{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BR6EX6PUAYZFSGITCPAO7G5VOO","short_pith_number":"pith:BR6EX6PU","canonical_record":{"source":{"id":"2210.11078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T08:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"a6c89c446ce7dfceaf8b2fe6491e471d53d08aff33000fc551ca7837406aeb67","abstract_canon_sha256":"df44a7b51bb4a55ba415cdede954c040eea10c028c1a0a325c1c41cf599f83b9"},"schema_version":"1.0"},"canonical_sha256":"0c7c4bf9f4063259191313c0ef9bb5739040dbf8c435b5f478bd16f4c51b2576","source":{"kind":"arxiv","id":"2210.11078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11078","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11078v1","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11078","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"BR6EX6PUAYZF","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"BR6EX6PUAYZFSGIT","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"BR6EX6PU","created_at":"2026-07-05T05:08:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BR6EX6PUAYZFSGITCPAO7G5VOO","target":"record","payload":{"canonical_record":{"source":{"id":"2210.11078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T08:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"a6c89c446ce7dfceaf8b2fe6491e471d53d08aff33000fc551ca7837406aeb67","abstract_canon_sha256":"df44a7b51bb4a55ba415cdede954c040eea10c028c1a0a325c1c41cf599f83b9"},"schema_version":"1.0"},"canonical_sha256":"0c7c4bf9f4063259191313c0ef9bb5739040dbf8c435b5f478bd16f4c51b2576","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:44.032830Z","signature_b64":"/TCIXMon/nZyt/9/OTXlV+BVEhKgCl6fyK48l4X4OMPkml1YE2CatZPZ4k+Thd89V29SOJy9z8wSQt/Lx6MRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c7c4bf9f4063259191313c0ef9bb5739040dbf8c435b5f478bd16f4c51b2576","last_reissued_at":"2026-07-05T05:08:44.032443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:44.032443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.11078","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":"2026-07-05T05:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKSp1ure+9myrfrgfzXyT255Oxr07GTUylgI95rcZe39WBxwJOnCzyZQ+TDG8oXn96F/io184FS6BlbuMa1yAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:49:01.669900Z"},"content_sha256":"7d1e334c93c77b0ce220d1a986427039f59397a99b53820e346b26333c951609","schema_version":"1.0","event_id":"sha256:7d1e334c93c77b0ce220d1a986427039f59397a99b53820e346b26333c951609"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BR6EX6PUAYZFSGITCPAO7G5VOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-batch Optimization for Dense Visual Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Jianming Liang, Liang Chen, Ping Luo, Yu Liu, Zeyue Xue, Zhuofan Zong","submitted_at":"2022-10-20T08:11:52Z","abstract_excerpt":"Training a large-scale deep neural network in a large-scale dataset is challenging and time-consuming. The recent breakthrough of large-batch optimization is a promising way to tackle this challenge. However, although the current advanced algorithms such as LARS and LAMB succeed in classification models, the complicated pipelines of dense visual predictions such as object detection and segmentation still suffer from the heavy performance drop in the large-batch training regime. To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11078","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/2210.11078/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":"2026-07-05T05:08:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M4p8GiZGkq3Yot9LlVsLU8l1p33s04fzWSZ0lq/PB4kdVjmBmw4irh5GQhoN6PL6MNENCRv1lhK7mYLvz6QoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:49:01.670273Z"},"content_sha256":"c7903a22bd500e7988bc73b7f4dfa5df11f3873d09d2b48cb16ce426e494d4f9","schema_version":"1.0","event_id":"sha256:c7903a22bd500e7988bc73b7f4dfa5df11f3873d09d2b48cb16ce426e494d4f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BR6EX6PUAYZFSGITCPAO7G5VOO/bundle.json","state_url":"https://pith.science/pith/BR6EX6PUAYZFSGITCPAO7G5VOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BR6EX6PUAYZFSGITCPAO7G5VOO/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":"2026-07-07T14:49:01Z","links":{"resolver":"https://pith.science/pith/BR6EX6PUAYZFSGITCPAO7G5VOO","bundle":"https://pith.science/pith/BR6EX6PUAYZFSGITCPAO7G5VOO/bundle.json","state":"https://pith.science/pith/BR6EX6PUAYZFSGITCPAO7G5VOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BR6EX6PUAYZFSGITCPAO7G5VOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BR6EX6PUAYZFSGITCPAO7G5VOO","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":"df44a7b51bb4a55ba415cdede954c040eea10c028c1a0a325c1c41cf599f83b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T08:11:52Z","title_canon_sha256":"a6c89c446ce7dfceaf8b2fe6491e471d53d08aff33000fc551ca7837406aeb67"},"schema_version":"1.0","source":{"id":"2210.11078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11078","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11078v1","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11078","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"BR6EX6PUAYZF","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"BR6EX6PUAYZFSGIT","created_at":"2026-07-05T05:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"BR6EX6PU","created_at":"2026-07-05T05:08:44Z"}],"graph_snapshots":[{"event_id":"sha256:c7903a22bd500e7988bc73b7f4dfa5df11f3873d09d2b48cb16ce426e494d4f9","target":"graph","created_at":"2026-07-05T05:08:44Z","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/2210.11078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a large-scale deep neural network in a large-scale dataset is challenging and time-consuming. The recent breakthrough of large-batch optimization is a promising way to tackle this challenge. However, although the current advanced algorithms such as LARS and LAMB succeed in classification models, the complicated pipelines of dense visual predictions such as object detection and segmentation still suffer from the heavy performance drop in the large-batch training regime. To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (A","authors_text":"Guanglu Song, Jianming Liang, Liang Chen, Ping Luo, Yu Liu, Zeyue Xue, Zhuofan Zong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T08:11:52Z","title":"Large-batch Optimization for Dense Visual Predictions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11078","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":"sha256:7d1e334c93c77b0ce220d1a986427039f59397a99b53820e346b26333c951609","target":"record","created_at":"2026-07-05T05:08:44Z","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":"df44a7b51bb4a55ba415cdede954c040eea10c028c1a0a325c1c41cf599f83b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T08:11:52Z","title_canon_sha256":"a6c89c446ce7dfceaf8b2fe6491e471d53d08aff33000fc551ca7837406aeb67"},"schema_version":"1.0","source":{"id":"2210.11078","kind":"arxiv","version":1}},"canonical_sha256":"0c7c4bf9f4063259191313c0ef9bb5739040dbf8c435b5f478bd16f4c51b2576","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c7c4bf9f4063259191313c0ef9bb5739040dbf8c435b5f478bd16f4c51b2576","first_computed_at":"2026-07-05T05:08:44.032443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:44.032443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/TCIXMon/nZyt/9/OTXlV+BVEhKgCl6fyK48l4X4OMPkml1YE2CatZPZ4k+Thd89V29SOJy9z8wSQt/Lx6MRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:44.032830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d1e334c93c77b0ce220d1a986427039f59397a99b53820e346b26333c951609","sha256:c7903a22bd500e7988bc73b7f4dfa5df11f3873d09d2b48cb16ce426e494d4f9"],"state_sha256":"edcf793cd046b99b106271c79380ad3b28c75015f8ce992875bc2dec1cd54a11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lmjA4XG1JQFUj3FZ2o6fETOeBXfh8aAD2yH/rKf8/lQJ4W34S30vQVtHJMXI4tvJxLXW+8UBYAwWF4+Ck2StCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:49:01.672225Z","bundle_sha256":"bfe630cff8f4caf86e0a8271ada9a1e1409d027ad7bdfa702835371d0e9ebf39"}}