+rkQ3SDifpDX/480PJ6NA4EaKBX/LSgEm3kHl/yCLGb6IC2BtQ5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14625ec1acad37c50e6d11188e28cc94eeda781237811cee8402c0a99fe1325b","last_reissued_at":"2026-07-05T08:24:02.076014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:02.076014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11215","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:24:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WhYwr2nwQ/wEqDcGyO5dPMNy7z1ED/3xdxMXyMe+XAVrfyPG+sQdqieHcwm5yCplg+rhFk/1NmKZFzGt5wJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:06:32.592484Z"},"content_sha256":"9cc6b6abb24c6e1fa2560ea509a9684ccb4406cbfbdf4ba3a73a824ef08974c9","schema_version":"1.0","event_id":"sha256:9cc6b6abb24c6e1fa2560ea509a9684ccb4406cbfbdf4ba3a73a824ef08974c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CRRF5QNMVU34KDTNCEMI4KGMST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Liu, Mladen Kolar, Tim Tsz-Kit Lau","submitted_at":"2024-02-17T07:49:50Z","abstract_excerpt":"The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance. Although large-batch training is arguably the dominant training paradigm for large-scale deep learning due to hardware advances, the generalization performance of the model deteriorates compared to small-batch training, leading to the so-called \"generalization gap\" phenomenon. To mitigate this, we investigate adaptive batch size strategies derived from adaptive sampling methods, originally developed only for stochastic gradient de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11215","kind":"arxiv","version":3},"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/2402.11215/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":"2026-07-05T08:24:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nSftCwmrFrPk92P3Ar36sav0HUrLJRzs2/Yh1KH4DLop8TIU88ZHTuVY7r3JYvkn43moyYgJbkjM/3i6Mq7iBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T21:06:32.593037Z"},"content_sha256":"89f0287678f89a932f8f6c3707ed79b70f7dd115c8f2a4728c734027e658c1bc","schema_version":"1.0","event_id":"sha256:89f0287678f89a932f8f6c3707ed79b70f7dd115c8f2a4728c734027e658c1bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRRF5QNMVU34KDTNCEMI4KGMST/bundle.json","state_url":"https://pith.science/pith/CRRF5QNMVU34KDTNCEMI4KGMST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRRF5QNMVU34KDTNCEMI4KGMST/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":"2026-08-20T21:06:32Z","links":{"resolver":"https://pith.science/pith/CRRF5QNMVU34KDTNCEMI4KGMST","bundle":"https://pith.science/pith/CRRF5QNMVU34KDTNCEMI4KGMST/bundle.json","state":"https://pith.science/pith/CRRF5QNMVU34KDTNCEMI4KGMST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRRF5QNMVU34KDTNCEMI4KGMST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CRRF5QNMVU34KDTNCEMI4KGMST","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":"1019988c3e37a1fdeac0c3e4f731b7347e182883675569b952f140ace9d56213","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-17T07:49:50Z","title_canon_sha256":"2f8681f3206479b7ebdef4d85113197e1b077b523cf65e00af8eeea3dbf345e2"},"schema_version":"1.0","source":{"id":"2402.11215","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11215","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11215v3","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11215","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"CRRF5QNMVU34","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"CRRF5QNMVU34KDTN","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"CRRF5QNM","created_at":"2026-07-05T08:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:89f0287678f89a932f8f6c3707ed79b70f7dd115c8f2a4728c734027e658c1bc","target":"graph","created_at":"2026-07-05T08:24:02Z","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/2402.11215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance. Although large-batch training is arguably the dominant training paradigm for large-scale deep learning due to hardware advances, the generalization performance of the model deteriorates compared to small-batch training, leading to the so-called \"generalization gap\" phenomenon. To mitigate this, we investigate adaptive batch size strategies derived from adaptive sampling methods, originally developed only for stochastic gradient de","authors_text":"Han Liu, Mladen Kolar, Tim Tsz-Kit Lau","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-17T07:49:50Z","title":"AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11215","kind":"arxiv","version":3},"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":"sha256:9cc6b6abb24c6e1fa2560ea509a9684ccb4406cbfbdf4ba3a73a824ef08974c9","target":"record","created_at":"2026-07-05T08:24:02Z","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":"1019988c3e37a1fdeac0c3e4f731b7347e182883675569b952f140ace9d56213","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-17T07:49:50Z","title_canon_sha256":"2f8681f3206479b7ebdef4d85113197e1b077b523cf65e00af8eeea3dbf345e2"},"schema_version":"1.0","source":{"id":"2402.11215","kind":"arxiv","version":3}},"canonical_sha256":"14625ec1acad37c50e6d11188e28cc94eeda781237811cee8402c0a99fe1325b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14625ec1acad37c50e6d11188e28cc94eeda781237811cee8402c0a99fe1325b","first_computed_at":"2026-07-05T08:24:02.076014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:02.076014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"muxXADYa8u4NlygVSKkuauYnWmX6lZrfs+rkQ3SDifpDX/480PJ6NA4EaKBX/LSgEm3kHl/yCLGb6IC2BtQ5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:02.076542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11215","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cc6b6abb24c6e1fa2560ea509a9684ccb4406cbfbdf4ba3a73a824ef08974c9","sha256:89f0287678f89a932f8f6c3707ed79b70f7dd115c8f2a4728c734027e658c1bc"],"state_sha256":"f6a37ef979020ceca0a5c93ff865559cf36a4cb163800dde0ecaf8b582ebbd9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rvvkQqRCAI8XBlN/v8uiKdMvghxfEYBD1wRxcX8JQOgXrdLleyaGC5MyKoOLszWJtBIftqYl+AuqTzlZPNiBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T21:06:32.598825Z","bundle_sha256":"284b195acc49ecfdc8dd67dbac46a02628e6d0819398cbd8c301d7865c6b921c"}}