{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G3Q7HJ45BGXLNGYCHZJMLNJQUZ","short_pith_number":"pith:G3Q7HJ45","canonical_record":{"source":{"id":"2005.02008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T08:47:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2bca48b4062def0ded5bca187766f056e256e7bd9929cd76ff01801b4f2ab054","abstract_canon_sha256":"b1b7b7df96c4ac765e7a9fc0ae3d52931d04e9262a459593252141b916b6cb56"},"schema_version":"1.0"},"canonical_sha256":"36e1f3a79d09aeb69b023e52c5b530a669d36cd410b46eaea93fcb238a67f7ec","source":{"kind":"arxiv","id":"2005.02008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.02008","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2005.02008v1","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02008","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"G3Q7HJ45BGXL","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"G3Q7HJ45BGXLNGYC","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"G3Q7HJ45","created_at":"2026-07-05T01:00:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G3Q7HJ45BGXLNGYCHZJMLNJQUZ","target":"record","payload":{"canonical_record":{"source":{"id":"2005.02008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T08:47:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2bca48b4062def0ded5bca187766f056e256e7bd9929cd76ff01801b4f2ab054","abstract_canon_sha256":"b1b7b7df96c4ac765e7a9fc0ae3d52931d04e9262a459593252141b916b6cb56"},"schema_version":"1.0"},"canonical_sha256":"36e1f3a79d09aeb69b023e52c5b530a669d36cd410b46eaea93fcb238a67f7ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:21.788247Z","signature_b64":"wT2h8KWTH6RV36Ch0oBIVfj45/SgsKvRo1iRpmX6A+WZDhS5MIUuedaag6N/xP2sDKbqwSRyAz7x/EAPEkDGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36e1f3a79d09aeb69b023e52c5b530a669d36cd410b46eaea93fcb238a67f7ec","last_reissued_at":"2026-07-05T01:00:21.787887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:21.787887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.02008","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":"2026-07-05T01:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E1m/Prk8ISdTv9z7qmKkbX7/AU93KYBe1zWTUydbUrZpf1tblS4EsitH/+7AodZdj9CUSoJ0DnLGin9JN0zECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:13:29.119530Z"},"content_sha256":"e378358a1af964b4a67217e9dc27acd5d59016fb0ff82856ce368a1e2f06f70d","schema_version":"1.0","event_id":"sha256:e378358a1af964b4a67217e9dc27acd5d59016fb0ff82856ce368a1e2f06f70d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G3Q7HJ45BGXLNGYCHZJMLNJQUZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Hongfei Xu, Josef van Genabith, Qiuhui Liu","submitted_at":"2020-05-05T08:47:34Z","abstract_excerpt":"The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the learning rate, comparatively few papers concentrate on the effect of batch size. In this paper, we analyze how increasing batch size affects gradient direction, and propose to evaluate the stability of gradients with their angle change. Based on our observations, the angle change of gradient direction first tends to stabilize (i.e. gradually decrease) while accu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02008","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/2005.02008/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":"2026-07-05T01:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nko9LEQn1n1HqbdSttMTP49HmGBoImh/NTVSLXfKhr1fD6dA2BjYqPqHIQZFL9mofsd+qJtDiqwkIzXqBq+1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:13:29.120641Z"},"content_sha256":"a2ca30b761a8f56dec1f2f088cb0e1e1d5f7596cf0cb5c100843a7e9bbc721c1","schema_version":"1.0","event_id":"sha256:a2ca30b761a8f56dec1f2f088cb0e1e1d5f7596cf0cb5c100843a7e9bbc721c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3Q7HJ45BGXLNGYCHZJMLNJQUZ/bundle.json","state_url":"https://pith.science/pith/G3Q7HJ45BGXLNGYCHZJMLNJQUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3Q7HJ45BGXLNGYCHZJMLNJQUZ/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":"2026-08-19T11:13:29Z","links":{"resolver":"https://pith.science/pith/G3Q7HJ45BGXLNGYCHZJMLNJQUZ","bundle":"https://pith.science/pith/G3Q7HJ45BGXLNGYCHZJMLNJQUZ/bundle.json","state":"https://pith.science/pith/G3Q7HJ45BGXLNGYCHZJMLNJQUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3Q7HJ45BGXLNGYCHZJMLNJQUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G3Q7HJ45BGXLNGYCHZJMLNJQUZ","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":"b1b7b7df96c4ac765e7a9fc0ae3d52931d04e9262a459593252141b916b6cb56","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T08:47:34Z","title_canon_sha256":"2bca48b4062def0ded5bca187766f056e256e7bd9929cd76ff01801b4f2ab054"},"schema_version":"1.0","source":{"id":"2005.02008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.02008","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2005.02008v1","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02008","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"G3Q7HJ45BGXL","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"G3Q7HJ45BGXLNGYC","created_at":"2026-07-05T01:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"G3Q7HJ45","created_at":"2026-07-05T01:00:21Z"}],"graph_snapshots":[{"event_id":"sha256:a2ca30b761a8f56dec1f2f088cb0e1e1d5f7596cf0cb5c100843a7e9bbc721c1","target":"graph","created_at":"2026-07-05T01:00:21Z","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/2005.02008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The choice of hyper-parameters affects the performance of neural models. While much previous research (Sutskever et al., 2013; Duchi et al., 2011; Kingma and Ba, 2015) focuses on accelerating convergence and reducing the effects of the learning rate, comparatively few papers concentrate on the effect of batch size. In this paper, we analyze how increasing batch size affects gradient direction, and propose to evaluate the stability of gradients with their angle change. Based on our observations, the angle change of gradient direction first tends to stabilize (i.e. gradually decrease) while accu","authors_text":"Deyi Xiong, Hongfei Xu, Josef van Genabith, Qiuhui Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T08:47:34Z","title":"Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02008","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:e378358a1af964b4a67217e9dc27acd5d59016fb0ff82856ce368a1e2f06f70d","target":"record","created_at":"2026-07-05T01:00:21Z","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":"b1b7b7df96c4ac765e7a9fc0ae3d52931d04e9262a459593252141b916b6cb56","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T08:47:34Z","title_canon_sha256":"2bca48b4062def0ded5bca187766f056e256e7bd9929cd76ff01801b4f2ab054"},"schema_version":"1.0","source":{"id":"2005.02008","kind":"arxiv","version":1}},"canonical_sha256":"36e1f3a79d09aeb69b023e52c5b530a669d36cd410b46eaea93fcb238a67f7ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36e1f3a79d09aeb69b023e52c5b530a669d36cd410b46eaea93fcb238a67f7ec","first_computed_at":"2026-07-05T01:00:21.787887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:21.787887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wT2h8KWTH6RV36Ch0oBIVfj45/SgsKvRo1iRpmX6A+WZDhS5MIUuedaag6N/xP2sDKbqwSRyAz7x/EAPEkDGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:21.788247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.02008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e378358a1af964b4a67217e9dc27acd5d59016fb0ff82856ce368a1e2f06f70d","sha256:a2ca30b761a8f56dec1f2f088cb0e1e1d5f7596cf0cb5c100843a7e9bbc721c1"],"state_sha256":"7cc7b1687405b0ffe8e3e18c9561e9dcbcbd456fdc9f8fc48e3db11a629e20bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3wooglDvxW+6KX50smK5uSnb5HWk5wzH+7tO3laNvtqFMaUyKJun3cR6GbjHpdjlRuzDyWYnUui5a9HK7JcBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:13:29.127790Z","bundle_sha256":"513bfafe91505b1bcc6b2d135cd8b5583cf728c1e8bb45e6f6c9d40c66342566"}}